├── LICENSE ├── README.md ├── caffe3d ├── CMakeLists.txt ├── CONTRIBUTING.md ├── CONTRIBUTORS.md ├── INSTALL.md ├── LICENSE ├── Makefile ├── Makefile.config ├── Makefile.config.example ├── README-original.md ├── README.md ├── caffe.cloc ├── cmake │ ├── ConfigGen.cmake │ ├── Cuda.cmake │ ├── Dependencies.cmake │ ├── External │ │ ├── gflags.cmake │ │ └── glog.cmake │ ├── Misc.cmake │ ├── Modules │ │ ├── FindAtlas.cmake │ │ ├── FindGFlags.cmake │ │ ├── FindGlog.cmake │ │ ├── FindLAPACK.cmake │ │ ├── FindLMDB.cmake │ │ ├── FindLevelDB.cmake │ │ ├── FindMKL.cmake │ │ ├── FindMatlabMex.cmake │ │ ├── FindNumPy.cmake │ │ ├── FindOpenBLAS.cmake │ │ ├── FindSnappy.cmake │ │ └── FindvecLib.cmake │ ├── ProtoBuf.cmake │ ├── Summary.cmake │ ├── Targets.cmake │ ├── Templates │ │ ├── CaffeConfig.cmake.in │ │ ├── CaffeConfigVersion.cmake.in │ │ └── caffe_config.h.in │ ├── Utils.cmake │ └── lint.cmake ├── data │ ├── cifar10 │ │ └── get_cifar10.sh │ ├── ilsvrc12 │ │ └── get_ilsvrc_aux.sh │ └── mnist │ │ └── get_mnist.sh ├── docker │ ├── Makefile │ ├── README.md │ ├── standalone │ │ ├── cpu │ │ │ └── Dockerfile │ │ └── gpu │ │ │ └── Dockerfile │ └── templates │ │ └── Dockerfile.template ├── docs │ ├── CMakeLists.txt │ ├── CNAME │ ├── README.md │ ├── _config.yml │ ├── _layouts │ │ └── default.html │ ├── development.md │ ├── images │ │ ├── GitHub-Mark-64px.png │ │ └── caffeine-icon.png │ ├── index.md │ ├── install_apt.md │ ├── install_osx.md │ ├── install_yum.md │ ├── installation.md │ ├── model_zoo.md │ ├── multigpu.md │ ├── performance_hardware.md │ ├── stylesheets │ │ ├── pygment_trac.css │ │ ├── reset.css │ │ └── styles.css │ └── tutorial │ │ ├── convolution.md │ │ ├── data.md │ │ ├── fig │ │ ├── backward.jpg │ │ ├── forward.jpg │ │ ├── forward_backward.png │ │ ├── layer.jpg │ │ └── logreg.jpg │ │ ├── forward_backward.md │ │ ├── index.md │ │ ├── interfaces.md │ │ ├── layers.md │ │ ├── loss.md │ │ ├── net_layer_blob.md │ │ └── solver.md ├── examples │ ├── 00-classification.ipynb │ ├── 01-learning-lenet.ipynb │ ├── 02-fine-tuning.ipynb │ ├── CMakeLists.txt │ ├── brewing-logreg.ipynb │ ├── c3d_finetune │ │ ├── README.md │ │ ├── c3d_ucf101_deploy.prototxt │ │ ├── c3d_ucf101_solver.prototxt │ │ ├── c3d_ucf101_test.log │ │ ├── c3d_ucf101_test.prototxt │ │ ├── c3d_ucf101_train_test.prototxt │ │ ├── check_data_and_model.py │ │ ├── convert_npy_to_binaryproto.py │ │ ├── feature_extraction │ │ │ ├── extract_c3d_features.sh │ │ │ └── read_binary_blob.m │ │ ├── test_01.lst │ │ ├── test_ucf101.sh │ │ ├── train_ucf101.sh │ │ ├── ucf101_mean.npy │ │ └── ucf101_train_mean.binaryproto │ ├── c3d_ucf101 │ │ ├── README.md │ │ ├── c3d_ucf101_deploy.prototxt │ │ ├── c3d_ucf101_solver.prototxt │ │ ├── c3d_ucf101_test.log │ │ ├── c3d_ucf101_test.prototxt │ │ ├── c3d_ucf101_test_split1.txt │ │ ├── c3d_ucf101_train_loss_accuracy.png │ │ ├── c3d_ucf101_train_split1.txt │ │ ├── c3d_ucf101_train_test.prototxt │ │ ├── check_data_and_model.py │ │ ├── extract_UCF-101_frames.sh │ │ ├── feature_extraction │ │ │ ├── extract_c3d_features.sh │ │ │ └── read_binary_blob.m │ │ ├── test_ucf101.sh │ │ ├── train_ucf101.sh │ │ └── ucf101_train_mean.binaryproto │ ├── cifar10 │ │ ├── cifar10_full.prototxt │ │ ├── cifar10_full_sigmoid_solver.prototxt │ │ ├── cifar10_full_sigmoid_solver_bn.prototxt │ │ ├── cifar10_full_sigmoid_train_test.prototxt │ │ ├── cifar10_full_sigmoid_train_test_bn.prototxt │ │ ├── cifar10_full_solver.prototxt │ │ ├── cifar10_full_solver_lr1.prototxt │ │ ├── cifar10_full_solver_lr2.prototxt │ │ ├── cifar10_full_train_test.prototxt │ │ ├── cifar10_quick.prototxt │ │ ├── cifar10_quick_solver.prototxt │ │ ├── cifar10_quick_solver_lr1.prototxt │ │ ├── cifar10_quick_train_test.prototxt │ │ ├── convert_cifar_data.cpp │ │ ├── create_cifar10.sh │ │ ├── readme.md │ │ ├── train_full.sh │ │ ├── train_full_sigmoid.sh │ │ ├── train_full_sigmoid_bn.sh │ │ └── train_quick.sh │ ├── cpp_classification │ │ ├── classification.cpp │ │ └── readme.md │ ├── detection.ipynb │ ├── feature_extraction │ │ ├── imagenet_val.prototxt │ │ └── readme.md │ ├── finetune_flickr_style │ │ ├── assemble_data.py │ │ ├── flickr_style.csv.gz │ │ ├── readme.md │ │ └── style_names.txt │ ├── finetune_pascal_detection │ │ ├── pascal_finetune_solver.prototxt │ │ └── pascal_finetune_trainval_test.prototxt │ ├── hdf5_classification │ │ ├── nonlinear_auto_test.prototxt │ │ ├── nonlinear_auto_train.prototxt │ │ ├── nonlinear_train_val.prototxt │ │ └── train_val.prototxt │ ├── imagenet │ │ ├── create_imagenet.sh │ │ ├── make_imagenet_mean.sh │ │ ├── readme.md │ │ ├── resume_training.sh │ │ └── train_caffenet.sh │ ├── images │ │ ├── cat gray.jpg │ │ ├── cat.jpg │ │ ├── cat_gray.jpg │ │ └── fish-bike.jpg │ ├── mnist │ │ ├── convert_mnist_data.cpp │ │ ├── create_mnist.sh │ │ ├── lenet.prototxt │ │ ├── lenet_adadelta_solver.prototxt │ │ ├── lenet_auto_solver.prototxt │ │ ├── lenet_consolidated_solver.prototxt │ │ ├── lenet_multistep_solver.prototxt │ │ ├── lenet_solver.prototxt │ │ ├── lenet_solver_adam.prototxt │ │ ├── lenet_solver_rmsprop.prototxt │ │ ├── lenet_train_test.prototxt │ │ ├── mnist_autoencoder.prototxt │ │ ├── mnist_autoencoder_solver.prototxt │ │ ├── mnist_autoencoder_solver_adadelta.prototxt │ │ ├── mnist_autoencoder_solver_adagrad.prototxt │ │ ├── mnist_autoencoder_solver_nesterov.prototxt │ │ ├── readme.md │ │ ├── train_lenet.sh │ │ ├── train_lenet_adam.sh │ │ ├── train_lenet_consolidated.sh │ │ ├── train_lenet_docker.sh │ │ ├── train_lenet_rmsprop.sh │ │ ├── train_mnist_autoencoder.sh │ │ ├── train_mnist_autoencoder_adadelta.sh │ │ ├── train_mnist_autoencoder_adagrad.sh │ │ └── train_mnist_autoencoder_nesterov.sh │ ├── net_surgery.ipynb │ ├── net_surgery │ │ ├── bvlc_caffenet_full_conv.prototxt │ │ └── conv.prototxt │ ├── pascal-multilabel-with-datalayer.ipynb │ ├── pycaffe │ │ ├── caffenet.py │ │ ├── layers │ │ │ ├── pascal_multilabel_datalayers.py │ │ │ └── pyloss.py │ │ ├── linreg.prototxt │ │ └── tools.py │ ├── siamese │ │ ├── convert_mnist_siamese_data.cpp │ │ ├── create_mnist_siamese.sh │ │ ├── mnist_siamese.ipynb │ │ ├── mnist_siamese.prototxt │ │ ├── mnist_siamese_solver.prototxt │ │ ├── mnist_siamese_solver.prototxt~ │ │ ├── mnist_siamese_train_test.prototxt │ │ ├── readme.md │ │ └── train_mnist_siamese.sh │ ├── siamese_origin │ │ ├── convert_mnist_siamese_data.cpp │ │ ├── create_mnist_siamese.sh │ │ ├── mnist_siamese.ipynb │ │ ├── mnist_siamese.prototxt │ │ ├── mnist_siamese_solver.prototxt │ │ ├── mnist_siamese_solver.prototxt~ │ │ ├── mnist_siamese_train_test.prototxt │ │ ├── readme.md │ │ └── train_mnist_siamese.sh │ └── web_demo │ │ ├── app.py │ │ ├── exifutil.py │ │ ├── readme.md │ │ ├── requirements.txt │ │ └── templates │ │ └── index.html ├── include │ └── caffe │ │ ├── blob.hpp │ │ ├── caffe.hpp │ │ ├── common.hpp │ │ ├── data_reader.hpp │ │ ├── data_transformer.hpp │ │ ├── filler.hpp │ │ ├── internal_thread.hpp │ │ ├── layer.hpp │ │ ├── layer_factory.hpp │ │ ├── layers │ │ ├── absval_layer.hpp │ │ ├── accuracy_layer.hpp │ │ ├── argmax_layer.hpp │ │ ├── base_conv_layer.hpp │ │ ├── base_data_layer.hpp │ │ ├── batch_norm_layer.hpp │ │ ├── batch_reindex_layer.hpp │ │ ├── bias_layer.hpp │ │ ├── bnll_layer.hpp │ │ ├── concat_layer.hpp │ │ ├── contrastive_loss_layer.hpp │ │ ├── conv_layer.hpp │ │ ├── crop_layer.hpp │ │ ├── cudnn_conv_layer.hpp │ │ ├── cudnn_lcn_layer.hpp │ │ ├── cudnn_lrn_layer.hpp │ │ ├── cudnn_pooling_layer.hpp │ │ ├── cudnn_relu_layer.hpp │ │ ├── cudnn_sigmoid_layer.hpp │ │ ├── cudnn_softmax_layer.hpp │ │ ├── cudnn_tanh_layer.hpp │ │ ├── data_layer.hpp │ │ ├── deconv_layer.hpp │ │ ├── dotproduct_similarity_layer.hpp │ │ ├── dropout_layer.hpp │ │ ├── dummy_data_layer.hpp │ │ ├── eltwise_layer.hpp │ │ ├── elu_layer.hpp │ │ ├── embed_layer.hpp │ │ ├── euclidean_loss_layer.hpp │ │ ├── euclidean_similarity_layer.hpp │ │ ├── exp_layer.hpp │ │ ├── filter_layer.hpp │ │ ├── flatten_layer.hpp │ │ ├── hdf5_data_layer.hpp │ │ ├── hdf5_output_layer.hpp │ │ ├── hinge_loss_layer.hpp │ │ ├── im2col_layer.hpp │ │ ├── image_data_layer.hpp │ │ ├── infogain_loss_layer.hpp │ │ ├── inner_product_layer.hpp │ │ ├── input_layer.hpp │ │ ├── log_layer.hpp │ │ ├── loss_layer.hpp │ │ ├── lp_norm_layer.hpp │ │ ├── lrn_layer.hpp │ │ ├── lstm_layer.hpp │ │ ├── lstm_layer.hpp~ │ │ ├── memory_data_layer.hpp │ │ ├── multinomial_logistic_loss_layer.hpp │ │ ├── mvn_layer.hpp │ │ ├── neuron_layer.hpp │ │ ├── pair_wise_ranking_loss_layer.hpp │ │ ├── parameter_layer.hpp │ │ ├── permute_layer.hpp │ │ ├── pooling_layer.hpp │ │ ├── power_layer.hpp │ │ ├── prelu_layer.hpp │ │ ├── python_layer.hpp │ │ ├── recurrent_layer.hpp │ │ ├── recurrent_layer.hpp~ │ │ ├── reduction_layer.hpp │ │ ├── relu_layer.hpp │ │ ├── reshape_layer.hpp │ │ ├── rnn_layer.hpp │ │ ├── roi_pooling_each_layer.hpp │ │ ├── roi_pooling_layer.hpp │ │ ├── scale_layer.hpp │ │ ├── sigmoid_cross_entropy_loss_layer.hpp │ │ ├── sigmoid_layer.hpp │ │ ├── silence_layer.hpp │ │ ├── similarity_layer.hpp │ │ ├── slice_layer.hpp │ │ ├── smooth_L1_loss_layer.hpp │ │ ├── softmax_layer.hpp │ │ ├── softmax_loss_layer.hpp │ │ ├── split_layer.hpp │ │ ├── spp_layer.hpp │ │ ├── tanh_layer.hpp │ │ ├── threshold_layer.hpp │ │ ├── tile_layer.hpp │ │ ├── video_data_layer.hpp │ │ ├── video_segment_data_layer.hpp │ │ ├── window_data_layer.hpp │ │ └── word_sum_layer.hpp │ │ ├── net.hpp │ │ ├── parallel.hpp │ │ ├── sgd_solvers.hpp │ │ ├── solver.hpp │ │ ├── solver_factory.hpp │ │ ├── syncedmem.hpp │ │ ├── test │ │ ├── test_caffe_main.hpp │ │ └── test_gradient_check_util.hpp │ │ └── util │ │ ├── benchmark.hpp │ │ ├── blocking_queue.hpp │ │ ├── cudnn.hpp │ │ ├── db.hpp │ │ ├── db_leveldb.hpp │ │ ├── db_lmdb.hpp │ │ ├── device_alternate.hpp │ │ ├── format.hpp │ │ ├── gpu_util.cuh │ │ ├── hdf5.hpp │ │ ├── im2col.hpp │ │ ├── image_io.hpp │ │ ├── insert_splits.hpp │ │ ├── io.hpp │ │ ├── math_functions.hpp │ │ ├── mkl_alternate.hpp │ │ ├── rng.hpp │ │ ├── signal_handler.h │ │ └── upgrade_proto.hpp ├── matlab │ ├── +caffe │ │ ├── +test │ │ │ ├── test_io.m │ │ │ ├── test_net.m │ │ │ └── test_solver.m │ │ ├── Blob.m │ │ ├── Layer.m │ │ ├── Net.m │ │ ├── Solver.m │ │ ├── get_net.m │ │ ├── get_solver.m │ │ ├── imagenet │ │ │ └── ilsvrc_2012_mean.mat │ │ ├── io.m │ │ ├── private │ │ │ ├── CHECK.m │ │ │ ├── CHECK_FILE_EXIST.m │ │ │ ├── caffe_.cpp │ │ │ └── is_valid_handle.m │ │ ├── reset_all.m │ │ ├── run_tests.m │ │ ├── set_device.m │ │ ├── set_mode_cpu.m │ │ ├── set_mode_gpu.m │ │ └── version.m │ ├── CMakeLists.txt │ ├── demo │ │ └── classification_demo.m │ └── hdf5creation │ │ ├── demo.m │ │ └── store2hdf5.m ├── models │ ├── bvlc_alexnet │ │ ├── deploy.prototxt │ │ ├── readme.md │ │ ├── solver.prototxt │ │ └── train_val.prototxt │ ├── bvlc_googlenet │ │ ├── deploy.prototxt │ │ ├── quick_solver.prototxt │ │ ├── readme.md │ │ ├── solver.prototxt │ │ └── train_val.prototxt │ ├── bvlc_reference_caffenet │ │ ├── deploy.prototxt │ │ ├── readme.md │ │ ├── solver.prototxt │ │ └── train_val.prototxt │ ├── bvlc_reference_rcnn_ilsvrc13 │ │ ├── deploy.prototxt │ │ └── readme.md │ └── finetune_flickr_style │ │ ├── deploy.prototxt │ │ ├── readme.md │ │ ├── solver.prototxt │ │ └── train_val.prototxt ├── python │ ├── CMakeLists.txt │ ├── caffe │ │ ├── __init__.py │ │ ├── __init__.pyc │ │ ├── _caffe.cpp │ │ ├── classifier.py │ │ ├── classifier.pyc │ │ ├── coord_map.py │ │ ├── detector.py │ │ ├── detector.pyc │ │ ├── draw.py │ │ ├── draw.pyc │ │ ├── imagenet │ │ │ └── ilsvrc_2012_mean.npy │ │ ├── io.py │ │ ├── io.pyc │ │ ├── net_spec.py │ │ ├── net_spec.pyc │ │ ├── pycaffe.py │ │ ├── pycaffe.pyc │ │ └── test │ │ │ ├── test_coord_map.py │ │ │ ├── test_io.py │ │ │ ├── test_layer_type_list.py │ │ │ ├── test_net.py │ │ │ ├── test_net_spec.py │ │ │ ├── test_python_layer.py │ │ │ ├── test_python_layer_with_param_str.py │ │ │ └── test_solver.py │ ├── classify.py │ ├── detect.py │ ├── draw_net.py │ └── requirements.txt ├── scripts │ ├── build_docs.sh │ ├── copy_notebook.py │ ├── cpp_lint.py │ ├── deploy_docs.sh │ ├── download_model_binary.py │ ├── download_model_from_gist.sh │ ├── gather_examples.sh │ ├── travis │ │ ├── build.sh │ │ ├── configure-cmake.sh │ │ ├── configure-make.sh │ │ ├── configure.sh │ │ ├── defaults.sh │ │ ├── install-deps.sh │ │ ├── install-python-deps.sh │ │ ├── setup-venv.sh │ │ └── test.sh │ └── upload_model_to_gist.sh ├── src │ ├── caffe │ │ ├── CMakeLists.txt │ │ ├── blob.cpp │ │ ├── common.cpp │ │ ├── data_reader.cpp │ │ ├── data_transformer.cpp │ │ ├── internal_thread.cpp │ │ ├── layer.cpp │ │ ├── layer_factory.cpp │ │ ├── layers │ │ │ ├── absval_layer.cpp │ │ │ ├── absval_layer.cu │ │ │ ├── accuracy_layer.cpp │ │ │ ├── argmax_layer.cpp │ │ │ ├── base_conv_layer.cpp │ │ │ ├── base_data_layer.cpp │ │ │ ├── base_data_layer.cu │ │ │ ├── batch_norm_layer.cpp │ │ │ ├── batch_norm_layer.cu │ │ │ ├── batch_reindex_layer.cpp │ │ │ ├── batch_reindex_layer.cu │ │ │ ├── bias_layer.cpp │ │ │ ├── bias_layer.cu │ │ │ ├── bnll_layer.cpp │ │ │ ├── bnll_layer.cu │ │ │ ├── concat_layer.cpp │ │ │ ├── concat_layer.cu │ │ │ ├── contrastive_loss_layer.cpp │ │ │ ├── contrastive_loss_layer.cu │ │ │ ├── conv_layer.cpp │ │ │ ├── conv_layer.cu │ │ │ ├── crop_layer.cpp │ │ │ ├── crop_layer.cu │ │ │ ├── cudnn_conv_layer.cpp │ │ │ ├── cudnn_conv_layer.cu │ │ │ ├── cudnn_lcn_layer.cpp │ │ │ ├── cudnn_lcn_layer.cu │ │ │ ├── cudnn_lrn_layer.cpp │ │ │ ├── cudnn_lrn_layer.cu │ │ │ ├── cudnn_pooling_layer.cpp │ │ │ ├── cudnn_pooling_layer.cu │ │ │ ├── cudnn_relu_layer.cpp │ │ │ ├── cudnn_relu_layer.cu │ │ │ ├── cudnn_sigmoid_layer.cpp │ │ │ ├── cudnn_sigmoid_layer.cu │ │ │ ├── cudnn_softmax_layer.cpp │ │ │ ├── cudnn_softmax_layer.cu │ │ │ ├── cudnn_tanh_layer.cpp │ │ │ ├── cudnn_tanh_layer.cu │ │ │ ├── data_layer.cpp │ │ │ ├── deconv_layer.cpp │ │ │ ├── deconv_layer.cu │ │ │ ├── dotproduct_similarity_layer.cpp │ │ │ ├── dotproduct_similarity_layer.cu │ │ │ ├── dropout_layer.cpp │ │ │ ├── dropout_layer.cu │ │ │ ├── dummy_data_layer.cpp │ │ │ ├── eltwise_layer.cpp │ │ │ ├── eltwise_layer.cu │ │ │ ├── elu_layer.cpp │ │ │ ├── elu_layer.cu │ │ │ ├── embed_layer.cpp │ │ │ ├── embed_layer.cu │ │ │ ├── euclidean_loss_layer.cpp │ │ │ ├── euclidean_loss_layer.cu │ │ │ ├── euclidean_similarity_layer.cpp │ │ │ ├── euclidean_similarity_layer.cu │ │ │ ├── exp_layer.cpp │ │ │ ├── exp_layer.cu │ │ │ ├── filter_layer.cpp │ │ │ ├── filter_layer.cu │ │ │ ├── flatten_layer.cpp │ │ │ ├── hdf5_data_layer.cpp │ │ │ ├── hdf5_data_layer.cu │ │ │ ├── hdf5_output_layer.cpp │ │ │ ├── hdf5_output_layer.cu │ │ │ ├── hinge_loss_layer.cpp │ │ │ ├── im2col_layer.cpp │ │ │ ├── im2col_layer.cu │ │ │ ├── image_data_layer.cpp │ │ │ ├── infogain_loss_layer.cpp │ │ │ ├── inner_product_layer.cpp │ │ │ ├── inner_product_layer.cu │ │ │ ├── input_layer.cpp │ │ │ ├── log_layer.cpp │ │ │ ├── log_layer.cu │ │ │ ├── loss_layer.cpp │ │ │ ├── lp_norm_layer.cpp │ │ │ ├── lp_norm_layer.cu │ │ │ ├── lrn_layer.cpp │ │ │ ├── lrn_layer.cu │ │ │ ├── lstm_controller_layer.cpp │ │ │ ├── lstm_layer.cpp │ │ │ ├── lstm_topic_layer.cpp │ │ │ ├── lstm_unit_layer.cpp │ │ │ ├── lstm_unit_layer.cu │ │ │ ├── memory_data_layer.cpp │ │ │ ├── multinomial_logistic_loss_layer.cpp │ │ │ ├── mvn_layer.cpp │ │ │ ├── mvn_layer.cu │ │ │ ├── neuron_layer.cpp │ │ │ ├── pairwise_ranking_loss_layer.cpp │ │ │ ├── parameter_layer.cpp │ │ │ ├── permute_layer.cpp │ │ │ ├── permute_layer.cu │ │ │ ├── pooling_layer.cpp │ │ │ ├── pooling_layer.cu │ │ │ ├── power_layer.cpp │ │ │ ├── power_layer.cu │ │ │ ├── prelu_layer.cpp │ │ │ ├── prelu_layer.cu │ │ │ ├── recurrent_layer.cpp │ │ │ ├── recurrent_layer.cu │ │ │ ├── reduction_layer.cpp │ │ │ ├── reduction_layer.cu │ │ │ ├── relu_layer.cpp │ │ │ ├── relu_layer.cu │ │ │ ├── reshape_layer.cpp │ │ │ ├── rnn_layer.cpp │ │ │ ├── roi_pooling_each_layer.cpp │ │ │ ├── roi_pooling_each_layer.cu │ │ │ ├── roi_pooling_layer.cpp │ │ │ ├── roi_pooling_layer.cu │ │ │ ├── scale_layer.cpp │ │ │ ├── scale_layer.cu │ │ │ ├── sigmoid_cross_entropy_loss_layer.cpp │ │ │ ├── sigmoid_cross_entropy_loss_layer.cu │ │ │ ├── sigmoid_layer.cpp │ │ │ ├── sigmoid_layer.cu │ │ │ ├── silence_layer.cpp │ │ │ ├── silence_layer.cu │ │ │ ├── similarity_layer.cpp │ │ │ ├── slice_layer.cpp │ │ │ ├── slice_layer.cu │ │ │ ├── smooth_L1_loss_layer.cpp │ │ │ ├── smooth_L1_loss_layer.cu │ │ │ ├── softmax_layer.cpp │ │ │ ├── softmax_layer.cu │ │ │ ├── softmax_loss_layer.cpp │ │ │ ├── softmax_loss_layer.cu │ │ │ ├── split_layer.cpp │ │ │ ├── split_layer.cu │ │ │ ├── spp_layer.cpp │ │ │ ├── tanh_layer.cpp │ │ │ ├── tanh_layer.cu │ │ │ ├── threshold_layer.cpp │ │ │ ├── threshold_layer.cu │ │ │ ├── tile_layer.cpp │ │ │ ├── tile_layer.cu │ │ │ ├── video_data_layer.cpp │ │ │ ├── video_segment_data_layer.cpp │ │ │ ├── window_data_layer.cpp │ │ │ ├── word_sum_layer.cpp │ │ │ └── word_sum_layer.cu │ │ ├── net.cpp │ │ ├── parallel.cpp │ │ ├── proto │ │ │ ├── caffe.proto │ │ │ └── caffe.proto~ │ │ ├── solver.cpp │ │ ├── solvers │ │ │ ├── adadelta_solver.cpp │ │ │ ├── adadelta_solver.cu │ │ │ ├── adagrad_solver.cpp │ │ │ ├── adagrad_solver.cu │ │ │ ├── adam_solver.cpp │ │ │ ├── adam_solver.cu │ │ │ ├── nesterov_solver.cpp │ │ │ ├── nesterov_solver.cu │ │ │ ├── rmsprop_solver.cpp │ │ │ ├── rmsprop_solver.cu │ │ │ ├── sgd_solver.cpp │ │ │ └── sgd_solver.cu │ │ ├── syncedmem.cpp │ │ ├── test │ │ │ ├── CMakeLists.txt │ │ │ ├── test_accuracy_layer.cpp │ │ │ ├── test_argmax_layer.cpp │ │ │ ├── test_batch_norm_layer.cpp │ │ │ ├── test_batch_reindex_layer.cpp │ │ │ ├── test_benchmark.cpp │ │ │ ├── test_bias_layer.cpp │ │ │ ├── test_blob.cpp │ │ │ ├── test_caffe_main.cpp │ │ │ ├── test_common.cpp │ │ │ ├── test_concat_layer.cpp │ │ │ ├── test_contrastive_loss_layer.cpp │ │ │ ├── test_convolution_layer.cpp │ │ │ ├── test_crop_layer.cpp │ │ │ ├── test_data │ │ │ │ ├── UCF-101_Rowing_g16_c03.avi │ │ │ │ ├── generate_sample_data.py │ │ │ │ ├── sample_data.h5 │ │ │ │ ├── sample_data_2_gzip.h5 │ │ │ │ ├── sample_data_list.txt │ │ │ │ ├── solver_data.h5 │ │ │ │ ├── solver_data_list.txt │ │ │ │ └── youtube_objects_dog_v0002_s006 │ │ │ │ │ ├── image_0001.jpg │ │ │ │ │ ├── image_0002.jpg │ │ │ │ │ ├── image_0003.jpg │ │ │ │ │ ├── image_0004.jpg │ │ │ │ │ ├── image_0005.jpg │ │ │ │ │ ├── image_0006.jpg │ │ │ │ │ ├── image_0007.jpg │ │ │ │ │ ├── image_0008.jpg │ │ │ │ │ ├── image_0009.jpg │ │ │ │ │ ├── image_0010.jpg │ │ │ │ │ ├── image_0011.jpg │ │ │ │ │ ├── image_0012.jpg │ │ │ │ │ ├── image_0013.jpg │ │ │ │ │ ├── image_0014.jpg │ │ │ │ │ ├── image_0015.jpg │ │ │ │ │ └── image_0016.jpg │ │ │ ├── test_data_layer.cpp │ │ │ ├── test_data_transformer.cpp │ │ │ ├── test_db.cpp │ │ │ ├── test_deconvolution_layer.cpp │ │ │ ├── test_dummy_data_layer.cpp │ │ │ ├── test_eltwise_layer.cpp │ │ │ ├── test_embed_layer.cpp │ │ │ ├── test_euclidean_loss_layer.cpp │ │ │ ├── test_filler.cpp │ │ │ ├── test_filter_layer.cpp │ │ │ ├── test_flatten_layer.cpp │ │ │ ├── test_gradient_based_solver.cpp │ │ │ ├── test_hdf5_output_layer.cpp │ │ │ ├── test_hdf5data_layer.cpp │ │ │ ├── test_hinge_loss_layer.cpp │ │ │ ├── test_im2col_kernel.cu │ │ │ ├── test_im2col_layer.cpp │ │ │ ├── test_image_data_layer.cpp │ │ │ ├── test_infogain_loss_layer.cpp │ │ │ ├── test_inner_product_layer.cpp │ │ │ ├── test_internal_thread.cpp │ │ │ ├── test_io.cpp │ │ │ ├── test_layer_factory.cpp │ │ │ ├── test_lrn_layer.cpp │ │ │ ├── test_lstm_layer.cpp │ │ │ ├── test_math_functions.cpp │ │ │ ├── test_maxpool_dropout_layers.cpp │ │ │ ├── test_memory_data_layer.cpp │ │ │ ├── test_multinomial_logistic_loss_layer.cpp │ │ │ ├── test_mvn_layer.cpp │ │ │ ├── test_net.cpp │ │ │ ├── test_neuron_layer.cpp │ │ │ ├── test_platform.cpp │ │ │ ├── test_pooling_layer.cpp │ │ │ ├── test_power_layer.cpp │ │ │ ├── test_protobuf.cpp │ │ │ ├── test_random_number_generator.cpp │ │ │ ├── test_reduction_layer.cpp │ │ │ ├── test_reshape_layer.cpp │ │ │ ├── test_rnn_layer.cpp │ │ │ ├── test_roi_pooling_each_layer.cpp │ │ │ ├── test_roi_pooling_layer.cpp │ │ │ ├── test_scale_layer.cpp │ │ │ ├── test_sigmoid_cross_entropy_loss_layer.cpp │ │ │ ├── test_slice_layer.cpp │ │ │ ├── test_softmax_layer.cpp │ │ │ ├── test_softmax_with_loss_layer.cpp │ │ │ ├── test_solver.cpp │ │ │ ├── test_solver_factory.cpp │ │ │ ├── test_split_layer.cpp │ │ │ ├── test_spp_layer.cpp │ │ │ ├── test_stochastic_pooling.cpp │ │ │ ├── test_syncedmem.cpp │ │ │ ├── test_tanh_layer.cpp │ │ │ ├── test_threshold_layer.cpp │ │ │ ├── test_tile_layer.cpp │ │ │ ├── test_upgrade_proto.cpp │ │ │ ├── test_util_blas.cpp │ │ │ └── test_video_data_layer.cpp │ │ └── util │ │ │ ├── benchmark.cpp │ │ │ ├── blocking_queue.cpp │ │ │ ├── cudnn.cpp │ │ │ ├── db.cpp │ │ │ ├── db_leveldb.cpp │ │ │ ├── db_lmdb.cpp │ │ │ ├── hdf5.cpp │ │ │ ├── im2col.cpp │ │ │ ├── im2col.cu │ │ │ ├── image_io.cpp │ │ │ ├── insert_splits.cpp │ │ │ ├── io.cpp │ │ │ ├── math_functions.cpp │ │ │ ├── math_functions.cu │ │ │ ├── signal_handler.cpp │ │ │ └── upgrade_proto.cpp │ └── gtest │ │ ├── CMakeLists.txt │ │ ├── gtest-all.cpp │ │ ├── gtest.h │ │ └── gtest_main.cc └── tools │ ├── CMakeLists.txt │ ├── caffe.cpp │ ├── compute_image_mean.cpp │ ├── convert_imageset.cpp │ ├── device_query.cpp │ ├── extra │ ├── extract_seconds.py │ ├── launch_resize_and_crop_images.sh │ ├── parse_log.py │ ├── parse_log.sh │ ├── plot_log.gnuplot.example │ ├── plot_training_log.py.example │ ├── plot_training_loss.sh │ ├── py_plot_training_loss.py │ ├── resize_and_crop_images.py │ └── summarize.py │ ├── extract_features.cpp │ ├── finetune_net.cpp │ ├── net_speed_benchmark.cpp │ ├── test_net.cpp │ ├── train_net.cpp │ ├── upgrade_net_proto_binary.cpp │ ├── upgrade_net_proto_text.cpp │ └── upgrade_solver_proto_text.cpp ├── experiments ├── Text_to_Clip │ ├── _init_paths.py │ ├── _init_paths.pyc │ ├── script_train.sh │ ├── solver.prototxt │ ├── td_cnn_end2end.yml │ ├── test_fast │ │ ├── _init_paths.py │ │ ├── _init_paths.pyc │ │ ├── evaluation │ │ │ ├── bash.sh │ │ │ ├── evaluation_recall.py │ │ │ └── recall_results_5000.txt │ │ ├── script_test.sh │ │ ├── td_cnn_end2end.yml │ │ ├── test_lstm.prototxt │ │ ├── test_net.py │ │ ├── test_retrieval.prototxt │ │ ├── test_rpn.prototxt │ │ ├── utils.py │ │ └── utils.pyc │ ├── train_lstm.prototxt │ └── train_net.py ├── extract_HDF_for_LSTM │ ├── _init_paths.py │ ├── _init_paths.pyc │ ├── script_test.sh │ ├── td_cnn_end2end.yml │ ├── test_net.py │ ├── test_rpn.prototxt │ ├── utils.py │ └── utils.pyc └── train_rpn │ ├── _init_paths.py │ ├── _init_paths.pyc │ ├── script_train.sh │ ├── solver.prototxt │ ├── td_cnn_end2end.yml │ ├── train.prototxt │ └── train_net.py ├── lib ├── Makefile ├── lstm │ └── lstm_last_hidden_state_layer.py ├── nms │ ├── __init__.py │ ├── __init__.pyc │ ├── cpu_nms.c │ ├── cpu_nms.pyx │ ├── cpu_nms.so │ ├── gpu_nms.cpp │ ├── gpu_nms.hpp │ ├── gpu_nms.pyx │ ├── gpu_nms.so │ ├── nms_kernel.cu │ └── py_cpu_nms.py ├── roi_data_layer │ ├── __init__.py │ ├── __init__.pyc │ ├── layer_caption.py │ ├── layer_caption.pyc │ ├── layer_retrieval_pairwiserank_caption_share.py │ ├── minibatch.py │ ├── minibatch.pyc │ ├── minibatch_caption.py │ ├── minibatch_caption.pyc │ ├── roidb.py │ └── roidb.pyc ├── rpn │ ├── GTbox_sorted.py │ ├── GTbox_sorted.pyc │ ├── GTboxes_to_GTrois.py │ ├── GTboxes_to_GTrois.pyc │ ├── Prepare_Paired_Positive_Negative_Sim.py │ ├── __init__.py │ ├── __init__.pyc │ ├── anchor_target_layer.py │ ├── anchor_target_layer.pyc │ ├── caption_layer.py │ ├── caption_target_layer.py │ ├── generate_anchors.py │ ├── generate_anchors.pyc │ ├── get_controller_hidden_layer.py │ ├── get_controller_hidden_layer.pyc │ ├── gt_caption_target_layer_hierarchical.py │ ├── gt_caption_target_layer_hierarchical.pyc │ ├── pad_controller_layer.py │ ├── pad_controller_layer.pyc │ ├── proposal_layer.py │ ├── proposal_layer.pyc │ └── proposal_target_layer_binary.py ├── setup.py ├── tdcnn │ ├── __init__.py │ ├── __init__.pyc │ ├── config.py │ ├── config.pyc │ ├── nms_wrapper.py │ ├── nms_wrapper.pyc │ ├── test_caption_extract_HDF_for_LSTM.py │ ├── test_caption_hierarchical_fc6ContextEvery_end2end.pyc │ ├── test_retrieval_caption_share_fast.py │ ├── train.py │ ├── train_end2end.pyc │ ├── train_retrieval_pairwiserank_adam_caption.py │ ├── twin_transform.py │ └── twin_transform.pyc └── utils │ ├── __init__.py │ ├── __init__.pyc │ ├── blob.py │ ├── blob.pyc │ ├── caption_generator.py │ ├── caption_generator.pyc │ ├── cython_twin.so │ ├── timer.py │ ├── timer.pyc │ ├── twin.c │ └── twin.pyx └── preprocess ├── caption_gt_test.json ├── caption_gt_train.json ├── generate_roidb_modified_freq1.py ├── generate_roidb_modified_freq1_full_retrieval_test.py └── util_2.py /LICENSE: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2018 VisionLearningGroup 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /caffe3d/CONTRIBUTORS.md: -------------------------------------------------------------------------------- 1 | # Contributors 2 | 3 | Caffe is developed by a core set of BVLC members and the open-source community. 4 | 5 | We thank all of our [contributors](https://github.com/BVLC/caffe/graphs/contributors)! 6 | 7 | **For the detailed history of contributions** of a given file, try 8 | 9 | git blame file 10 | 11 | to see line-by-line credits and 12 | 13 | git log --follow file 14 | 15 | to see the change log even across renames and rewrites. 16 | 17 | Please refer to the [acknowledgements](http://caffe.berkeleyvision.org/#acknowledgements) on the Caffe site for further details. 18 | 19 | **Copyright** is held by the original contributor according to the versioning history; see LICENSE. 20 | -------------------------------------------------------------------------------- /caffe3d/INSTALL.md: -------------------------------------------------------------------------------- 1 | # Installation 2 | 3 | See http://caffe.berkeleyvision.org/installation.html for the latest 4 | installation instructions. 5 | 6 | Check the users group in case you need help: 7 | https://groups.google.com/forum/#!forum/caffe-users 8 | -------------------------------------------------------------------------------- /caffe3d/caffe.cloc: -------------------------------------------------------------------------------- 1 | Bourne Shell 2 | filter remove_matches ^\s*# 3 | filter remove_inline #.*$ 4 | extension sh 5 | script_exe sh 6 | C 7 | filter remove_matches ^\s*// 8 | filter call_regexp_common C 9 | filter remove_inline //.*$ 10 | extension c 11 | extension ec 12 | extension pgc 13 | C++ 14 | filter remove_matches ^\s*// 15 | filter remove_inline //.*$ 16 | filter call_regexp_common C 17 | extension C 18 | extension cc 19 | extension cpp 20 | extension cxx 21 | extension pcc 22 | C/C++ Header 23 | filter remove_matches ^\s*// 24 | filter call_regexp_common C 25 | filter remove_inline //.*$ 26 | extension H 27 | extension h 28 | extension hh 29 | extension hpp 30 | CUDA 31 | filter remove_matches ^\s*// 32 | filter remove_inline //.*$ 33 | filter call_regexp_common C 34 | extension cu 35 | Python 36 | filter remove_matches ^\s*# 37 | filter docstring_to_C 38 | filter call_regexp_common C 39 | filter remove_inline #.*$ 40 | extension py 41 | make 42 | filter remove_matches ^\s*# 43 | filter remove_inline #.*$ 44 | extension Gnumakefile 45 | extension Makefile 46 | extension am 47 | extension gnumakefile 48 | extension makefile 49 | filename Gnumakefile 50 | filename Makefile 51 | filename gnumakefile 52 | filename makefile 53 | script_exe make 54 | -------------------------------------------------------------------------------- /caffe3d/cmake/Modules/FindLMDB.cmake: -------------------------------------------------------------------------------- 1 | # Try to find the LMBD libraries and headers 2 | # LMDB_FOUND - system has LMDB lib 3 | # LMDB_INCLUDE_DIR - the LMDB include directory 4 | # LMDB_LIBRARIES - Libraries needed to use LMDB 5 | 6 | # FindCWD based on FindGMP by: 7 | # Copyright (c) 2006, Laurent Montel, 8 | # 9 | # Redistribution and use is allowed according to the terms of the BSD license. 10 | 11 | # Adapted from FindCWD by: 12 | # Copyright 2013 Conrad Steenberg 13 | # Aug 31, 2013 14 | 15 | find_path(LMDB_INCLUDE_DIR NAMES lmdb.h PATHS "$ENV{LMDB_DIR}/include") 16 | find_library(LMDB_LIBRARIES NAMES lmdb PATHS "$ENV{LMDB_DIR}/lib" ) 17 | 18 | include(FindPackageHandleStandardArgs) 19 | find_package_handle_standard_args(LMDB DEFAULT_MSG LMDB_INCLUDE_DIR LMDB_LIBRARIES) 20 | 21 | if(LMDB_FOUND) 22 | message(STATUS "Found lmdb (include: ${LMDB_INCLUDE_DIR}, library: ${LMDB_LIBRARIES})") 23 | mark_as_advanced(LMDB_INCLUDE_DIR LMDB_LIBRARIES) 24 | 25 | caffe_parse_header(${LMDB_INCLUDE_DIR}/lmdb.h 26 | LMDB_VERSION_LINES MDB_VERSION_MAJOR MDB_VERSION_MINOR MDB_VERSION_PATCH) 27 | set(LMDB_VERSION "${MDB_VERSION_MAJOR}.${MDB_VERSION_MINOR}.${MDB_VERSION_PATCH}") 28 | endif() 29 | -------------------------------------------------------------------------------- /caffe3d/cmake/Modules/FindSnappy.cmake: -------------------------------------------------------------------------------- 1 | # Find the Snappy libraries 2 | # 3 | # The following variables are optionally searched for defaults 4 | # Snappy_ROOT_DIR: Base directory where all Snappy components are found 5 | # 6 | # The following are set after configuration is done: 7 | # SNAPPY_FOUND 8 | # Snappy_INCLUDE_DIR 9 | # Snappy_LIBRARIES 10 | 11 | find_path(Snappy_INCLUDE_DIR NAMES snappy.h 12 | PATHS ${SNAPPY_ROOT_DIR} ${SNAPPY_ROOT_DIR}/include) 13 | 14 | find_library(Snappy_LIBRARIES NAMES snappy 15 | PATHS ${SNAPPY_ROOT_DIR} ${SNAPPY_ROOT_DIR}/lib) 16 | 17 | include(FindPackageHandleStandardArgs) 18 | find_package_handle_standard_args(Snappy DEFAULT_MSG Snappy_INCLUDE_DIR Snappy_LIBRARIES) 19 | 20 | if(SNAPPY_FOUND) 21 | message(STATUS "Found Snappy (include: ${Snappy_INCLUDE_DIR}, library: ${Snappy_LIBRARIES})") 22 | mark_as_advanced(Snappy_INCLUDE_DIR Snappy_LIBRARIES) 23 | 24 | caffe_parse_header(${Snappy_INCLUDE_DIR}/snappy-stubs-public.h 25 | SNAPPY_VERION_LINES SNAPPY_MAJOR SNAPPY_MINOR SNAPPY_PATCHLEVEL) 26 | set(Snappy_VERSION "${SNAPPY_MAJOR}.${SNAPPY_MINOR}.${SNAPPY_PATCHLEVEL}") 27 | endif() 28 | 29 | -------------------------------------------------------------------------------- /caffe3d/cmake/Modules/FindvecLib.cmake: -------------------------------------------------------------------------------- 1 | # Find the vecLib libraries as part of Accelerate.framework or as standalon framework 2 | # 3 | # The following are set after configuration is done: 4 | # VECLIB_FOUND 5 | # vecLib_INCLUDE_DIR 6 | # vecLib_LINKER_LIBS 7 | 8 | 9 | if(NOT APPLE) 10 | return() 11 | endif() 12 | 13 | set(__veclib_include_suffix "Frameworks/vecLib.framework/Versions/Current/Headers") 14 | 15 | find_path(vecLib_INCLUDE_DIR vecLib.h 16 | DOC "vecLib include directory" 17 | PATHS /System/Library/Frameworks/Accelerate.framework/Versions/Current/${__veclib_include_suffix} 18 | /System/Library/${__veclib_include_suffix} 19 | /Applications/Xcode.app/Contents/Developer/Platforms/MacOSX.platform/Developer/SDKs/MacOSX10.9.sdk/System/Library/Frameworks/Accelerate.framework/Versions/Current/Frameworks/vecLib.framework/Headers/ 20 | NO_DEFAULT_PATH) 21 | 22 | include(FindPackageHandleStandardArgs) 23 | find_package_handle_standard_args(vecLib DEFAULT_MSG vecLib_INCLUDE_DIR) 24 | 25 | if(VECLIB_FOUND) 26 | if(vecLib_INCLUDE_DIR MATCHES "^/System/Library/Frameworks/vecLib.framework.*") 27 | set(vecLib_LINKER_LIBS -lcblas "-framework vecLib") 28 | message(STATUS "Found standalone vecLib.framework") 29 | else() 30 | set(vecLib_LINKER_LIBS -lcblas "-framework Accelerate") 31 | message(STATUS "Found vecLib as part of Accelerate.framework") 32 | endif() 33 | 34 | mark_as_advanced(vecLib_INCLUDE_DIR) 35 | endif() 36 | -------------------------------------------------------------------------------- /caffe3d/cmake/Templates/CaffeConfigVersion.cmake.in: -------------------------------------------------------------------------------- 1 | set(PACKAGE_VERSION "@Caffe_VERSION@") 2 | 3 | # Check whether the requested PACKAGE_FIND_VERSION is compatible 4 | if("${PACKAGE_VERSION}" VERSION_LESS "${PACKAGE_FIND_VERSION}") 5 | set(PACKAGE_VERSION_COMPATIBLE FALSE) 6 | else() 7 | set(PACKAGE_VERSION_COMPATIBLE TRUE) 8 | if ("${PACKAGE_VERSION}" VERSION_EQUAL "${PACKAGE_FIND_VERSION}") 9 | set(PACKAGE_VERSION_EXACT TRUE) 10 | endif() 11 | endif() 12 | -------------------------------------------------------------------------------- /caffe3d/cmake/Templates/caffe_config.h.in: -------------------------------------------------------------------------------- 1 | /* Sources directory */ 2 | #define SOURCE_FOLDER "${PROJECT_SOURCE_DIR}" 3 | 4 | /* Binaries directory */ 5 | #define BINARY_FOLDER "${PROJECT_BINARY_DIR}" 6 | 7 | /* NVIDA Cuda */ 8 | #cmakedefine HAVE_CUDA 9 | 10 | /* NVIDA cuDNN */ 11 | #cmakedefine HAVE_CUDNN 12 | #cmakedefine USE_CUDNN 13 | 14 | /* NVIDA cuDNN */ 15 | #cmakedefine CPU_ONLY 16 | 17 | /* Test device */ 18 | #define CUDA_TEST_DEVICE ${CUDA_TEST_DEVICE} 19 | 20 | /* Temporary (TODO: remove) */ 21 | #if 1 22 | #define CMAKE_SOURCE_DIR SOURCE_FOLDER "/src/" 23 | #define EXAMPLES_SOURCE_DIR BINARY_FOLDER "/examples/" 24 | #define CMAKE_EXT ".gen.cmake" 25 | #else 26 | #define CMAKE_SOURCE_DIR "src/" 27 | #define EXAMPLES_SOURCE_DIR "examples/" 28 | #define CMAKE_EXT "" 29 | #endif 30 | 31 | /* Matlab */ 32 | #cmakedefine HAVE_MATLAB 33 | 34 | /* IO libraries */ 35 | #cmakedefine USE_OPENCV 36 | #cmakedefine USE_LEVELDB 37 | #cmakedefine USE_LMDB 38 | #cmakedefine ALLOW_LMDB_NOLOCK 39 | -------------------------------------------------------------------------------- /caffe3d/data/cifar10/get_cifar10.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | # This scripts downloads the CIFAR10 (binary version) data and unzips it. 3 | 4 | DIR="$( cd "$(dirname "$0")" ; pwd -P )" 5 | cd "$DIR" 6 | 7 | echo "Downloading..." 8 | 9 | wget --no-check-certificate http://www.cs.toronto.edu/~kriz/cifar-10-binary.tar.gz 10 | 11 | echo "Unzipping..." 12 | 13 | tar -xf cifar-10-binary.tar.gz && rm -f cifar-10-binary.tar.gz 14 | mv cifar-10-batches-bin/* . && rm -rf cifar-10-batches-bin 15 | 16 | # Creation is split out because leveldb sometimes causes segfault 17 | # and needs to be re-created. 18 | 19 | echo "Done." 20 | -------------------------------------------------------------------------------- /caffe3d/data/ilsvrc12/get_ilsvrc_aux.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | # 3 | # N.B. This does not download the ilsvrcC12 data set, as it is gargantuan. 4 | # This script downloads the imagenet example auxiliary files including: 5 | # - the ilsvrc12 image mean, binaryproto 6 | # - synset ids and words 7 | # - Python pickle-format data of ImageNet graph structure and relative infogain 8 | # - the training splits with labels 9 | 10 | DIR="$( cd "$(dirname "$0")" ; pwd -P )" 11 | cd "$DIR" 12 | 13 | echo "Downloading..." 14 | 15 | wget -c http://dl.caffe.berkeleyvision.org/caffe_ilsvrc12.tar.gz 16 | 17 | echo "Unzipping..." 18 | 19 | tar -xf caffe_ilsvrc12.tar.gz && rm -f caffe_ilsvrc12.tar.gz 20 | 21 | echo "Done." 22 | -------------------------------------------------------------------------------- /caffe3d/data/mnist/get_mnist.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | # This scripts downloads the mnist data and unzips it. 3 | 4 | DIR="$( cd "$(dirname "$0")" ; pwd -P )" 5 | cd "$DIR" 6 | 7 | echo "Downloading..." 8 | 9 | for fname in train-images-idx3-ubyte train-labels-idx1-ubyte t10k-images-idx3-ubyte t10k-labels-idx1-ubyte 10 | do 11 | if [ ! -e $fname ]; then 12 | wget --no-check-certificate http://yann.lecun.com/exdb/mnist/${fname}.gz 13 | gunzip ${fname}.gz 14 | fi 15 | done 16 | -------------------------------------------------------------------------------- /caffe3d/docker/standalone/cpu/Dockerfile: -------------------------------------------------------------------------------- 1 | FROM ubuntu:14.04 2 | MAINTAINER caffe-maint@googlegroups.com 3 | 4 | RUN apt-get update && apt-get install -y --no-install-recommends \ 5 | build-essential \ 6 | cmake \ 7 | git \ 8 | wget \ 9 | libatlas-base-dev \ 10 | libboost-all-dev \ 11 | libgflags-dev \ 12 | libgoogle-glog-dev \ 13 | libhdf5-serial-dev \ 14 | libleveldb-dev \ 15 | liblmdb-dev \ 16 | libopencv-dev \ 17 | libprotobuf-dev \ 18 | libsnappy-dev \ 19 | protobuf-compiler \ 20 | python-dev \ 21 | python-numpy \ 22 | python-pip \ 23 | python-scipy && \ 24 | rm -rf /var/lib/apt/lists/* 25 | 26 | ENV CAFFE_ROOT=/opt/caffe 27 | WORKDIR $CAFFE_ROOT 28 | 29 | # FIXME: clone a specific git tag and use ARG instead of ENV once DockerHub supports this. 30 | ENV CLONE_TAG=master 31 | 32 | RUN git clone -b ${CLONE_TAG} --depth 1 https://github.com/BVLC/caffe.git . && \ 33 | for req in $(cat python/requirements.txt) pydot; do pip install $req; done && \ 34 | mkdir build && cd build && \ 35 | cmake -DCPU_ONLY=1 .. && \ 36 | make -j"$(nproc)" 37 | 38 | ENV PYCAFFE_ROOT $CAFFE_ROOT/python 39 | ENV PYTHONPATH $PYCAFFE_ROOT:$PYTHONPATH 40 | ENV PATH $CAFFE_ROOT/build/tools:$PYCAFFE_ROOT:$PATH 41 | RUN echo "$CAFFE_ROOT/build/lib" >> /etc/ld.so.conf.d/caffe.conf && ldconfig 42 | 43 | WORKDIR /workspace 44 | -------------------------------------------------------------------------------- /caffe3d/docker/standalone/gpu/Dockerfile: -------------------------------------------------------------------------------- 1 | FROM nvidia/cuda:7.5-cudnn5-devel-ubuntu14.04 2 | MAINTAINER caffe-maint@googlegroups.com 3 | 4 | RUN apt-get update && apt-get install -y --no-install-recommends \ 5 | build-essential \ 6 | cmake \ 7 | git \ 8 | wget \ 9 | libatlas-base-dev \ 10 | libboost-all-dev \ 11 | libgflags-dev \ 12 | libgoogle-glog-dev \ 13 | libhdf5-serial-dev \ 14 | libleveldb-dev \ 15 | liblmdb-dev \ 16 | libopencv-dev \ 17 | libprotobuf-dev \ 18 | libsnappy-dev \ 19 | protobuf-compiler \ 20 | python-dev \ 21 | python-numpy \ 22 | python-pip \ 23 | python-scipy && \ 24 | rm -rf /var/lib/apt/lists/* 25 | 26 | ENV CAFFE_ROOT=/opt/caffe 27 | WORKDIR $CAFFE_ROOT 28 | 29 | # FIXME: clone a specific git tag and use ARG instead of ENV once DockerHub supports this. 30 | ENV CLONE_TAG=master 31 | 32 | RUN git clone -b ${CLONE_TAG} --depth 1 https://github.com/BVLC/caffe.git . && \ 33 | for req in $(cat python/requirements.txt) pydot; do pip install $req; done && \ 34 | mkdir build && cd build && \ 35 | cmake -DUSE_CUDNN=1 .. && \ 36 | make -j"$(nproc)" 37 | 38 | ENV PYCAFFE_ROOT $CAFFE_ROOT/python 39 | ENV PYTHONPATH $PYCAFFE_ROOT:$PYTHONPATH 40 | ENV PATH $CAFFE_ROOT/build/tools:$PYCAFFE_ROOT:$PATH 41 | RUN echo "$CAFFE_ROOT/build/lib" >> /etc/ld.so.conf.d/caffe.conf && ldconfig 42 | 43 | WORKDIR /workspace 44 | -------------------------------------------------------------------------------- /caffe3d/docker/templates/Dockerfile.template: -------------------------------------------------------------------------------- 1 | MAINTAINER caffe-maint@googlegroups.com 2 | 3 | RUN apt-get update && apt-get install -y --no-install-recommends \ 4 | build-essential \ 5 | cmake \ 6 | git \ 7 | wget \ 8 | libatlas-base-dev \ 9 | libboost-all-dev \ 10 | libgflags-dev \ 11 | libgoogle-glog-dev \ 12 | libhdf5-serial-dev \ 13 | libleveldb-dev \ 14 | liblmdb-dev \ 15 | libopencv-dev \ 16 | libprotobuf-dev \ 17 | libsnappy-dev \ 18 | protobuf-compiler \ 19 | python-dev \ 20 | python-numpy \ 21 | python-pip \ 22 | python-scipy && \ 23 | rm -rf /var/lib/apt/lists/* 24 | 25 | ENV CAFFE_ROOT=/opt/caffe 26 | WORKDIR $CAFFE_ROOT 27 | 28 | # FIXME: clone a specific git tag and use ARG instead of ENV once DockerHub supports this. 29 | ENV CLONE_TAG=master 30 | 31 | RUN git clone -b ${CLONE_TAG} --depth 1 https://github.com/BVLC/caffe.git . && \ 32 | for req in $(cat python/requirements.txt) pydot; do pip install $req; done && \ 33 | mkdir build && cd build && \ 34 | cmake ${CMAKE_ARGS} .. && \ 35 | make -j"$(nproc)" 36 | 37 | ENV PYCAFFE_ROOT $CAFFE_ROOT/python 38 | ENV PYTHONPATH $PYCAFFE_ROOT:$PYTHONPATH 39 | ENV PATH $CAFFE_ROOT/build/tools:$PYCAFFE_ROOT:$PATH 40 | RUN echo "$CAFFE_ROOT/build/lib" >> /etc/ld.so.conf.d/caffe.conf && ldconfig 41 | 42 | WORKDIR /workspace 43 | -------------------------------------------------------------------------------- /caffe3d/docs/CNAME: -------------------------------------------------------------------------------- 1 | caffe.berkeleyvision.org 2 | -------------------------------------------------------------------------------- /caffe3d/docs/README.md: -------------------------------------------------------------------------------- 1 | # Caffe Documentation 2 | 3 | To generate the documentation, run `$CAFFE_ROOT/scripts/build_docs.sh`. 4 | 5 | To push your changes to the documentation to the gh-pages branch of your or the BVLC repo, run `$CAFFE_ROOT/scripts/deploy_docs.sh `. 6 | -------------------------------------------------------------------------------- /caffe3d/docs/_config.yml: -------------------------------------------------------------------------------- 1 | defaults: 2 | - 3 | scope: 4 | path: "" # an empty string here means all files in the project 5 | values: 6 | layout: "default" 7 | 8 | -------------------------------------------------------------------------------- /caffe3d/docs/images/GitHub-Mark-64px.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/docs/images/GitHub-Mark-64px.png -------------------------------------------------------------------------------- /caffe3d/docs/images/caffeine-icon.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/docs/images/caffeine-icon.png -------------------------------------------------------------------------------- /caffe3d/docs/stylesheets/reset.css: -------------------------------------------------------------------------------- 1 | /* MeyerWeb Reset */ 2 | 3 | html, body, div, span, applet, object, iframe, 4 | h1, h2, h3, h4, h5, h6, p, blockquote, pre, 5 | a, abbr, acronym, address, big, cite, code, 6 | del, dfn, em, img, ins, kbd, q, s, samp, 7 | small, strike, strong, sub, sup, tt, var, 8 | b, u, i, center, 9 | dl, dt, dd, ol, ul, li, 10 | fieldset, form, label, legend, 11 | table, caption, tbody, tfoot, thead, tr, th, td, 12 | article, aside, canvas, details, embed, 13 | figure, figcaption, footer, header, hgroup, 14 | menu, nav, output, ruby, section, summary, 15 | time, mark, audio, video { 16 | margin: 0; 17 | padding: 0; 18 | border: 0; 19 | font: inherit; 20 | vertical-align: baseline; 21 | } 22 | -------------------------------------------------------------------------------- /caffe3d/docs/tutorial/convolution.md: -------------------------------------------------------------------------------- 1 | --- 2 | title: Convolution 3 | --- 4 | # Caffeinated Convolution 5 | 6 | The Caffe strategy for convolution is to reduce the problem to matrix-matrix multiplication. 7 | This linear algebra computation is highly-tuned in BLAS libraries and efficiently computed on GPU devices. 8 | 9 | For more details read Yangqing's [Convolution in Caffe: a memo](https://github.com/Yangqing/caffe/wiki/Convolution-in-Caffe:-a-memo). 10 | 11 | As it turns out, this same reduction was independently explored in the context of conv. nets by 12 | 13 | > K. Chellapilla, S. Puri, P. Simard, et al. High performance convolutional neural networks for document processing. In Tenth International Workshop on Frontiers in Handwriting Recognition, 2006. 14 | -------------------------------------------------------------------------------- /caffe3d/docs/tutorial/fig/backward.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/docs/tutorial/fig/backward.jpg -------------------------------------------------------------------------------- /caffe3d/docs/tutorial/fig/forward.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/docs/tutorial/fig/forward.jpg -------------------------------------------------------------------------------- /caffe3d/docs/tutorial/fig/forward_backward.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/docs/tutorial/fig/forward_backward.png -------------------------------------------------------------------------------- /caffe3d/docs/tutorial/fig/layer.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/docs/tutorial/fig/layer.jpg -------------------------------------------------------------------------------- /caffe3d/docs/tutorial/fig/logreg.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/docs/tutorial/fig/logreg.jpg -------------------------------------------------------------------------------- /caffe3d/examples/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | file(GLOB_RECURSE examples_srcs "${PROJECT_SOURCE_DIR}/examples/*.cpp") 2 | 3 | foreach(source_file ${examples_srcs}) 4 | # get file name 5 | get_filename_component(name ${source_file} NAME_WE) 6 | 7 | # get folder name 8 | get_filename_component(path ${source_file} PATH) 9 | get_filename_component(folder ${path} NAME_WE) 10 | 11 | add_executable(${name} ${source_file}) 12 | target_link_libraries(${name} ${Caffe_LINK}) 13 | caffe_default_properties(${name}) 14 | 15 | # set back RUNTIME_OUTPUT_DIRECTORY 16 | set_target_properties(${name} PROPERTIES 17 | RUNTIME_OUTPUT_DIRECTORY "${PROJECT_BINARY_DIR}/examples/${folder}") 18 | 19 | caffe_set_solution_folder(${name} examples) 20 | 21 | # install 22 | install(TARGETS ${name} DESTINATION bin) 23 | 24 | if(UNIX OR APPLE) 25 | # Funny command to make tutorials work 26 | # TODO: remove in future as soon as naming is standartaized everywhere 27 | set(__outname ${PROJECT_BINARY_DIR}/examples/${folder}/${name}${Caffe_POSTFIX}) 28 | add_custom_command(TARGET ${name} POST_BUILD 29 | COMMAND ln -sf "${__outname}" "${__outname}.bin") 30 | endif() 31 | endforeach() 32 | -------------------------------------------------------------------------------- /caffe3d/examples/c3d_finetune/c3d_ucf101_solver.prototxt: -------------------------------------------------------------------------------- 1 | net: "examples/c3d_ucf101/c3d_ucf101_train_test.prototxt" 2 | # num test samples / batch_size = 41822/10 = 4182, but only 100 iterations 3 | # are used for testing to speed up training 4 | # optionally run test on train set, to monitor overfitting 5 | #test_iter: 100 6 | #test_state: { stage: 'test-on-train' } 7 | test_iter: 100 8 | test_state: { stage: 'test-on-val' } 9 | test_interval: 1000 10 | base_lr: 0.003 11 | momentum: 0.9 12 | weight_decay: 0.005 13 | lr_policy: "step" 14 | gamma: 0.1 15 | # original paper uses gamma of 0.1 every 4 epochs 16 | # using batch_size=15, 2 GPUs, stepsize = 4*(107258/15/2) to match original results 17 | # https://arxiv.org/pdf/1412.0767.pdf: figure 2 -- ~45% clip accuracy around 18 | # 6th spoch 19 | stepsize: 14301 20 | # Display every 20 iterations 21 | display: 20 22 | # The maximum number of iterations: 10 epochs 23 | max_iter: 143010 24 | # snapshot intermediate results 25 | snapshot: 5000 26 | snapshot_prefix: "examples/c3d_ucf101/c3d_ucf101" 27 | solver_mode: GPU 28 | -------------------------------------------------------------------------------- /caffe3d/examples/c3d_finetune/convert_npy_to_binaryproto.py: -------------------------------------------------------------------------------- 1 | import sys 2 | sys.path.insert(0, '/home/gpuadmin/Documents/segmentation/tdcnn/caffe3d/python') 3 | import caffe 4 | import numpy as np 5 | 6 | blob = caffe.proto.caffe_pb2.BlobProto() 7 | arr = np.load('ucf101_mean.npy') 8 | blob = caffe.io.array_to_blobproto(arr) 9 | data = open('ucf101_train_mean.binaryproto', 'wb') 10 | data.write(blob.SerializeToString()) 11 | data.close() 12 | 13 | 14 | data = open('ucf101_train_mean.binaryproto', 'rb').read() 15 | blob.ParseFromString(data) 16 | arr1 = np.array(caffe.io.blobproto_to_array(blob)) 17 | 18 | -------------------------------------------------------------------------------- /caffe3d/examples/c3d_finetune/feature_extraction/extract_c3d_features.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | 3 | ## params 4 | # test.prototxt 5 | # model file 6 | # id of gpu 7 | # batch_size 8 | # mini_batch_num 9 | # prefix file 10 | # target feature 11 | 12 | ./build/tools/predict.bin \ 13 | examples/c3d_ucf101/c3d_ucf101_test.prototxt \ 14 | examples/c3d_ucf101/c3d_iter_25.caffemodel \ 15 | 3 \ 16 | 16 \ 17 | 1 \ 18 | examples/c3d_ucf101/videos_output_prefix.txt \ 19 | fc8 20 | -------------------------------------------------------------------------------- /caffe3d/examples/c3d_finetune/feature_extraction/read_binary_blob.m: -------------------------------------------------------------------------------- 1 | % 2 | % Licensed under the Creative Commons Attribution-NonCommercial 3.0 3 | % License (the "License"). You may obtain a copy of the License at 4 | % https://creativecommons.org/licenses/by-nc/3.0/. 5 | % Unless required by applicable law or agreed to in writing, software 6 | % distributed under the License is distributed on an "AS IS" BASIS, WITHOUT 7 | % WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the 8 | % License for the specific language governing permissions and limitations 9 | % under the License. 10 | % 11 | 12 | function [s, data] = read_binary_blob(fn) 13 | 14 | f = fopen(fn, 'r'); 15 | s = fread(f, [1 5], 'int32'); 16 | 17 | % s contains size of the blob e.g. num x chanel x length x height x width 18 | m = s(1)*s(2)*s(3)*s(4)*s(5); 19 | 20 | % data is the blob binary data in single precision (e.g float in C++) 21 | data = fread(f, [1 m], 'single'); 22 | fclose(f); 23 | 24 | end 25 | -------------------------------------------------------------------------------- /caffe3d/examples/c3d_finetune/test_ucf101.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | 3 | # get the last model (latest) 4 | LASTMODEL=/home/gpuadmin/Documents/segmentation/tdcnn/pretrain/ucf101.caffemodel 5 | 6 | echo "[Info] The caffemodel to be used: ${LASTMODEL}" 7 | 8 | # check the # test samples and batch_size: 41822/30=1395 9 | NUMITERS=838 10 | echo "[Info] Tested for ${NUMITERS} iterations" 11 | 12 | if [ -z "${LASTMODEL}" ]; then 13 | echo "[Error] Can not find the model. Check the caffemodel name." 14 | else 15 | build/tools/caffe \ 16 | test \ 17 | --model=./examples/c3d_finetune/c3d_ucf101_test.prototxt \ 18 | --weights=${LASTMODEL} \ 19 | --iterations=${NUMITERS} \ 20 | --gpu=0 \ 21 | 2>&1 | tee ./examples/c3d_finetune/c3d_ucf101_test.log 22 | fi 23 | -------------------------------------------------------------------------------- /caffe3d/examples/c3d_finetune/train_ucf101.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | set -e 3 | 4 | ./build/tools/caffe \ 5 | train \ 6 | --solver=examples/c3d_ucf101/c3d_ucf101_solver.prototxt \ 7 | $@ \ 8 | 2>&1 | tee examples/c3d_ucf101/c3d_ucf101_train.log 9 | -------------------------------------------------------------------------------- /caffe3d/examples/c3d_finetune/ucf101_mean.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/examples/c3d_finetune/ucf101_mean.npy -------------------------------------------------------------------------------- /caffe3d/examples/c3d_finetune/ucf101_train_mean.binaryproto: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/examples/c3d_finetune/ucf101_train_mean.binaryproto -------------------------------------------------------------------------------- /caffe3d/examples/c3d_ucf101/c3d_ucf101_solver.prototxt: -------------------------------------------------------------------------------- 1 | net: "examples/c3d_ucf101/c3d_ucf101_train_test.prototxt" 2 | # num test samples / batch_size = 41822/10 = 4182, but only 100 iterations 3 | # are used for testing to speed up training 4 | # optionally run test on train set, to monitor overfitting 5 | #test_iter: 100 6 | #test_state: { stage: 'test-on-train' } 7 | test_iter: 100 8 | test_state: { stage: 'test-on-val' } 9 | test_interval: 1000 10 | base_lr: 0.003 11 | momentum: 0.9 12 | weight_decay: 0.005 13 | lr_policy: "step" 14 | gamma: 0.1 15 | # original paper uses gamma of 0.1 every 4 epochs 16 | # using batch_size=15, 2 GPUs, stepsize = 4*(107258/15/2) to match original results 17 | # https://arxiv.org/pdf/1412.0767.pdf: figure 2 -- ~45% clip accuracy around 18 | # 6th spoch 19 | stepsize: 14301 20 | # Display every 20 iterations 21 | display: 20 22 | # The maximum number of iterations: 10 epochs 23 | max_iter: 143010 24 | # snapshot intermediate results 25 | snapshot: 5000 26 | snapshot_prefix: "examples/c3d_ucf101/c3d_ucf101" 27 | solver_mode: GPU 28 | -------------------------------------------------------------------------------- /caffe3d/examples/c3d_ucf101/c3d_ucf101_test.log: -------------------------------------------------------------------------------- 1 | I1202 13:59:40.355363 31686 caffe.cpp:270] Use GPU with device ID 0 2 | I1202 13:59:40.375721 31686 caffe.cpp:274] GPU device name: GeForce GTX TITAN X 3 | [libprotobuf ERROR google/protobuf/text_format.cc:245] Error parsing text-format caffe.NetParameter: 44:18: Message type "caffe.ConvolutionParameter" has no field named "kernel_shape". 4 | F1202 13:59:40.721417 31686 upgrade_proto.cpp:88] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file: examples/c3d_ucf101/c3d_ucf101_test.prototxt 5 | *** Check failure stack trace: *** 6 | @ 0x7f1525738daa (unknown) 7 | @ 0x7f1525738ce4 (unknown) 8 | @ 0x7f15257386e6 (unknown) 9 | @ 0x7f152573b687 (unknown) 10 | @ 0x7f1525dac67e caffe::ReadNetParamsFromTextFileOrDie() 11 | @ 0x7f1525d8811f caffe::Net<>::Net() 12 | @ 0x4075ab test() 13 | @ 0x405e6c main 14 | @ 0x7f1523f93f45 (unknown) 15 | @ 0x406773 (unknown) 16 | @ (nil) (unknown) 17 | -------------------------------------------------------------------------------- /caffe3d/examples/c3d_ucf101/c3d_ucf101_train_loss_accuracy.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/examples/c3d_ucf101/c3d_ucf101_train_loss_accuracy.png -------------------------------------------------------------------------------- /caffe3d/examples/c3d_ucf101/extract_UCF-101_frames.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | ############################################# 4 | # modify the UCF-101 data directory: 5 | UCF101DIR=/media/TB/Videos/UCF-101 6 | 7 | # and, make sure ffmpeg is installed 8 | FFMPEGBIN=ffmpeg 9 | ############################################# 10 | 11 | for f in ${UCF101DIR}/*/*.avi; do 12 | dir=${f::-4} 13 | echo ----- 14 | echo Extracting frames from ${f} into ${dir}... 15 | if [[ ! -d ${dir} ]]; then 16 | echo Creating directory=${dir} 17 | mkdir -p ${dir} 18 | fi 19 | 20 | ${FFMPEGBIN} \ 21 | -i ${f} \ 22 | ${dir}/image_%4d.jpg 23 | done 24 | 25 | echo ------------------------------------------- 26 | echo Done! 27 | -------------------------------------------------------------------------------- /caffe3d/examples/c3d_ucf101/feature_extraction/extract_c3d_features.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | 3 | ## params 4 | # test.prototxt 5 | # model file 6 | # id of gpu 7 | # batch_size 8 | # mini_batch_num 9 | # prefix file 10 | # target feature 11 | 12 | ./build/tools/predict.bin \ 13 | examples/c3d_ucf101/c3d_ucf101_test.prototxt \ 14 | examples/c3d_ucf101/c3d_iter_25.caffemodel \ 15 | 3 \ 16 | 16 \ 17 | 1 \ 18 | examples/c3d_ucf101/videos_output_prefix.txt \ 19 | fc8 20 | -------------------------------------------------------------------------------- /caffe3d/examples/c3d_ucf101/feature_extraction/read_binary_blob.m: -------------------------------------------------------------------------------- 1 | % 2 | % Licensed under the Creative Commons Attribution-NonCommercial 3.0 3 | % License (the "License"). You may obtain a copy of the License at 4 | % https://creativecommons.org/licenses/by-nc/3.0/. 5 | % Unless required by applicable law or agreed to in writing, software 6 | % distributed under the License is distributed on an "AS IS" BASIS, WITHOUT 7 | % WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the 8 | % License for the specific language governing permissions and limitations 9 | % under the License. 10 | % 11 | 12 | function [s, data] = read_binary_blob(fn) 13 | 14 | f = fopen(fn, 'r'); 15 | s = fread(f, [1 5], 'int32'); 16 | 17 | % s contains size of the blob e.g. num x chanel x length x height x width 18 | m = s(1)*s(2)*s(3)*s(4)*s(5); 19 | 20 | % data is the blob binary data in single precision (e.g float in C++) 21 | data = fread(f, [1 m], 'single'); 22 | fclose(f); 23 | 24 | end 25 | -------------------------------------------------------------------------------- /caffe3d/examples/c3d_ucf101/test_ucf101.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | 3 | # get the last model (latest) 4 | LASTMODEL=$(ls -1t examples/c3d_ucf101/c3d_ucf101_iter_*.caffemodel | head -n 1) 5 | echo "[Info] The caffemodel to be used: ${LASTMODEL}" 6 | 7 | # check the # test samples and batch_size: 41822/30=1395 8 | NUMITERS=1395 9 | echo "[Info] Tested for ${NUMITERS} iterations" 10 | 11 | if [ -z "${LASTMODEL}" ]; then 12 | echo "[Error] Can not find the model. Check the caffemodel name." 13 | else 14 | build/tools/caffe \ 15 | test \ 16 | --model=examples/c3d_ucf101/c3d_ucf101_test.prototxt \ 17 | --weights=${LASTMODEL} \ 18 | --iterations=${NUMITERS} \ 19 | --gpu=0 \ 20 | 2>&1 | tee examples/c3d_ucf101/c3d_ucf101_test.log 21 | fi 22 | -------------------------------------------------------------------------------- /caffe3d/examples/c3d_ucf101/train_ucf101.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | set -e 3 | 4 | ./build/tools/caffe \ 5 | train \ 6 | --solver=examples/c3d_ucf101/c3d_ucf101_solver.prototxt \ 7 | $@ \ 8 | 2>&1 | tee examples/c3d_ucf101/c3d_ucf101_train.log 9 | -------------------------------------------------------------------------------- /caffe3d/examples/c3d_ucf101/ucf101_train_mean.binaryproto: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/examples/c3d_ucf101/ucf101_train_mean.binaryproto -------------------------------------------------------------------------------- /caffe3d/examples/cifar10/cifar10_full_sigmoid_solver.prototxt: -------------------------------------------------------------------------------- 1 | # reduce learning rate after 120 epochs (60000 iters) by factor 0f 10 2 | # then another factor of 10 after 10 more epochs (5000 iters) 3 | 4 | # The train/test net protocol buffer definition 5 | net: "examples/cifar10/cifar10_full_sigmoid_train_test.prototxt" 6 | # test_iter specifies how many forward passes the test should carry out. 7 | # In the case of CIFAR10, we have test batch size 100 and 100 test iterations, 8 | # covering the full 10,000 testing images. 9 | test_iter: 10 10 | # Carry out testing every 1000 training iterations. 11 | test_interval: 1000 12 | # The base learning rate, momentum and the weight decay of the network. 13 | base_lr: 0.001 14 | momentum: 0.9 15 | #weight_decay: 0.004 16 | # The learning rate policy 17 | lr_policy: "step" 18 | gamma: 1 19 | stepsize: 5000 20 | # Display every 100 iterations 21 | display: 100 22 | # The maximum number of iterations 23 | max_iter: 60000 24 | # snapshot intermediate results 25 | snapshot: 10000 26 | snapshot_prefix: "examples/cifar10_full_sigmoid" 27 | # solver mode: CPU or GPU 28 | solver_mode: GPU 29 | -------------------------------------------------------------------------------- /caffe3d/examples/cifar10/cifar10_full_sigmoid_solver_bn.prototxt: -------------------------------------------------------------------------------- 1 | # reduce learning rate after 120 epochs (60000 iters) by factor 0f 10 2 | # then another factor of 10 after 10 more epochs (5000 iters) 3 | 4 | # The train/test net protocol buffer definition 5 | net: "examples/cifar10/cifar10_full_sigmoid_train_test_bn.prototxt" 6 | # test_iter specifies how many forward passes the test should carry out. 7 | # In the case of CIFAR10, we have test batch size 100 and 100 test iterations, 8 | # covering the full 10,000 testing images. 9 | test_iter: 10 10 | # Carry out testing every 1000 training iterations. 11 | test_interval: 1000 12 | # The base learning rate, momentum and the weight decay of the network. 13 | base_lr: 0.001 14 | momentum: 0.9 15 | #weight_decay: 0.004 16 | # The learning rate policy 17 | lr_policy: "step" 18 | gamma: 1 19 | stepsize: 5000 20 | # Display every 100 iterations 21 | display: 100 22 | # The maximum number of iterations 23 | max_iter: 60000 24 | # snapshot intermediate results 25 | snapshot: 10000 26 | snapshot_prefix: "examples/cifar10_full_sigmoid_bn" 27 | # solver mode: CPU or GPU 28 | solver_mode: GPU 29 | -------------------------------------------------------------------------------- /caffe3d/examples/cifar10/cifar10_full_solver.prototxt: -------------------------------------------------------------------------------- 1 | # reduce learning rate after 120 epochs (60000 iters) by factor 0f 10 2 | # then another factor of 10 after 10 more epochs (5000 iters) 3 | 4 | # The train/test net protocol buffer definition 5 | net: "examples/cifar10/cifar10_full_train_test.prototxt" 6 | # test_iter specifies how many forward passes the test should carry out. 7 | # In the case of CIFAR10, we have test batch size 100 and 100 test iterations, 8 | # covering the full 10,000 testing images. 9 | test_iter: 100 10 | # Carry out testing every 1000 training iterations. 11 | test_interval: 1000 12 | # The base learning rate, momentum and the weight decay of the network. 13 | base_lr: 0.001 14 | momentum: 0.9 15 | weight_decay: 0.004 16 | # The learning rate policy 17 | lr_policy: "fixed" 18 | # Display every 200 iterations 19 | display: 200 20 | # The maximum number of iterations 21 | max_iter: 60000 22 | # snapshot intermediate results 23 | snapshot: 10000 24 | snapshot_format: HDF5 25 | snapshot_prefix: "examples/cifar10/cifar10_full" 26 | # solver mode: CPU or GPU 27 | solver_mode: GPU 28 | -------------------------------------------------------------------------------- /caffe3d/examples/cifar10/cifar10_full_solver_lr1.prototxt: -------------------------------------------------------------------------------- 1 | # reduce learning rate after 120 epochs (60000 iters) by factor 0f 10 2 | # then another factor of 10 after 10 more epochs (5000 iters) 3 | 4 | # The train/test net protocol buffer definition 5 | net: "examples/cifar10/cifar10_full_train_test.prototxt" 6 | # test_iter specifies how many forward passes the test should carry out. 7 | # In the case of CIFAR10, we have test batch size 100 and 100 test iterations, 8 | # covering the full 10,000 testing images. 9 | test_iter: 100 10 | # Carry out testing every 1000 training iterations. 11 | test_interval: 1000 12 | # The base learning rate, momentum and the weight decay of the network. 13 | base_lr: 0.0001 14 | momentum: 0.9 15 | weight_decay: 0.004 16 | # The learning rate policy 17 | lr_policy: "fixed" 18 | # Display every 200 iterations 19 | display: 200 20 | # The maximum number of iterations 21 | max_iter: 65000 22 | # snapshot intermediate results 23 | snapshot: 5000 24 | snapshot_format: HDF5 25 | snapshot_prefix: "examples/cifar10/cifar10_full" 26 | # solver mode: CPU or GPU 27 | solver_mode: GPU 28 | -------------------------------------------------------------------------------- /caffe3d/examples/cifar10/cifar10_full_solver_lr2.prototxt: -------------------------------------------------------------------------------- 1 | # reduce learning rate after 120 epochs (60000 iters) by factor 0f 10 2 | # then another factor of 10 after 10 more epochs (5000 iters) 3 | 4 | # The train/test net protocol buffer definition 5 | net: "examples/cifar10/cifar10_full_train_test.prototxt" 6 | # test_iter specifies how many forward passes the test should carry out. 7 | # In the case of CIFAR10, we have test batch size 100 and 100 test iterations, 8 | # covering the full 10,000 testing images. 9 | test_iter: 100 10 | # Carry out testing every 1000 training iterations. 11 | test_interval: 1000 12 | # The base learning rate, momentum and the weight decay of the network. 13 | base_lr: 0.00001 14 | momentum: 0.9 15 | weight_decay: 0.004 16 | # The learning rate policy 17 | lr_policy: "fixed" 18 | # Display every 200 iterations 19 | display: 200 20 | # The maximum number of iterations 21 | max_iter: 70000 22 | # snapshot intermediate results 23 | snapshot: 5000 24 | snapshot_format: HDF5 25 | snapshot_prefix: "examples/cifar10/cifar10_full" 26 | # solver mode: CPU or GPU 27 | solver_mode: GPU 28 | -------------------------------------------------------------------------------- /caffe3d/examples/cifar10/cifar10_quick_solver.prototxt: -------------------------------------------------------------------------------- 1 | # reduce the learning rate after 8 epochs (4000 iters) by a factor of 10 2 | 3 | # The train/test net protocol buffer definition 4 | net: "examples/cifar10/cifar10_quick_train_test.prototxt" 5 | # test_iter specifies how many forward passes the test should carry out. 6 | # In the case of MNIST, we have test batch size 100 and 100 test iterations, 7 | # covering the full 10,000 testing images. 8 | test_iter: 100 9 | # Carry out testing every 500 training iterations. 10 | test_interval: 500 11 | # The base learning rate, momentum and the weight decay of the network. 12 | base_lr: 0.001 13 | momentum: 0.9 14 | weight_decay: 0.004 15 | # The learning rate policy 16 | lr_policy: "fixed" 17 | # Display every 100 iterations 18 | display: 100 19 | # The maximum number of iterations 20 | max_iter: 4000 21 | # snapshot intermediate results 22 | snapshot: 4000 23 | snapshot_format: HDF5 24 | snapshot_prefix: "examples/cifar10/cifar10_quick" 25 | # solver mode: CPU or GPU 26 | solver_mode: GPU 27 | -------------------------------------------------------------------------------- /caffe3d/examples/cifar10/cifar10_quick_solver_lr1.prototxt: -------------------------------------------------------------------------------- 1 | # reduce the learning rate after 8 epochs (4000 iters) by a factor of 10 2 | 3 | # The train/test net protocol buffer definition 4 | net: "examples/cifar10/cifar10_quick_train_test.prototxt" 5 | # test_iter specifies how many forward passes the test should carry out. 6 | # In the case of MNIST, we have test batch size 100 and 100 test iterations, 7 | # covering the full 10,000 testing images. 8 | test_iter: 100 9 | # Carry out testing every 500 training iterations. 10 | test_interval: 500 11 | # The base learning rate, momentum and the weight decay of the network. 12 | base_lr: 0.0001 13 | momentum: 0.9 14 | weight_decay: 0.004 15 | # The learning rate policy 16 | lr_policy: "fixed" 17 | # Display every 100 iterations 18 | display: 100 19 | # The maximum number of iterations 20 | max_iter: 5000 21 | # snapshot intermediate results 22 | snapshot: 5000 23 | snapshot_format: HDF5 24 | snapshot_prefix: "examples/cifar10/cifar10_quick" 25 | # solver mode: CPU or GPU 26 | solver_mode: GPU 27 | -------------------------------------------------------------------------------- /caffe3d/examples/cifar10/create_cifar10.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | # This script converts the cifar data into leveldb format. 3 | set -e 4 | 5 | EXAMPLE=examples/cifar10 6 | DATA=data/cifar10 7 | DBTYPE=lmdb 8 | 9 | echo "Creating $DBTYPE..." 10 | 11 | rm -rf $EXAMPLE/cifar10_train_$DBTYPE $EXAMPLE/cifar10_test_$DBTYPE 12 | 13 | ./build/examples/cifar10/convert_cifar_data.bin $DATA $EXAMPLE $DBTYPE 14 | 15 | echo "Computing image mean..." 16 | 17 | ./build/tools/compute_image_mean -backend=$DBTYPE \ 18 | $EXAMPLE/cifar10_train_$DBTYPE $EXAMPLE/mean.binaryproto 19 | 20 | echo "Done." 21 | -------------------------------------------------------------------------------- /caffe3d/examples/cifar10/train_full.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | set -e 3 | 4 | TOOLS=./build/tools 5 | 6 | $TOOLS/caffe train \ 7 | --solver=examples/cifar10/cifar10_full_solver.prototxt $@ 8 | 9 | # reduce learning rate by factor of 10 10 | $TOOLS/caffe train \ 11 | --solver=examples/cifar10/cifar10_full_solver_lr1.prototxt \ 12 | --snapshot=examples/cifar10/cifar10_full_iter_60000.solverstate.h5 $@ 13 | 14 | # reduce learning rate by factor of 10 15 | $TOOLS/caffe train \ 16 | --solver=examples/cifar10/cifar10_full_solver_lr2.prototxt \ 17 | --snapshot=examples/cifar10/cifar10_full_iter_65000.solverstate.h5 $@ 18 | -------------------------------------------------------------------------------- /caffe3d/examples/cifar10/train_full_sigmoid.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | set -e 3 | 4 | TOOLS=./build/tools 5 | 6 | $TOOLS/caffe train \ 7 | --solver=examples/cifar10/cifar10_full_sigmoid_solver.prototxt $@ 8 | 9 | -------------------------------------------------------------------------------- /caffe3d/examples/cifar10/train_full_sigmoid_bn.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | set -e 3 | 4 | TOOLS=./build/tools 5 | 6 | $TOOLS/caffe train \ 7 | --solver=examples/cifar10/cifar10_full_sigmoid_solver_bn.prototxt $@ 8 | 9 | -------------------------------------------------------------------------------- /caffe3d/examples/cifar10/train_quick.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | set -e 3 | 4 | TOOLS=./build/tools 5 | 6 | $TOOLS/caffe train \ 7 | --solver=examples/cifar10/cifar10_quick_solver.prototxt $@ 8 | 9 | # reduce learning rate by factor of 10 after 8 epochs 10 | $TOOLS/caffe train \ 11 | --solver=examples/cifar10/cifar10_quick_solver_lr1.prototxt \ 12 | --snapshot=examples/cifar10/cifar10_quick_iter_4000.solverstate.h5 $@ 13 | -------------------------------------------------------------------------------- /caffe3d/examples/finetune_flickr_style/flickr_style.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/examples/finetune_flickr_style/flickr_style.csv.gz -------------------------------------------------------------------------------- /caffe3d/examples/finetune_flickr_style/style_names.txt: -------------------------------------------------------------------------------- 1 | Detailed 2 | Pastel 3 | Melancholy 4 | Noir 5 | HDR 6 | Vintage 7 | Long Exposure 8 | Horror 9 | Sunny 10 | Bright 11 | Hazy 12 | Bokeh 13 | Serene 14 | Texture 15 | Ethereal 16 | Macro 17 | Depth of Field 18 | Geometric Composition 19 | Minimal 20 | Romantic 21 | -------------------------------------------------------------------------------- /caffe3d/examples/finetune_pascal_detection/pascal_finetune_solver.prototxt: -------------------------------------------------------------------------------- 1 | net: "examples/finetune_pascal_detection/pascal_finetune_trainval_test.prototxt" 2 | test_iter: 100 3 | test_interval: 1000 4 | base_lr: 0.001 5 | lr_policy: "step" 6 | gamma: 0.1 7 | stepsize: 20000 8 | display: 20 9 | max_iter: 100000 10 | momentum: 0.9 11 | weight_decay: 0.0005 12 | snapshot: 10000 13 | snapshot_prefix: "examples/finetune_pascal_detection/pascal_det_finetune" 14 | -------------------------------------------------------------------------------- /caffe3d/examples/hdf5_classification/nonlinear_auto_test.prototxt: -------------------------------------------------------------------------------- 1 | layer { 2 | name: "data" 3 | type: "HDF5Data" 4 | top: "data" 5 | top: "label" 6 | hdf5_data_param { 7 | source: "examples/hdf5_classification/data/test.txt" 8 | batch_size: 10 9 | } 10 | } 11 | layer { 12 | name: "ip1" 13 | type: "InnerProduct" 14 | bottom: "data" 15 | top: "ip1" 16 | inner_product_param { 17 | num_output: 40 18 | weight_filler { 19 | type: "xavier" 20 | } 21 | } 22 | } 23 | layer { 24 | name: "relu1" 25 | type: "ReLU" 26 | bottom: "ip1" 27 | top: "ip1" 28 | } 29 | layer { 30 | name: "ip2" 31 | type: "InnerProduct" 32 | bottom: "ip1" 33 | top: "ip2" 34 | inner_product_param { 35 | num_output: 2 36 | weight_filler { 37 | type: "xavier" 38 | } 39 | } 40 | } 41 | layer { 42 | name: "accuracy" 43 | type: "Accuracy" 44 | bottom: "ip2" 45 | bottom: "label" 46 | top: "accuracy" 47 | } 48 | layer { 49 | name: "loss" 50 | type: "SoftmaxWithLoss" 51 | bottom: "ip2" 52 | bottom: "label" 53 | top: "loss" 54 | } 55 | -------------------------------------------------------------------------------- /caffe3d/examples/hdf5_classification/nonlinear_auto_train.prototxt: -------------------------------------------------------------------------------- 1 | layer { 2 | name: "data" 3 | type: "HDF5Data" 4 | top: "data" 5 | top: "label" 6 | hdf5_data_param { 7 | source: "examples/hdf5_classification/data/train.txt" 8 | batch_size: 10 9 | } 10 | } 11 | layer { 12 | name: "ip1" 13 | type: "InnerProduct" 14 | bottom: "data" 15 | top: "ip1" 16 | inner_product_param { 17 | num_output: 40 18 | weight_filler { 19 | type: "xavier" 20 | } 21 | } 22 | } 23 | layer { 24 | name: "relu1" 25 | type: "ReLU" 26 | bottom: "ip1" 27 | top: "ip1" 28 | } 29 | layer { 30 | name: "ip2" 31 | type: "InnerProduct" 32 | bottom: "ip1" 33 | top: "ip2" 34 | inner_product_param { 35 | num_output: 2 36 | weight_filler { 37 | type: "xavier" 38 | } 39 | } 40 | } 41 | layer { 42 | name: "accuracy" 43 | type: "Accuracy" 44 | bottom: "ip2" 45 | bottom: "label" 46 | top: "accuracy" 47 | } 48 | layer { 49 | name: "loss" 50 | type: "SoftmaxWithLoss" 51 | bottom: "ip2" 52 | bottom: "label" 53 | top: "loss" 54 | } 55 | -------------------------------------------------------------------------------- /caffe3d/examples/hdf5_classification/train_val.prototxt: -------------------------------------------------------------------------------- 1 | name: "LogisticRegressionNet" 2 | layer { 3 | name: "data" 4 | type: "HDF5Data" 5 | top: "data" 6 | top: "label" 7 | include { 8 | phase: TRAIN 9 | } 10 | hdf5_data_param { 11 | source: "examples/hdf5_classification/data/train.txt" 12 | batch_size: 10 13 | } 14 | } 15 | layer { 16 | name: "data" 17 | type: "HDF5Data" 18 | top: "data" 19 | top: "label" 20 | include { 21 | phase: TEST 22 | } 23 | hdf5_data_param { 24 | source: "examples/hdf5_classification/data/test.txt" 25 | batch_size: 10 26 | } 27 | } 28 | layer { 29 | name: "fc1" 30 | type: "InnerProduct" 31 | bottom: "data" 32 | top: "fc1" 33 | param { 34 | lr_mult: 1 35 | decay_mult: 1 36 | } 37 | param { 38 | lr_mult: 2 39 | decay_mult: 0 40 | } 41 | inner_product_param { 42 | num_output: 2 43 | weight_filler { 44 | type: "xavier" 45 | } 46 | bias_filler { 47 | type: "constant" 48 | value: 0 49 | } 50 | } 51 | } 52 | layer { 53 | name: "loss" 54 | type: "SoftmaxWithLoss" 55 | bottom: "fc1" 56 | bottom: "label" 57 | top: "loss" 58 | } 59 | layer { 60 | name: "accuracy" 61 | type: "Accuracy" 62 | bottom: "fc1" 63 | bottom: "label" 64 | top: "accuracy" 65 | include { 66 | phase: TEST 67 | } 68 | } 69 | -------------------------------------------------------------------------------- /caffe3d/examples/imagenet/make_imagenet_mean.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | # Compute the mean image from the imagenet training lmdb 3 | # N.B. this is available in data/ilsvrc12 4 | 5 | EXAMPLE=examples/imagenet 6 | DATA=data/ilsvrc12 7 | TOOLS=build/tools 8 | 9 | $TOOLS/compute_image_mean $EXAMPLE/ilsvrc12_train_lmdb \ 10 | $DATA/imagenet_mean.binaryproto 11 | 12 | echo "Done." 13 | -------------------------------------------------------------------------------- /caffe3d/examples/imagenet/resume_training.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | set -e 3 | 4 | ./build/tools/caffe train \ 5 | --solver=models/bvlc_reference_caffenet/solver.prototxt \ 6 | --snapshot=models/bvlc_reference_caffenet/caffenet_train_10000.solverstate.h5 \ 7 | $@ 8 | -------------------------------------------------------------------------------- /caffe3d/examples/imagenet/train_caffenet.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | set -e 3 | 4 | ./build/tools/caffe train \ 5 | --solver=models/bvlc_reference_caffenet/solver.prototxt $@ 6 | -------------------------------------------------------------------------------- /caffe3d/examples/images/cat gray.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/examples/images/cat gray.jpg -------------------------------------------------------------------------------- /caffe3d/examples/images/cat.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/examples/images/cat.jpg -------------------------------------------------------------------------------- /caffe3d/examples/images/cat_gray.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/examples/images/cat_gray.jpg -------------------------------------------------------------------------------- /caffe3d/examples/images/fish-bike.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/examples/images/fish-bike.jpg -------------------------------------------------------------------------------- /caffe3d/examples/mnist/create_mnist.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | # This script converts the mnist data into lmdb/leveldb format, 3 | # depending on the value assigned to $BACKEND. 4 | set -e 5 | 6 | EXAMPLE=examples/mnist 7 | DATA=data/mnist 8 | BUILD=build/examples/mnist 9 | 10 | BACKEND="lmdb" 11 | 12 | echo "Creating ${BACKEND}..." 13 | 14 | rm -rf $EXAMPLE/mnist_train_${BACKEND} 15 | rm -rf $EXAMPLE/mnist_test_${BACKEND} 16 | 17 | $BUILD/convert_mnist_data.bin $DATA/train-images-idx3-ubyte \ 18 | $DATA/train-labels-idx1-ubyte $EXAMPLE/mnist_train_${BACKEND} --backend=${BACKEND} 19 | $BUILD/convert_mnist_data.bin $DATA/t10k-images-idx3-ubyte \ 20 | $DATA/t10k-labels-idx1-ubyte $EXAMPLE/mnist_test_${BACKEND} --backend=${BACKEND} 21 | 22 | echo "Done." 23 | -------------------------------------------------------------------------------- /caffe3d/examples/mnist/lenet_adadelta_solver.prototxt: -------------------------------------------------------------------------------- 1 | # The train/test net protocol buffer definition 2 | net: "examples/mnist/lenet_train_test.prototxt" 3 | # test_iter specifies how many forward passes the test should carry out. 4 | # In the case of MNIST, we have test batch size 100 and 100 test iterations, 5 | # covering the full 10,000 testing images. 6 | test_iter: 100 7 | # Carry out testing every 500 training iterations. 8 | test_interval: 500 9 | # The base learning rate, momentum and the weight decay of the network. 10 | base_lr: 1.0 11 | lr_policy: "fixed" 12 | momentum: 0.95 13 | weight_decay: 0.0005 14 | # Display every 100 iterations 15 | display: 100 16 | # The maximum number of iterations 17 | max_iter: 10000 18 | # snapshot intermediate results 19 | snapshot: 5000 20 | snapshot_prefix: "examples/mnist/lenet_adadelta" 21 | # solver mode: CPU or GPU 22 | solver_mode: GPU 23 | type: "AdaDelta" 24 | delta: 1e-6 25 | -------------------------------------------------------------------------------- /caffe3d/examples/mnist/lenet_auto_solver.prototxt: -------------------------------------------------------------------------------- 1 | # The train/test net protocol buffer definition 2 | train_net: "mnist/lenet_auto_train.prototxt" 3 | test_net: "mnist/lenet_auto_test.prototxt" 4 | # test_iter specifies how many forward passes the test should carry out. 5 | # In the case of MNIST, we have test batch size 100 and 100 test iterations, 6 | # covering the full 10,000 testing images. 7 | test_iter: 100 8 | # Carry out testing every 500 training iterations. 9 | test_interval: 500 10 | # The base learning rate, momentum and the weight decay of the network. 11 | base_lr: 0.01 12 | momentum: 0.9 13 | weight_decay: 0.0005 14 | # The learning rate policy 15 | lr_policy: "inv" 16 | gamma: 0.0001 17 | power: 0.75 18 | # Display every 100 iterations 19 | display: 100 20 | # The maximum number of iterations 21 | max_iter: 10000 22 | # snapshot intermediate results 23 | snapshot: 5000 24 | snapshot_prefix: "mnist/lenet" 25 | -------------------------------------------------------------------------------- /caffe3d/examples/mnist/lenet_multistep_solver.prototxt: -------------------------------------------------------------------------------- 1 | # The train/test net protocol buffer definition 2 | net: "examples/mnist/lenet_train_test.prototxt" 3 | # test_iter specifies how many forward passes the test should carry out. 4 | # In the case of MNIST, we have test batch size 100 and 100 test iterations, 5 | # covering the full 10,000 testing images. 6 | test_iter: 100 7 | # Carry out testing every 500 training iterations. 8 | test_interval: 500 9 | # The base learning rate, momentum and the weight decay of the network. 10 | base_lr: 0.01 11 | momentum: 0.9 12 | weight_decay: 0.0005 13 | # The learning rate policy 14 | lr_policy: "multistep" 15 | gamma: 0.9 16 | stepvalue: 5000 17 | stepvalue: 7000 18 | stepvalue: 8000 19 | stepvalue: 9000 20 | stepvalue: 9500 21 | # Display every 100 iterations 22 | display: 100 23 | # The maximum number of iterations 24 | max_iter: 10000 25 | # snapshot intermediate results 26 | snapshot: 5000 27 | snapshot_prefix: "examples/mnist/lenet_multistep" 28 | # solver mode: CPU or GPU 29 | solver_mode: GPU 30 | -------------------------------------------------------------------------------- /caffe3d/examples/mnist/lenet_solver.prototxt: -------------------------------------------------------------------------------- 1 | # The train/test net protocol buffer definition 2 | net: "examples/mnist/lenet_train_test.prototxt" 3 | # test_iter specifies how many forward passes the test should carry out. 4 | # In the case of MNIST, we have test batch size 100 and 100 test iterations, 5 | # covering the full 10,000 testing images. 6 | test_iter: 100 7 | # Carry out testing every 500 training iterations. 8 | test_interval: 500 9 | # The base learning rate, momentum and the weight decay of the network. 10 | base_lr: 0.01 11 | momentum: 0.9 12 | weight_decay: 0.0005 13 | # The learning rate policy 14 | lr_policy: "inv" 15 | gamma: 0.0001 16 | power: 0.75 17 | # Display every 100 iterations 18 | display: 100 19 | # The maximum number of iterations 20 | max_iter: 10000 21 | # snapshot intermediate results 22 | snapshot: 5000 23 | snapshot_prefix: "examples/mnist/lenet" 24 | # solver mode: CPU or GPU 25 | solver_mode: GPU 26 | -------------------------------------------------------------------------------- /caffe3d/examples/mnist/lenet_solver_adam.prototxt: -------------------------------------------------------------------------------- 1 | # The train/test net protocol buffer definition 2 | # this follows "ADAM: A METHOD FOR STOCHASTIC OPTIMIZATION" 3 | net: "examples/mnist/lenet_train_test.prototxt" 4 | # test_iter specifies how many forward passes the test should carry out. 5 | # In the case of MNIST, we have test batch size 100 and 100 test iterations, 6 | # covering the full 10,000 testing images. 7 | test_iter: 100 8 | # Carry out testing every 500 training iterations. 9 | test_interval: 500 10 | # All parameters are from the cited paper above 11 | base_lr: 0.001 12 | momentum: 0.9 13 | momentum2: 0.999 14 | # since Adam dynamically changes the learning rate, we set the base learning 15 | # rate to a fixed value 16 | lr_policy: "fixed" 17 | # Display every 100 iterations 18 | display: 100 19 | # The maximum number of iterations 20 | max_iter: 10000 21 | # snapshot intermediate results 22 | snapshot: 5000 23 | snapshot_prefix: "examples/mnist/lenet" 24 | # solver mode: CPU or GPU 25 | type: "Adam" 26 | solver_mode: GPU 27 | -------------------------------------------------------------------------------- /caffe3d/examples/mnist/lenet_solver_rmsprop.prototxt: -------------------------------------------------------------------------------- 1 | # The train/test net protocol buffer definition 2 | net: "examples/mnist/lenet_train_test.prototxt" 3 | # test_iter specifies how many forward passes the test should carry out. 4 | # In the case of MNIST, we have test batch size 100 and 100 test iterations, 5 | # covering the full 10,000 testing images. 6 | test_iter: 100 7 | # Carry out testing every 500 training iterations. 8 | test_interval: 500 9 | # The base learning rate, momentum and the weight decay of the network. 10 | base_lr: 0.01 11 | momentum: 0.0 12 | weight_decay: 0.0005 13 | # The learning rate policy 14 | lr_policy: "inv" 15 | gamma: 0.0001 16 | power: 0.75 17 | # Display every 100 iterations 18 | display: 100 19 | # The maximum number of iterations 20 | max_iter: 10000 21 | # snapshot intermediate results 22 | snapshot: 5000 23 | snapshot_prefix: "examples/mnist/lenet_rmsprop" 24 | # solver mode: CPU or GPU 25 | solver_mode: GPU 26 | type: "RMSProp" 27 | rms_decay: 0.98 28 | -------------------------------------------------------------------------------- /caffe3d/examples/mnist/mnist_autoencoder_solver.prototxt: -------------------------------------------------------------------------------- 1 | net: "examples/mnist/mnist_autoencoder.prototxt" 2 | test_state: { stage: 'test-on-train' } 3 | test_iter: 500 4 | test_state: { stage: 'test-on-test' } 5 | test_iter: 100 6 | test_interval: 500 7 | test_compute_loss: true 8 | base_lr: 0.01 9 | lr_policy: "step" 10 | gamma: 0.1 11 | stepsize: 10000 12 | display: 100 13 | max_iter: 65000 14 | weight_decay: 0.0005 15 | snapshot: 10000 16 | snapshot_prefix: "examples/mnist/mnist_autoencoder" 17 | momentum: 0.9 18 | # solver mode: CPU or GPU 19 | solver_mode: GPU 20 | -------------------------------------------------------------------------------- /caffe3d/examples/mnist/mnist_autoencoder_solver_adadelta.prototxt: -------------------------------------------------------------------------------- 1 | net: "examples/mnist/mnist_autoencoder.prototxt" 2 | test_state: { stage: 'test-on-train' } 3 | test_iter: 500 4 | test_state: { stage: 'test-on-test' } 5 | test_iter: 100 6 | test_interval: 500 7 | test_compute_loss: true 8 | base_lr: 1.0 9 | lr_policy: "fixed" 10 | momentum: 0.95 11 | delta: 1e-8 12 | display: 100 13 | max_iter: 65000 14 | weight_decay: 0.0005 15 | snapshot: 10000 16 | snapshot_prefix: "examples/mnist/mnist_autoencoder_adadelta_train" 17 | # solver mode: CPU or GPU 18 | solver_mode: GPU 19 | type: "AdaDelta" 20 | -------------------------------------------------------------------------------- /caffe3d/examples/mnist/mnist_autoencoder_solver_adagrad.prototxt: -------------------------------------------------------------------------------- 1 | net: "examples/mnist/mnist_autoencoder.prototxt" 2 | test_state: { stage: 'test-on-train' } 3 | test_iter: 500 4 | test_state: { stage: 'test-on-test' } 5 | test_iter: 100 6 | test_interval: 500 7 | test_compute_loss: true 8 | base_lr: 0.01 9 | lr_policy: "fixed" 10 | display: 100 11 | max_iter: 65000 12 | weight_decay: 0.0005 13 | snapshot: 10000 14 | snapshot_prefix: "examples/mnist/mnist_autoencoder_adagrad_train" 15 | # solver mode: CPU or GPU 16 | solver_mode: GPU 17 | type: "AdaGrad" 18 | -------------------------------------------------------------------------------- /caffe3d/examples/mnist/mnist_autoencoder_solver_nesterov.prototxt: -------------------------------------------------------------------------------- 1 | net: "examples/mnist/mnist_autoencoder.prototxt" 2 | test_state: { stage: 'test-on-train' } 3 | test_iter: 500 4 | test_state: { stage: 'test-on-test' } 5 | test_iter: 100 6 | test_interval: 500 7 | test_compute_loss: true 8 | base_lr: 0.01 9 | lr_policy: "step" 10 | gamma: 0.1 11 | stepsize: 10000 12 | display: 100 13 | max_iter: 65000 14 | weight_decay: 0.0005 15 | snapshot: 10000 16 | snapshot_prefix: "examples/mnist/mnist_autoencoder_nesterov_train" 17 | momentum: 0.95 18 | # solver mode: CPU or GPU 19 | solver_mode: GPU 20 | type: "Nesterov" 21 | -------------------------------------------------------------------------------- /caffe3d/examples/mnist/train_lenet.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | set -e 3 | 4 | ./build/tools/caffe train --solver=examples/mnist/lenet_solver.prototxt $@ 5 | -------------------------------------------------------------------------------- /caffe3d/examples/mnist/train_lenet_adam.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | set -e 3 | 4 | ./build/tools/caffe train --solver=examples/mnist/lenet_solver_adam.prototxt $@ 5 | -------------------------------------------------------------------------------- /caffe3d/examples/mnist/train_lenet_consolidated.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | set -e 3 | 4 | ./build/tools/caffe train \ 5 | --solver=examples/mnist/lenet_consolidated_solver.prototxt $@ 6 | -------------------------------------------------------------------------------- /caffe3d/examples/mnist/train_lenet_rmsprop.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | set -e 3 | 4 | ./build/tools/caffe train \ 5 | --solver=examples/mnist/lenet_solver_rmsprop.prototxt $@ 6 | -------------------------------------------------------------------------------- /caffe3d/examples/mnist/train_mnist_autoencoder.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | set -e 3 | 4 | ./build/tools/caffe train \ 5 | --solver=examples/mnist/mnist_autoencoder_solver.prototxt $@ 6 | -------------------------------------------------------------------------------- /caffe3d/examples/mnist/train_mnist_autoencoder_adadelta.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | set -e 3 | 4 | ./build/tools/caffe train \ 5 | --solver=examples/mnist/mnist_autoencoder_solver_adadelta.prototxt $@ 6 | -------------------------------------------------------------------------------- /caffe3d/examples/mnist/train_mnist_autoencoder_adagrad.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | set -e 3 | 4 | ./build/tools/caffe train \ 5 | --solver=examples/mnist/mnist_autoencoder_solver_adagrad.prototxt $@ 6 | -------------------------------------------------------------------------------- /caffe3d/examples/mnist/train_mnist_autoencoder_nesterov.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | set -e 3 | 4 | ./build/tools/caffe train \ 5 | --solver=examples/mnist/mnist_autoencoder_solver_nesterov.prototxt $@ 6 | -------------------------------------------------------------------------------- /caffe3d/examples/net_surgery/conv.prototxt: -------------------------------------------------------------------------------- 1 | # Simple single-layer network to showcase editing model parameters. 2 | name: "convolution" 3 | layer { 4 | name: "data" 5 | type: "Input" 6 | top: "data" 7 | input_param { shape: { dim: 1 dim: 1 dim: 100 dim: 100 } } 8 | } 9 | layer { 10 | name: "conv" 11 | type: "Convolution" 12 | bottom: "data" 13 | top: "conv" 14 | convolution_param { 15 | num_output: 3 16 | kernel_size: 5 17 | stride: 1 18 | weight_filler { 19 | type: "gaussian" 20 | std: 0.01 21 | } 22 | bias_filler { 23 | type: "constant" 24 | value: 0 25 | } 26 | } 27 | } 28 | -------------------------------------------------------------------------------- /caffe3d/examples/pycaffe/layers/pyloss.py: -------------------------------------------------------------------------------- 1 | import caffe 2 | import numpy as np 3 | 4 | 5 | class EuclideanLossLayer(caffe.Layer): 6 | """ 7 | Compute the Euclidean Loss in the same manner as the C++ EuclideanLossLayer 8 | to demonstrate the class interface for developing layers in Python. 9 | """ 10 | 11 | def setup(self, bottom, top): 12 | # check input pair 13 | if len(bottom) != 2: 14 | raise Exception("Need two inputs to compute distance.") 15 | 16 | def reshape(self, bottom, top): 17 | # check input dimensions match 18 | if bottom[0].count != bottom[1].count: 19 | raise Exception("Inputs must have the same dimension.") 20 | # difference is shape of inputs 21 | self.diff = np.zeros_like(bottom[0].data, dtype=np.float32) 22 | # loss output is scalar 23 | top[0].reshape(1) 24 | 25 | def forward(self, bottom, top): 26 | self.diff[...] = bottom[0].data - bottom[1].data 27 | top[0].data[...] = np.sum(self.diff**2) / bottom[0].num / 2. 28 | 29 | def backward(self, top, propagate_down, bottom): 30 | for i in range(2): 31 | if not propagate_down[i]: 32 | continue 33 | if i == 0: 34 | sign = 1 35 | else: 36 | sign = -1 37 | bottom[i].diff[...] = sign * self.diff / bottom[i].num 38 | -------------------------------------------------------------------------------- /caffe3d/examples/siamese/create_mnist_siamese.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | # This script converts the mnist data into leveldb format. 3 | set -e 4 | 5 | EXAMPLES=./build/examples/siamese 6 | DATA=./data/mnist 7 | 8 | echo "Creating leveldb..." 9 | 10 | rm -rf ./examples/siamese/mnist_siamese_train_leveldb 11 | rm -rf ./examples/siamese/mnist_siamese_test_leveldb 12 | 13 | $EXAMPLES/convert_mnist_siamese_data.bin \ 14 | $DATA/train-images-idx3-ubyte \ 15 | $DATA/train-labels-idx1-ubyte \ 16 | ./examples/siamese/mnist_siamese_train_leveldb 17 | $EXAMPLES/convert_mnist_siamese_data.bin \ 18 | $DATA/t10k-images-idx3-ubyte \ 19 | $DATA/t10k-labels-idx1-ubyte \ 20 | ./examples/siamese/mnist_siamese_test_leveldb 21 | 22 | echo "Done." 23 | -------------------------------------------------------------------------------- /caffe3d/examples/siamese/mnist_siamese_solver.prototxt: -------------------------------------------------------------------------------- 1 | # The train/test net protocol buffer definition 2 | net: "examples/siamese/mnist_siamese_train_test.prototxt" 3 | 4 | # test_iter specifies how many forward passes the test should carry out. 5 | # In the case of MNIST, we have test batch size 100 and 100 test iterations, 6 | # covering the full 10,000 testing images. 7 | test_iter: 100 8 | 9 | # Carry out testing every 500 training iterations. 10 | test_interval: 500 11 | 12 | # The base learning rate, momentum and the weight decay of the network. 13 | base_lr: 0.01 14 | momentum: 0.9 15 | weight_decay: 0.0000 16 | 17 | # The learning rate policy 18 | lr_policy: "inv" 19 | gamma: 0.0001 20 | power: 0.75 21 | 22 | # Display every 100 iterations 23 | display: 100 24 | 25 | # The maximum number of iterations 26 | max_iter: 50000 27 | 28 | # snapshot intermediate results 29 | snapshot: 5000 30 | snapshot_prefix: "examples/siamese/mnist_siamese" 31 | 32 | # solver mode: CPU or GPU 33 | solver_mode: GPU 34 | -------------------------------------------------------------------------------- /caffe3d/examples/siamese/mnist_siamese_solver.prototxt~: -------------------------------------------------------------------------------- 1 | # The train/test net protocol buffer definition 2 | net: "examples/siamese/mnist_siamese_train_test.prototxt" 3 | # test_iter specifies how many forward passes the test should carry out. 4 | # In the case of MNIST, we have test batch size 100 and 100 test iterations, 5 | # covering the full 10,000 testing images. 6 | test_iter: 100 7 | # Carry out testing every 500 training iterations. 8 | test_interval: 500 9 | # The base learning rate, momentum and the weight decay of the network. 10 | base_lr: 0.01 11 | momentum: 0.9 12 | weight_decay: 0.0000 13 | # The learning rate policy 14 | lr_policy: "inv" 15 | gamma: 0.0001 16 | power: 0.75 17 | # Display every 100 iterations 18 | display: 100 19 | # The maximum number of iterations 20 | max_iter: 50000 21 | # snapshot intermediate results 22 | snapshot: 5000 23 | snapshot_prefix: "examples/siamese/mnist_siamese" 24 | # solver mode: CPU or GPU 25 | solver_mode: GPU 26 | -------------------------------------------------------------------------------- /caffe3d/examples/siamese/train_mnist_siamese.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | set -e 3 | 4 | TOOLS=./build/tools 5 | 6 | $TOOLS/caffe train --solver=examples/siamese/mnist_siamese_solver.prototxt $@ 7 | -------------------------------------------------------------------------------- /caffe3d/examples/siamese_origin/create_mnist_siamese.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | # This script converts the mnist data into leveldb format. 3 | set -e 4 | 5 | EXAMPLES=./build/examples/siamese 6 | DATA=./data/mnist 7 | 8 | echo "Creating leveldb..." 9 | 10 | rm -rf ./examples/siamese/mnist_siamese_train_leveldb 11 | rm -rf ./examples/siamese/mnist_siamese_test_leveldb 12 | 13 | $EXAMPLES/convert_mnist_siamese_data.bin \ 14 | $DATA/train-images-idx3-ubyte \ 15 | $DATA/train-labels-idx1-ubyte \ 16 | ./examples/siamese/mnist_siamese_train_leveldb 17 | $EXAMPLES/convert_mnist_siamese_data.bin \ 18 | $DATA/t10k-images-idx3-ubyte \ 19 | $DATA/t10k-labels-idx1-ubyte \ 20 | ./examples/siamese/mnist_siamese_test_leveldb 21 | 22 | echo "Done." 23 | -------------------------------------------------------------------------------- /caffe3d/examples/siamese_origin/mnist_siamese_solver.prototxt: -------------------------------------------------------------------------------- 1 | # The train/test net protocol buffer definition 2 | net: "examples/siamese/mnist_siamese_train_test.prototxt" 3 | 4 | # test_iter specifies how many forward passes the test should carry out. 5 | # In the case of MNIST, we have test batch size 100 and 100 test iterations, 6 | # covering the full 10,000 testing images. 7 | test_iter: 100 8 | 9 | # Carry out testing every 500 training iterations. 10 | test_interval: 500 11 | 12 | # The base learning rate, momentum and the weight decay of the network. 13 | base_lr: 0.01 14 | momentum: 0.9 15 | weight_decay: 0.0000 16 | 17 | # The learning rate policy 18 | lr_policy: "inv" 19 | gamma: 0.0001 20 | power: 0.75 21 | 22 | # Display every 100 iterations 23 | display: 100 24 | 25 | # The maximum number of iterations 26 | max_iter: 50000 27 | 28 | # snapshot intermediate results 29 | snapshot: 5000 30 | snapshot_prefix: "examples/siamese/mnist_siamese" 31 | 32 | # solver mode: CPU or GPU 33 | solver_mode: GPU 34 | -------------------------------------------------------------------------------- /caffe3d/examples/siamese_origin/mnist_siamese_solver.prototxt~: -------------------------------------------------------------------------------- 1 | # The train/test net protocol buffer definition 2 | net: "examples/siamese/mnist_siamese_train_test.prototxt" 3 | # test_iter specifies how many forward passes the test should carry out. 4 | # In the case of MNIST, we have test batch size 100 and 100 test iterations, 5 | # covering the full 10,000 testing images. 6 | test_iter: 100 7 | # Carry out testing every 500 training iterations. 8 | test_interval: 500 9 | # The base learning rate, momentum and the weight decay of the network. 10 | base_lr: 0.01 11 | momentum: 0.9 12 | weight_decay: 0.0000 13 | # The learning rate policy 14 | lr_policy: "inv" 15 | gamma: 0.0001 16 | power: 0.75 17 | # Display every 100 iterations 18 | display: 100 19 | # The maximum number of iterations 20 | max_iter: 50000 21 | # snapshot intermediate results 22 | snapshot: 5000 23 | snapshot_prefix: "examples/siamese/mnist_siamese" 24 | # solver mode: CPU or GPU 25 | solver_mode: GPU 26 | -------------------------------------------------------------------------------- /caffe3d/examples/siamese_origin/train_mnist_siamese.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | set -e 3 | 4 | TOOLS=./build/tools 5 | 6 | $TOOLS/caffe train --solver=examples/siamese/mnist_siamese_solver.prototxt $@ 7 | -------------------------------------------------------------------------------- /caffe3d/examples/web_demo/exifutil.py: -------------------------------------------------------------------------------- 1 | """ 2 | This script handles the skimage exif problem. 3 | """ 4 | 5 | from PIL import Image 6 | import numpy as np 7 | 8 | ORIENTATIONS = { # used in apply_orientation 9 | 2: (Image.FLIP_LEFT_RIGHT,), 10 | 3: (Image.ROTATE_180,), 11 | 4: (Image.FLIP_TOP_BOTTOM,), 12 | 5: (Image.FLIP_LEFT_RIGHT, Image.ROTATE_90), 13 | 6: (Image.ROTATE_270,), 14 | 7: (Image.FLIP_LEFT_RIGHT, Image.ROTATE_270), 15 | 8: (Image.ROTATE_90,) 16 | } 17 | 18 | 19 | def open_oriented_im(im_path): 20 | im = Image.open(im_path) 21 | if hasattr(im, '_getexif'): 22 | exif = im._getexif() 23 | if exif is not None and 274 in exif: 24 | orientation = exif[274] 25 | im = apply_orientation(im, orientation) 26 | img = np.asarray(im).astype(np.float32) / 255. 27 | if img.ndim == 2: 28 | img = img[:, :, np.newaxis] 29 | img = np.tile(img, (1, 1, 3)) 30 | elif img.shape[2] == 4: 31 | img = img[:, :, :3] 32 | return img 33 | 34 | 35 | def apply_orientation(im, orientation): 36 | if orientation in ORIENTATIONS: 37 | for method in ORIENTATIONS[orientation]: 38 | im = im.transpose(method) 39 | return im 40 | -------------------------------------------------------------------------------- /caffe3d/examples/web_demo/requirements.txt: -------------------------------------------------------------------------------- 1 | werkzeug 2 | flask 3 | tornado 4 | numpy 5 | pandas 6 | pillow 7 | pyyaml 8 | -------------------------------------------------------------------------------- /caffe3d/include/caffe/caffe.hpp: -------------------------------------------------------------------------------- 1 | // caffe.hpp is the header file that you need to include in your code. It wraps 2 | // all the internal caffe header files into one for simpler inclusion. 3 | 4 | #ifndef CAFFE_CAFFE_HPP_ 5 | #define CAFFE_CAFFE_HPP_ 6 | 7 | #include "caffe/blob.hpp" 8 | #include "caffe/common.hpp" 9 | #include "caffe/filler.hpp" 10 | #include "caffe/layer.hpp" 11 | #include "caffe/layer_factory.hpp" 12 | #include "caffe/net.hpp" 13 | #include "caffe/parallel.hpp" 14 | #include "caffe/proto/caffe.pb.h" 15 | #include "caffe/solver.hpp" 16 | #include "caffe/solver_factory.hpp" 17 | #include "caffe/util/benchmark.hpp" 18 | #include "caffe/util/io.hpp" 19 | #include "caffe/util/upgrade_proto.hpp" 20 | 21 | #endif // CAFFE_CAFFE_HPP_ 22 | -------------------------------------------------------------------------------- /caffe3d/include/caffe/layers/cudnn_lrn_layer.hpp: -------------------------------------------------------------------------------- 1 | #ifndef CAFFE_CUDNN_LRN_LAYER_HPP_ 2 | #define CAFFE_CUDNN_LRN_LAYER_HPP_ 3 | 4 | #include 5 | 6 | #include "caffe/blob.hpp" 7 | #include "caffe/layer.hpp" 8 | #include "caffe/proto/caffe.pb.h" 9 | 10 | #include "caffe/layers/lrn_layer.hpp" 11 | 12 | namespace caffe { 13 | 14 | #ifdef USE_CUDNN 15 | template 16 | class CuDNNLRNLayer : public LRNLayer { 17 | public: 18 | explicit CuDNNLRNLayer(const LayerParameter& param) 19 | : LRNLayer(param), handles_setup_(false) {} 20 | virtual void LayerSetUp(const vector*>& bottom, 21 | const vector*>& top); 22 | virtual void Reshape(const vector*>& bottom, 23 | const vector*>& top); 24 | virtual ~CuDNNLRNLayer(); 25 | 26 | protected: 27 | virtual void Forward_gpu(const vector*>& bottom, 28 | const vector*>& top); 29 | virtual void Backward_gpu(const vector*>& top, 30 | const vector& propagate_down, const vector*>& bottom); 31 | 32 | bool handles_setup_; 33 | cudnnHandle_t handle_; 34 | cudnnLRNDescriptor_t norm_desc_; 35 | cudnnTensorDescriptor_t bottom_desc_, top_desc_; 36 | 37 | int size_; 38 | Dtype alpha_, beta_, k_; 39 | }; 40 | #endif 41 | 42 | } // namespace caffe 43 | 44 | #endif // CAFFE_CUDNN_LRN_LAYER_HPP_ 45 | -------------------------------------------------------------------------------- /caffe3d/include/caffe/layers/cudnn_relu_layer.hpp: -------------------------------------------------------------------------------- 1 | #ifndef CAFFE_CUDNN_RELU_LAYER_HPP_ 2 | #define CAFFE_CUDNN_RELU_LAYER_HPP_ 3 | 4 | #include 5 | 6 | #include "caffe/blob.hpp" 7 | #include "caffe/layer.hpp" 8 | #include "caffe/proto/caffe.pb.h" 9 | 10 | #include "caffe/layers/neuron_layer.hpp" 11 | #include "caffe/layers/relu_layer.hpp" 12 | 13 | namespace caffe { 14 | 15 | #ifdef USE_CUDNN 16 | /** 17 | * @brief CuDNN acceleration of ReLULayer. 18 | */ 19 | template 20 | class CuDNNReLULayer : public ReLULayer { 21 | public: 22 | explicit CuDNNReLULayer(const LayerParameter& param) 23 | : ReLULayer(param), handles_setup_(false) {} 24 | virtual void LayerSetUp(const vector*>& bottom, 25 | const vector*>& top); 26 | virtual void Reshape(const vector*>& bottom, 27 | const vector*>& top); 28 | virtual ~CuDNNReLULayer(); 29 | 30 | protected: 31 | virtual void Forward_gpu(const vector*>& bottom, 32 | const vector*>& top); 33 | virtual void Backward_gpu(const vector*>& top, 34 | const vector& propagate_down, const vector*>& bottom); 35 | 36 | bool handles_setup_; 37 | cudnnHandle_t handle_; 38 | cudnnTensorDescriptor_t bottom_desc_; 39 | cudnnTensorDescriptor_t top_desc_; 40 | cudnnActivationDescriptor_t activ_desc_; 41 | }; 42 | #endif 43 | 44 | } // namespace caffe 45 | 46 | #endif // CAFFE_CUDNN_RELU_LAYER_HPP_ 47 | -------------------------------------------------------------------------------- /caffe3d/include/caffe/layers/cudnn_sigmoid_layer.hpp: -------------------------------------------------------------------------------- 1 | #ifndef CAFFE_CUDNN_SIGMOID_LAYER_HPP_ 2 | #define CAFFE_CUDNN_SIGMOID_LAYER_HPP_ 3 | 4 | #include 5 | 6 | #include "caffe/blob.hpp" 7 | #include "caffe/layer.hpp" 8 | #include "caffe/proto/caffe.pb.h" 9 | 10 | #include "caffe/layers/neuron_layer.hpp" 11 | #include "caffe/layers/sigmoid_layer.hpp" 12 | 13 | namespace caffe { 14 | 15 | #ifdef USE_CUDNN 16 | /** 17 | * @brief CuDNN acceleration of SigmoidLayer. 18 | */ 19 | template 20 | class CuDNNSigmoidLayer : public SigmoidLayer { 21 | public: 22 | explicit CuDNNSigmoidLayer(const LayerParameter& param) 23 | : SigmoidLayer(param), handles_setup_(false) {} 24 | virtual void LayerSetUp(const vector*>& bottom, 25 | const vector*>& top); 26 | virtual void Reshape(const vector*>& bottom, 27 | const vector*>& top); 28 | virtual ~CuDNNSigmoidLayer(); 29 | 30 | protected: 31 | virtual void Forward_gpu(const vector*>& bottom, 32 | const vector*>& top); 33 | virtual void Backward_gpu(const vector*>& top, 34 | const vector& propagate_down, const vector*>& bottom); 35 | 36 | bool handles_setup_; 37 | cudnnHandle_t handle_; 38 | cudnnTensorDescriptor_t bottom_desc_; 39 | cudnnTensorDescriptor_t top_desc_; 40 | cudnnActivationDescriptor_t activ_desc_; 41 | }; 42 | #endif 43 | 44 | } // namespace caffe 45 | 46 | #endif // CAFFE_CUDNN_SIGMOID_LAYER_HPP_ 47 | -------------------------------------------------------------------------------- /caffe3d/include/caffe/layers/cudnn_softmax_layer.hpp: -------------------------------------------------------------------------------- 1 | #ifndef CAFFE_CUDNN_SOFTMAX_LAYER_HPP_ 2 | #define CAFFE_CUDNN_SOFTMAX_LAYER_HPP_ 3 | 4 | #include 5 | 6 | #include "caffe/blob.hpp" 7 | #include "caffe/layer.hpp" 8 | #include "caffe/proto/caffe.pb.h" 9 | 10 | #include "caffe/layers/softmax_layer.hpp" 11 | 12 | namespace caffe { 13 | 14 | #ifdef USE_CUDNN 15 | /** 16 | * @brief cuDNN implementation of SoftmaxLayer. 17 | * Fallback to SoftmaxLayer for CPU mode. 18 | */ 19 | template 20 | class CuDNNSoftmaxLayer : public SoftmaxLayer { 21 | public: 22 | explicit CuDNNSoftmaxLayer(const LayerParameter& param) 23 | : SoftmaxLayer(param), handles_setup_(false) {} 24 | virtual void LayerSetUp(const vector*>& bottom, 25 | const vector*>& top); 26 | virtual void Reshape(const vector*>& bottom, 27 | const vector*>& top); 28 | virtual ~CuDNNSoftmaxLayer(); 29 | 30 | protected: 31 | virtual void Forward_gpu(const vector*>& bottom, 32 | const vector*>& top); 33 | virtual void Backward_gpu(const vector*>& top, 34 | const vector& propagate_down, const vector*>& bottom); 35 | 36 | bool handles_setup_; 37 | cudnnHandle_t handle_; 38 | cudnnTensorDescriptor_t bottom_desc_; 39 | cudnnTensorDescriptor_t top_desc_; 40 | }; 41 | #endif 42 | 43 | } // namespace caffe 44 | 45 | #endif // CAFFE_CUDNN_SOFTMAX_LAYER_HPP_ 46 | -------------------------------------------------------------------------------- /caffe3d/include/caffe/layers/cudnn_tanh_layer.hpp: -------------------------------------------------------------------------------- 1 | #ifndef CAFFE_CUDNN_TANH_LAYER_HPP_ 2 | #define CAFFE_CUDNN_TANH_LAYER_HPP_ 3 | 4 | #include 5 | 6 | #include "caffe/blob.hpp" 7 | #include "caffe/layer.hpp" 8 | #include "caffe/proto/caffe.pb.h" 9 | 10 | #include "caffe/layers/neuron_layer.hpp" 11 | #include "caffe/layers/tanh_layer.hpp" 12 | 13 | namespace caffe { 14 | 15 | #ifdef USE_CUDNN 16 | /** 17 | * @brief CuDNN acceleration of TanHLayer. 18 | */ 19 | template 20 | class CuDNNTanHLayer : public TanHLayer { 21 | public: 22 | explicit CuDNNTanHLayer(const LayerParameter& param) 23 | : TanHLayer(param), handles_setup_(false) {} 24 | virtual void LayerSetUp(const vector*>& bottom, 25 | const vector*>& top); 26 | virtual void Reshape(const vector*>& bottom, 27 | const vector*>& top); 28 | virtual ~CuDNNTanHLayer(); 29 | 30 | protected: 31 | virtual void Forward_gpu(const vector*>& bottom, 32 | const vector*>& top); 33 | virtual void Backward_gpu(const vector*>& top, 34 | const vector& propagate_down, const vector*>& bottom); 35 | 36 | bool handles_setup_; 37 | cudnnHandle_t handle_; 38 | cudnnTensorDescriptor_t bottom_desc_; 39 | cudnnTensorDescriptor_t top_desc_; 40 | cudnnActivationDescriptor_t activ_desc_; 41 | }; 42 | #endif 43 | 44 | } // namespace caffe 45 | 46 | #endif // CAFFE_CUDNN_TANH_LAYER_HPP_ 47 | -------------------------------------------------------------------------------- /caffe3d/include/caffe/layers/data_layer.hpp: -------------------------------------------------------------------------------- 1 | #ifndef CAFFE_DATA_LAYER_HPP_ 2 | #define CAFFE_DATA_LAYER_HPP_ 3 | 4 | #include 5 | 6 | #include "caffe/blob.hpp" 7 | #include "caffe/data_reader.hpp" 8 | #include "caffe/data_transformer.hpp" 9 | #include "caffe/internal_thread.hpp" 10 | #include "caffe/layer.hpp" 11 | #include "caffe/layers/base_data_layer.hpp" 12 | #include "caffe/proto/caffe.pb.h" 13 | #include "caffe/util/db.hpp" 14 | 15 | namespace caffe { 16 | 17 | template 18 | class DataLayer : public BasePrefetchingDataLayer { 19 | public: 20 | explicit DataLayer(const LayerParameter& param); 21 | virtual ~DataLayer(); 22 | virtual void DataLayerSetUp(const vector*>& bottom, 23 | const vector*>& top); 24 | // DataLayer uses DataReader instead for sharing for parallelism 25 | virtual inline bool ShareInParallel() const { return false; } 26 | virtual inline const char* type() const { return "Data"; } 27 | virtual inline int ExactNumBottomBlobs() const { return 0; } 28 | virtual inline int MinTopBlobs() const { return 1; } 29 | virtual inline int MaxTopBlobs() const { return 2; } 30 | 31 | protected: 32 | virtual void load_batch(Batch* batch); 33 | 34 | DataReader reader_; 35 | }; 36 | 37 | } // namespace caffe 38 | 39 | #endif // CAFFE_DATA_LAYER_HPP_ 40 | -------------------------------------------------------------------------------- /caffe3d/include/caffe/layers/image_data_layer.hpp: -------------------------------------------------------------------------------- 1 | #ifndef CAFFE_IMAGE_DATA_LAYER_HPP_ 2 | #define CAFFE_IMAGE_DATA_LAYER_HPP_ 3 | 4 | #include 5 | #include 6 | #include 7 | 8 | #include "caffe/blob.hpp" 9 | #include "caffe/data_transformer.hpp" 10 | #include "caffe/internal_thread.hpp" 11 | #include "caffe/layer.hpp" 12 | #include "caffe/layers/base_data_layer.hpp" 13 | #include "caffe/proto/caffe.pb.h" 14 | 15 | namespace caffe { 16 | 17 | /** 18 | * @brief Provides data to the Net from image files. 19 | * 20 | * TODO(dox): thorough documentation for Forward and proto params. 21 | */ 22 | template 23 | class ImageDataLayer : public BasePrefetchingDataLayer { 24 | public: 25 | explicit ImageDataLayer(const LayerParameter& param) 26 | : BasePrefetchingDataLayer(param) {} 27 | virtual ~ImageDataLayer(); 28 | virtual void DataLayerSetUp(const vector*>& bottom, 29 | const vector*>& top); 30 | 31 | virtual inline const char* type() const { return "ImageData"; } 32 | virtual inline int ExactNumBottomBlobs() const { return 0; } 33 | virtual inline int ExactNumTopBlobs() const { return 2; } 34 | 35 | protected: 36 | shared_ptr prefetch_rng_; 37 | virtual void ShuffleImages(); 38 | virtual void load_batch(Batch* batch); 39 | 40 | vector > lines_; 41 | int lines_id_; 42 | }; 43 | 44 | 45 | } // namespace caffe 46 | 47 | #endif // CAFFE_IMAGE_DATA_LAYER_HPP_ 48 | -------------------------------------------------------------------------------- /caffe3d/include/caffe/layers/neuron_layer.hpp: -------------------------------------------------------------------------------- 1 | #ifndef CAFFE_NEURON_LAYER_HPP_ 2 | #define CAFFE_NEURON_LAYER_HPP_ 3 | 4 | #include 5 | 6 | #include "caffe/blob.hpp" 7 | #include "caffe/layer.hpp" 8 | #include "caffe/proto/caffe.pb.h" 9 | 10 | namespace caffe { 11 | 12 | /** 13 | * @brief An interface for layers that take one blob as input (@f$ x @f$) 14 | * and produce one equally-sized blob as output (@f$ y @f$), where 15 | * each element of the output depends only on the corresponding input 16 | * element. 17 | */ 18 | template 19 | class NeuronLayer : public Layer { 20 | public: 21 | explicit NeuronLayer(const LayerParameter& param) 22 | : Layer(param) {} 23 | virtual void Reshape(const vector*>& bottom, 24 | const vector*>& top); 25 | 26 | virtual inline int ExactNumBottomBlobs() const { return 1; } 27 | virtual inline int ExactNumTopBlobs() const { return 1; } 28 | }; 29 | 30 | } // namespace caffe 31 | 32 | #endif // CAFFE_NEURON_LAYER_HPP_ 33 | -------------------------------------------------------------------------------- /caffe3d/include/caffe/layers/similarity_layer.hpp: -------------------------------------------------------------------------------- 1 | #ifndef CAFFE_LOSS_LAYERS_HPP_ 2 | #define CAFFE_LOSS_LAYERS_HPP_ 3 | 4 | #include 5 | #include 6 | #include 7 | 8 | #include "caffe/blob.hpp" 9 | #include "caffe/common.hpp" 10 | #include "caffe/layer.hpp" 11 | #include "caffe/proto/caffe.pb.h" 12 | 13 | namespace caffe { 14 | 15 | /** 16 | * @brief An interface for Layer%s that take two Blob%s as input and output a 17 | * singleton Blob representing the similarity. 18 | */ 19 | template 20 | class SimilarityLayer : public Layer { 21 | public: 22 | explicit SimilarityLayer(const LayerParameter& param) 23 | : Layer(param) {} 24 | virtual void Reshape( 25 | const vector*>& bottom, const vector*>& top); 26 | 27 | virtual inline int ExactNumBottomBlobs() const { return 2; } 28 | virtual inline int ExactNumTopBlobs() const { return 1; } 29 | /** 30 | * We usually can backpropagate to both inputs. 31 | */ 32 | virtual inline bool AllowForceBackward(const int bottom_index) const { 33 | return true; 34 | } 35 | }; 36 | 37 | } // namespace caffe 38 | 39 | #endif // CAFFE_LOSS_LAYERS_HPP_ 40 | -------------------------------------------------------------------------------- /caffe3d/include/caffe/layers/tile_layer.hpp: -------------------------------------------------------------------------------- 1 | #ifndef CAFFE_TILE_LAYER_HPP_ 2 | #define CAFFE_TILE_LAYER_HPP_ 3 | 4 | #include 5 | 6 | #include "caffe/blob.hpp" 7 | #include "caffe/layer.hpp" 8 | #include "caffe/proto/caffe.pb.h" 9 | 10 | namespace caffe { 11 | 12 | /** 13 | * @brief Copy a Blob along specified dimensions. 14 | */ 15 | template 16 | class TileLayer : public Layer { 17 | public: 18 | explicit TileLayer(const LayerParameter& param) 19 | : Layer(param) {} 20 | virtual void Reshape(const vector*>& bottom, 21 | const vector*>& top); 22 | 23 | virtual inline const char* type() const { return "Tile"; } 24 | virtual inline int ExactNumBottomBlobs() const { return 1; } 25 | virtual inline int ExactNumTopBlobs() const { return 1; } 26 | 27 | protected: 28 | virtual void Forward_cpu(const vector*>& bottom, 29 | const vector*>& top); 30 | virtual void Forward_gpu(const vector*>& bottom, 31 | const vector*>& top); 32 | 33 | virtual void Backward_cpu(const vector*>& top, 34 | const vector& propagate_down, const vector*>& bottom); 35 | virtual void Backward_gpu(const vector*>& top, 36 | const vector& propagate_down, const vector*>& bottom); 37 | 38 | unsigned int axis_, tiles_, outer_dim_, inner_dim_; 39 | }; 40 | 41 | } // namespace caffe 42 | 43 | #endif // CAFFE_TILE_LAYER_HPP_ 44 | -------------------------------------------------------------------------------- /caffe3d/include/caffe/util/benchmark.hpp: -------------------------------------------------------------------------------- 1 | #ifndef CAFFE_UTIL_BENCHMARK_H_ 2 | #define CAFFE_UTIL_BENCHMARK_H_ 3 | 4 | #include 5 | 6 | #include "caffe/util/device_alternate.hpp" 7 | 8 | namespace caffe { 9 | 10 | class Timer { 11 | public: 12 | Timer(); 13 | virtual ~Timer(); 14 | virtual void Start(); 15 | virtual void Stop(); 16 | virtual float MilliSeconds(); 17 | virtual float MicroSeconds(); 18 | virtual float Seconds(); 19 | 20 | inline bool initted() { return initted_; } 21 | inline bool running() { return running_; } 22 | inline bool has_run_at_least_once() { return has_run_at_least_once_; } 23 | 24 | protected: 25 | void Init(); 26 | 27 | bool initted_; 28 | bool running_; 29 | bool has_run_at_least_once_; 30 | #ifndef CPU_ONLY 31 | cudaEvent_t start_gpu_; 32 | cudaEvent_t stop_gpu_; 33 | #endif 34 | boost::posix_time::ptime start_cpu_; 35 | boost::posix_time::ptime stop_cpu_; 36 | float elapsed_milliseconds_; 37 | float elapsed_microseconds_; 38 | }; 39 | 40 | class CPUTimer : public Timer { 41 | public: 42 | explicit CPUTimer(); 43 | virtual ~CPUTimer() {} 44 | virtual void Start(); 45 | virtual void Stop(); 46 | virtual float MilliSeconds(); 47 | virtual float MicroSeconds(); 48 | }; 49 | 50 | } // namespace caffe 51 | 52 | #endif // CAFFE_UTIL_BENCHMARK_H_ 53 | -------------------------------------------------------------------------------- /caffe3d/include/caffe/util/blocking_queue.hpp: -------------------------------------------------------------------------------- 1 | #ifndef CAFFE_UTIL_BLOCKING_QUEUE_HPP_ 2 | #define CAFFE_UTIL_BLOCKING_QUEUE_HPP_ 3 | 4 | #include 5 | #include 6 | 7 | namespace caffe { 8 | 9 | template 10 | class BlockingQueue { 11 | public: 12 | explicit BlockingQueue(); 13 | 14 | void push(const T& t); 15 | 16 | bool try_pop(T* t); 17 | 18 | // This logs a message if the threads needs to be blocked 19 | // useful for detecting e.g. when data feeding is too slow 20 | T pop(const string& log_on_wait = ""); 21 | 22 | bool try_peek(T* t); 23 | 24 | // Return element without removing it 25 | T peek(); 26 | 27 | size_t size() const; 28 | 29 | protected: 30 | /** 31 | Move synchronization fields out instead of including boost/thread.hpp 32 | to avoid a boost/NVCC issues (#1009, #1010) on OSX. Also fails on 33 | Linux CUDA 7.0.18. 34 | */ 35 | class sync; 36 | 37 | std::queue queue_; 38 | shared_ptr sync_; 39 | 40 | DISABLE_COPY_AND_ASSIGN(BlockingQueue); 41 | }; 42 | 43 | } // namespace caffe 44 | 45 | #endif 46 | -------------------------------------------------------------------------------- /caffe3d/include/caffe/util/db.hpp: -------------------------------------------------------------------------------- 1 | #ifndef CAFFE_UTIL_DB_HPP 2 | #define CAFFE_UTIL_DB_HPP 3 | 4 | #include 5 | 6 | #include "caffe/common.hpp" 7 | #include "caffe/proto/caffe.pb.h" 8 | 9 | namespace caffe { namespace db { 10 | 11 | enum Mode { READ, WRITE, NEW }; 12 | 13 | class Cursor { 14 | public: 15 | Cursor() { } 16 | virtual ~Cursor() { } 17 | virtual void SeekToFirst() = 0; 18 | virtual void Next() = 0; 19 | virtual string key() = 0; 20 | virtual string value() = 0; 21 | virtual bool valid() = 0; 22 | 23 | DISABLE_COPY_AND_ASSIGN(Cursor); 24 | }; 25 | 26 | class Transaction { 27 | public: 28 | Transaction() { } 29 | virtual ~Transaction() { } 30 | virtual void Put(const string& key, const string& value) = 0; 31 | virtual void Commit() = 0; 32 | 33 | DISABLE_COPY_AND_ASSIGN(Transaction); 34 | }; 35 | 36 | class DB { 37 | public: 38 | DB() { } 39 | virtual ~DB() { } 40 | virtual void Open(const string& source, Mode mode) = 0; 41 | virtual void Close() = 0; 42 | virtual Cursor* NewCursor() = 0; 43 | virtual Transaction* NewTransaction() = 0; 44 | 45 | DISABLE_COPY_AND_ASSIGN(DB); 46 | }; 47 | 48 | DB* GetDB(DataParameter::DB backend); 49 | DB* GetDB(const string& backend); 50 | 51 | } // namespace db 52 | } // namespace caffe 53 | 54 | #endif // CAFFE_UTIL_DB_HPP 55 | -------------------------------------------------------------------------------- /caffe3d/include/caffe/util/format.hpp: -------------------------------------------------------------------------------- 1 | #ifndef CAFFE_UTIL_FORMAT_H_ 2 | #define CAFFE_UTIL_FORMAT_H_ 3 | 4 | #include // NOLINT(readability/streams) 5 | #include // NOLINT(readability/streams) 6 | #include 7 | 8 | namespace caffe { 9 | 10 | inline std::string format_int(int n, int numberOfLeadingZeros = 0 ) { 11 | std::ostringstream s; 12 | s << std::setw(numberOfLeadingZeros) << std::setfill('0') << n; 13 | return s.str(); 14 | } 15 | 16 | } 17 | 18 | #endif // CAFFE_UTIL_FORMAT_H_ 19 | -------------------------------------------------------------------------------- /caffe3d/include/caffe/util/gpu_util.cuh: -------------------------------------------------------------------------------- 1 | #ifndef CAFFE_UTIL_GPU_UTIL_H_ 2 | #define CAFFE_UTIL_GPU_UTIL_H_ 3 | 4 | namespace caffe { 5 | 6 | template 7 | inline __device__ Dtype caffe_gpu_atomic_add(const Dtype val, Dtype* address); 8 | 9 | template <> 10 | inline __device__ 11 | float caffe_gpu_atomic_add(const float val, float* address) { 12 | return atomicAdd(address, val); 13 | } 14 | 15 | // double atomicAdd implementation taken from: 16 | // http://docs.nvidia.com/cuda/cuda-c-programming-guide/#axzz3PVCpVsEG 17 | template <> 18 | inline __device__ 19 | double caffe_gpu_atomic_add(const double val, double* address) { 20 | unsigned long long int* address_as_ull = // NOLINT(runtime/int) 21 | // NOLINT_NEXT_LINE(runtime/int) 22 | reinterpret_cast(address); 23 | unsigned long long int old = *address_as_ull; // NOLINT(runtime/int) 24 | unsigned long long int assumed; // NOLINT(runtime/int) 25 | do { 26 | assumed = old; 27 | old = atomicCAS(address_as_ull, assumed, 28 | __double_as_longlong(val + __longlong_as_double(assumed))); 29 | } while (assumed != old); 30 | return __longlong_as_double(old); 31 | } 32 | 33 | } // namespace caffe 34 | 35 | #endif // CAFFE_UTIL_GPU_UTIL_H_ 36 | -------------------------------------------------------------------------------- /caffe3d/include/caffe/util/hdf5.hpp: -------------------------------------------------------------------------------- 1 | #ifndef CAFFE_UTIL_HDF5_H_ 2 | #define CAFFE_UTIL_HDF5_H_ 3 | 4 | #include 5 | 6 | #include "hdf5.h" 7 | #include "hdf5_hl.h" 8 | 9 | #include "caffe/blob.hpp" 10 | 11 | namespace caffe { 12 | 13 | template 14 | void hdf5_load_nd_dataset_helper( 15 | hid_t file_id, const char* dataset_name_, int min_dim, int max_dim, 16 | Blob* blob); 17 | 18 | template 19 | void hdf5_load_nd_dataset( 20 | hid_t file_id, const char* dataset_name_, int min_dim, int max_dim, 21 | Blob* blob); 22 | 23 | template 24 | void hdf5_save_nd_dataset( 25 | const hid_t file_id, const string& dataset_name, const Blob& blob, 26 | bool write_diff = false); 27 | 28 | int hdf5_load_int(hid_t loc_id, const string& dataset_name); 29 | void hdf5_save_int(hid_t loc_id, const string& dataset_name, int i); 30 | string hdf5_load_string(hid_t loc_id, const string& dataset_name); 31 | void hdf5_save_string(hid_t loc_id, const string& dataset_name, 32 | const string& s); 33 | 34 | int hdf5_get_num_links(hid_t loc_id); 35 | string hdf5_get_name_by_idx(hid_t loc_id, int idx); 36 | 37 | } // namespace caffe 38 | 39 | #endif // CAFFE_UTIL_HDF5_H_ 40 | -------------------------------------------------------------------------------- /caffe3d/include/caffe/util/image_io.hpp: -------------------------------------------------------------------------------- 1 | #ifndef IMAGE_IO_HPP_ 2 | #define IMAGE_IO_HPP_ 3 | 4 | 5 | #include 6 | 7 | #include "caffe/blob.hpp" 8 | 9 | using std::string; 10 | 11 | namespace caffe { 12 | 13 | template 14 | bool save_blob_to_binary(Blob* blob, 15 | const string fn_blob, int num_index); 16 | 17 | template 18 | inline bool save_blob_to_binary(Blob* blob, 19 | const string fn_blob) { 20 | return save_blob_to_binary(blob, fn_blob, -1); 21 | } 22 | 23 | 24 | } // namespace caffe 25 | 26 | 27 | #endif /* IMAGE_IO_HPP_ */ 28 | -------------------------------------------------------------------------------- /caffe3d/include/caffe/util/insert_splits.hpp: -------------------------------------------------------------------------------- 1 | #ifndef _CAFFE_UTIL_INSERT_SPLITS_HPP_ 2 | #define _CAFFE_UTIL_INSERT_SPLITS_HPP_ 3 | 4 | #include 5 | 6 | #include "caffe/proto/caffe.pb.h" 7 | 8 | namespace caffe { 9 | 10 | // Copy NetParameters with SplitLayers added to replace any shared bottom 11 | // blobs with unique bottom blobs provided by the SplitLayer. 12 | void InsertSplits(const NetParameter& param, NetParameter* param_split); 13 | 14 | void ConfigureSplitLayer(const string& layer_name, const string& blob_name, 15 | const int blob_idx, const int split_count, const float loss_weight, 16 | LayerParameter* split_layer_param); 17 | 18 | string SplitLayerName(const string& layer_name, const string& blob_name, 19 | const int blob_idx); 20 | 21 | string SplitBlobName(const string& layer_name, const string& blob_name, 22 | const int blob_idx, const int split_idx); 23 | 24 | } // namespace caffe 25 | 26 | #endif // CAFFE_UTIL_INSERT_SPLITS_HPP_ 27 | -------------------------------------------------------------------------------- /caffe3d/include/caffe/util/rng.hpp: -------------------------------------------------------------------------------- 1 | #ifndef CAFFE_RNG_CPP_HPP_ 2 | #define CAFFE_RNG_CPP_HPP_ 3 | 4 | #include 5 | #include 6 | 7 | #include "boost/random/mersenne_twister.hpp" 8 | #include "boost/random/uniform_int.hpp" 9 | 10 | #include "caffe/common.hpp" 11 | 12 | namespace caffe { 13 | 14 | typedef boost::mt19937 rng_t; 15 | 16 | inline rng_t* caffe_rng() { 17 | return static_cast(Caffe::rng_stream().generator()); 18 | } 19 | 20 | // Fisher–Yates algorithm 21 | template 22 | inline void shuffle(RandomAccessIterator begin, RandomAccessIterator end, 23 | RandomGenerator* gen) { 24 | typedef typename std::iterator_traits::difference_type 25 | difference_type; 26 | typedef typename boost::uniform_int dist_type; 27 | 28 | difference_type length = std::distance(begin, end); 29 | if (length <= 0) return; 30 | 31 | for (difference_type i = length - 1; i > 0; --i) { 32 | dist_type dist(0, i); 33 | std::iter_swap(begin + i, begin + dist(*gen)); 34 | } 35 | } 36 | 37 | template 38 | inline void shuffle(RandomAccessIterator begin, RandomAccessIterator end) { 39 | shuffle(begin, end, caffe_rng()); 40 | } 41 | } // namespace caffe 42 | 43 | #endif // CAFFE_RNG_HPP_ 44 | -------------------------------------------------------------------------------- /caffe3d/include/caffe/util/signal_handler.h: -------------------------------------------------------------------------------- 1 | #ifndef INCLUDE_CAFFE_UTIL_SIGNAL_HANDLER_H_ 2 | #define INCLUDE_CAFFE_UTIL_SIGNAL_HANDLER_H_ 3 | 4 | #include "caffe/proto/caffe.pb.h" 5 | #include "caffe/solver.hpp" 6 | 7 | namespace caffe { 8 | 9 | class SignalHandler { 10 | public: 11 | // Contructor. Specify what action to take when a signal is received. 12 | SignalHandler(SolverAction::Enum SIGINT_action, 13 | SolverAction::Enum SIGHUP_action); 14 | ~SignalHandler(); 15 | ActionCallback GetActionFunction(); 16 | private: 17 | SolverAction::Enum CheckForSignals() const; 18 | SolverAction::Enum SIGINT_action_; 19 | SolverAction::Enum SIGHUP_action_; 20 | }; 21 | 22 | } // namespace caffe 23 | 24 | #endif // INCLUDE_CAFFE_UTIL_SIGNAL_HANDLER_H_ 25 | -------------------------------------------------------------------------------- /caffe3d/matlab/+caffe/+test/test_io.m: -------------------------------------------------------------------------------- 1 | classdef test_io < matlab.unittest.TestCase 2 | methods (Test) 3 | function test_read_write_mean(self) 4 | % randomly generate mean data 5 | width = 200; 6 | height = 300; 7 | channels = 3; 8 | mean_data_write = 255 * rand(width, height, channels, 'single'); 9 | % write mean data to binary proto 10 | mean_proto_file = tempname(); 11 | caffe.io.write_mean(mean_data_write, mean_proto_file); 12 | % read mean data from saved binary proto and test whether they are equal 13 | mean_data_read = caffe.io.read_mean(mean_proto_file); 14 | self.verifyEqual(mean_data_write, mean_data_read) 15 | delete(mean_proto_file); 16 | end 17 | end 18 | end 19 | -------------------------------------------------------------------------------- /caffe3d/matlab/+caffe/Layer.m: -------------------------------------------------------------------------------- 1 | classdef Layer < handle 2 | % Wrapper class of caffe::Layer in matlab 3 | 4 | properties (Access = private) 5 | hLayer_self 6 | attributes 7 | % attributes fields: 8 | % hBlob_blobs 9 | end 10 | properties (SetAccess = private) 11 | params 12 | end 13 | 14 | methods 15 | function self = Layer(hLayer_layer) 16 | CHECK(is_valid_handle(hLayer_layer), 'invalid Layer handle'); 17 | 18 | % setup self handle and attributes 19 | self.hLayer_self = hLayer_layer; 20 | self.attributes = caffe_('layer_get_attr', self.hLayer_self); 21 | 22 | % setup weights 23 | self.params = caffe.Blob.empty(); 24 | for n = 1:length(self.attributes.hBlob_blobs) 25 | self.params(n) = caffe.Blob(self.attributes.hBlob_blobs(n)); 26 | end 27 | end 28 | function layer_type = type(self) 29 | layer_type = caffe_('layer_get_type', self.hLayer_self); 30 | end 31 | end 32 | end 33 | -------------------------------------------------------------------------------- /caffe3d/matlab/+caffe/get_net.m: -------------------------------------------------------------------------------- 1 | function net = get_net(varargin) 2 | % net = get_net(model_file, phase_name) or 3 | % net = get_net(model_file, weights_file, phase_name) 4 | % Construct a net from model_file, and load weights from weights_file 5 | % phase_name can only be 'train' or 'test' 6 | 7 | CHECK(nargin == 2 || nargin == 3, ['usage: ' ... 8 | 'net = get_net(model_file, phase_name) or ' ... 9 | 'net = get_net(model_file, weights_file, phase_name)']); 10 | if nargin == 3 11 | model_file = varargin{1}; 12 | weights_file = varargin{2}; 13 | phase_name = varargin{3}; 14 | elseif nargin == 2 15 | model_file = varargin{1}; 16 | phase_name = varargin{2}; 17 | end 18 | 19 | CHECK(ischar(model_file), 'model_file must be a string'); 20 | CHECK(ischar(phase_name), 'phase_name must be a string'); 21 | CHECK_FILE_EXIST(model_file); 22 | CHECK(strcmp(phase_name, 'train') || strcmp(phase_name, 'test'), ... 23 | sprintf('phase_name can only be %strain%s or %stest%s', ... 24 | char(39), char(39), char(39), char(39))); 25 | 26 | % construct caffe net from model_file 27 | hNet = caffe_('get_net', model_file, phase_name); 28 | net = caffe.Net(hNet); 29 | 30 | % load weights from weights_file 31 | if nargin == 3 32 | CHECK(ischar(weights_file), 'weights_file must be a string'); 33 | CHECK_FILE_EXIST(weights_file); 34 | net.copy_from(weights_file); 35 | end 36 | 37 | end 38 | -------------------------------------------------------------------------------- /caffe3d/matlab/+caffe/get_solver.m: -------------------------------------------------------------------------------- 1 | function solver = get_solver(solver_file) 2 | % solver = get_solver(solver_file) 3 | % Construct a Solver object from solver_file 4 | 5 | CHECK(ischar(solver_file), 'solver_file must be a string'); 6 | CHECK_FILE_EXIST(solver_file); 7 | pSolver = caffe_('get_solver', solver_file); 8 | solver = caffe.Solver(pSolver); 9 | 10 | end 11 | -------------------------------------------------------------------------------- /caffe3d/matlab/+caffe/imagenet/ilsvrc_2012_mean.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/matlab/+caffe/imagenet/ilsvrc_2012_mean.mat -------------------------------------------------------------------------------- /caffe3d/matlab/+caffe/private/CHECK.m: -------------------------------------------------------------------------------- 1 | function CHECK(expr, error_msg) 2 | 3 | if ~expr 4 | error(error_msg); 5 | end 6 | 7 | end 8 | -------------------------------------------------------------------------------- /caffe3d/matlab/+caffe/private/CHECK_FILE_EXIST.m: -------------------------------------------------------------------------------- 1 | function CHECK_FILE_EXIST(filename) 2 | 3 | if exist(filename, 'file') == 0 4 | error('%s does not exist', filename); 5 | end 6 | 7 | end 8 | -------------------------------------------------------------------------------- /caffe3d/matlab/+caffe/private/is_valid_handle.m: -------------------------------------------------------------------------------- 1 | function valid = is_valid_handle(hObj) 2 | % valid = is_valid_handle(hObj) or is_valid_handle('get_new_init_key') 3 | % Check if a handle is valid (has the right data type and init_key matches) 4 | % Use is_valid_handle('get_new_init_key') to get new init_key from C++; 5 | 6 | % a handle is a struct array with the following fields 7 | % (uint64) ptr : the pointer to the C++ object 8 | % (double) init_key : caffe initialization key 9 | 10 | persistent init_key; 11 | if isempty(init_key) 12 | init_key = caffe_('get_init_key'); 13 | end 14 | 15 | % is_valid_handle('get_new_init_key') to get new init_key from C++; 16 | if ischar(hObj) && strcmp(hObj, 'get_new_init_key') 17 | init_key = caffe_('get_init_key'); 18 | return 19 | else 20 | % check whether data types are correct and init_key matches 21 | valid = isstruct(hObj) ... 22 | && isscalar(hObj.ptr) && isa(hObj.ptr, 'uint64') ... 23 | && isscalar(hObj.init_key) && isa(hObj.init_key, 'double') ... 24 | && hObj.init_key == init_key; 25 | end 26 | 27 | end 28 | -------------------------------------------------------------------------------- /caffe3d/matlab/+caffe/reset_all.m: -------------------------------------------------------------------------------- 1 | function reset_all() 2 | % reset_all() 3 | % clear all solvers and stand-alone nets and reset Caffe to initial status 4 | 5 | caffe_('reset'); 6 | is_valid_handle('get_new_init_key'); 7 | 8 | end 9 | -------------------------------------------------------------------------------- /caffe3d/matlab/+caffe/run_tests.m: -------------------------------------------------------------------------------- 1 | function results = run_tests() 2 | % results = run_tests() 3 | % run all tests in this caffe matlab wrapper package 4 | 5 | % use CPU for testing 6 | caffe.set_mode_cpu(); 7 | 8 | % reset caffe before testing 9 | caffe.reset_all(); 10 | 11 | % put all test cases here 12 | results = [... 13 | run(caffe.test.test_net) ... 14 | run(caffe.test.test_solver) ... 15 | run(caffe.test.test_io) ]; 16 | 17 | % reset caffe after testing 18 | caffe.reset_all(); 19 | 20 | end 21 | -------------------------------------------------------------------------------- /caffe3d/matlab/+caffe/set_device.m: -------------------------------------------------------------------------------- 1 | function set_device(device_id) 2 | % set_device(device_id) 3 | % set Caffe's GPU device ID 4 | 5 | CHECK(isscalar(device_id) && device_id >= 0, ... 6 | 'device_id must be non-negative integer'); 7 | device_id = double(device_id); 8 | 9 | caffe_('set_device', device_id); 10 | 11 | end 12 | -------------------------------------------------------------------------------- /caffe3d/matlab/+caffe/set_mode_cpu.m: -------------------------------------------------------------------------------- 1 | function set_mode_cpu() 2 | % set_mode_cpu() 3 | % set Caffe to CPU mode 4 | 5 | caffe_('set_mode_cpu'); 6 | 7 | end 8 | -------------------------------------------------------------------------------- /caffe3d/matlab/+caffe/set_mode_gpu.m: -------------------------------------------------------------------------------- 1 | function set_mode_gpu() 2 | % set_mode_gpu() 3 | % set Caffe to GPU mode 4 | 5 | caffe_('set_mode_gpu'); 6 | 7 | end 8 | -------------------------------------------------------------------------------- /caffe3d/matlab/+caffe/version.m: -------------------------------------------------------------------------------- 1 | function version_str = version() 2 | % version() 3 | % show Caffe's version. 4 | 5 | version_str = caffe_('version'); 6 | 7 | end 8 | -------------------------------------------------------------------------------- /caffe3d/models/bvlc_alexnet/readme.md: -------------------------------------------------------------------------------- 1 | --- 2 | name: BVLC AlexNet Model 3 | caffemodel: bvlc_alexnet.caffemodel 4 | caffemodel_url: http://dl.caffe.berkeleyvision.org/bvlc_alexnet.caffemodel 5 | license: unrestricted 6 | sha1: 9116a64c0fbe4459d18f4bb6b56d647b63920377 7 | caffe_commit: 709dc15af4a06bebda027c1eb2b3f3e3375d5077 8 | --- 9 | 10 | This model is a replication of the model described in the [AlexNet](http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks) publication. 11 | 12 | Differences: 13 | - not training with the relighting data-augmentation; 14 | - initializing non-zero biases to 0.1 instead of 1 (found necessary for training, as initialization to 1 gave flat loss). 15 | 16 | The bundled model is the iteration 360,000 snapshot. 17 | The best validation performance during training was iteration 358,000 with validation accuracy 57.258% and loss 1.83948. 18 | This model obtains a top-1 accuracy 57.1% and a top-5 accuracy 80.2% on the validation set, using just the center crop. 19 | (Using the average of 10 crops, (4 + 1 center) * 2 mirror, should obtain a bit higher accuracy.) 20 | 21 | This model was trained by Evan Shelhamer @shelhamer 22 | 23 | ## License 24 | 25 | This model is released for unrestricted use. 26 | -------------------------------------------------------------------------------- /caffe3d/models/bvlc_alexnet/solver.prototxt: -------------------------------------------------------------------------------- 1 | net: "models/bvlc_alexnet/train_val.prototxt" 2 | test_iter: 1000 3 | test_interval: 1000 4 | base_lr: 0.01 5 | lr_policy: "step" 6 | gamma: 0.1 7 | stepsize: 100000 8 | display: 20 9 | max_iter: 450000 10 | momentum: 0.9 11 | weight_decay: 0.0005 12 | snapshot: 10000 13 | snapshot_prefix: "models/bvlc_alexnet/caffe_alexnet_train" 14 | solver_mode: GPU 15 | -------------------------------------------------------------------------------- /caffe3d/models/bvlc_googlenet/quick_solver.prototxt: -------------------------------------------------------------------------------- 1 | net: "models/bvlc_googlenet/train_val.prototxt" 2 | test_iter: 1000 3 | test_interval: 4000 4 | test_initialization: false 5 | display: 40 6 | average_loss: 40 7 | base_lr: 0.01 8 | lr_policy: "poly" 9 | power: 0.5 10 | max_iter: 2400000 11 | momentum: 0.9 12 | weight_decay: 0.0002 13 | snapshot: 40000 14 | snapshot_prefix: "models/bvlc_googlenet/bvlc_googlenet_quick" 15 | solver_mode: GPU 16 | -------------------------------------------------------------------------------- /caffe3d/models/bvlc_googlenet/solver.prototxt: -------------------------------------------------------------------------------- 1 | net: "models/bvlc_googlenet/train_val.prototxt" 2 | test_iter: 1000 3 | test_interval: 4000 4 | test_initialization: false 5 | display: 40 6 | average_loss: 40 7 | base_lr: 0.01 8 | lr_policy: "step" 9 | stepsize: 320000 10 | gamma: 0.96 11 | max_iter: 10000000 12 | momentum: 0.9 13 | weight_decay: 0.0002 14 | snapshot: 40000 15 | snapshot_prefix: "models/bvlc_googlenet/bvlc_googlenet" 16 | solver_mode: GPU 17 | -------------------------------------------------------------------------------- /caffe3d/models/bvlc_reference_caffenet/readme.md: -------------------------------------------------------------------------------- 1 | --- 2 | name: BVLC CaffeNet Model 3 | caffemodel: bvlc_reference_caffenet.caffemodel 4 | caffemodel_url: http://dl.caffe.berkeleyvision.org/bvlc_reference_caffenet.caffemodel 5 | license: unrestricted 6 | sha1: 4c8d77deb20ea792f84eb5e6d0a11ca0a8660a46 7 | caffe_commit: 709dc15af4a06bebda027c1eb2b3f3e3375d5077 8 | --- 9 | 10 | This model is the result of following the Caffe [ImageNet model training instructions](http://caffe.berkeleyvision.org/gathered/examples/imagenet.html). 11 | It is a replication of the model described in the [AlexNet](http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks) publication with some differences: 12 | 13 | - not training with the relighting data-augmentation; 14 | - the order of pooling and normalization layers is switched (in CaffeNet, pooling is done before normalization). 15 | 16 | This model is snapshot of iteration 310,000. 17 | The best validation performance during training was iteration 313,000 with validation accuracy 57.412% and loss 1.82328. 18 | This model obtains a top-1 accuracy 57.4% and a top-5 accuracy 80.4% on the validation set, using just the center crop. 19 | (Using the average of 10 crops, (4 + 1 center) * 2 mirror, should obtain a bit higher accuracy still.) 20 | 21 | This model was trained by Jeff Donahue @jeffdonahue 22 | 23 | ## License 24 | 25 | This model is released for unrestricted use. 26 | -------------------------------------------------------------------------------- /caffe3d/models/bvlc_reference_caffenet/solver.prototxt: -------------------------------------------------------------------------------- 1 | net: "models/bvlc_reference_caffenet/train_val.prototxt" 2 | test_iter: 1000 3 | test_interval: 1000 4 | base_lr: 0.01 5 | lr_policy: "step" 6 | gamma: 0.1 7 | stepsize: 100000 8 | display: 20 9 | max_iter: 450000 10 | momentum: 0.9 11 | weight_decay: 0.0005 12 | snapshot: 10000 13 | snapshot_prefix: "models/bvlc_reference_caffenet/caffenet_train" 14 | solver_mode: GPU 15 | -------------------------------------------------------------------------------- /caffe3d/models/bvlc_reference_rcnn_ilsvrc13/readme.md: -------------------------------------------------------------------------------- 1 | --- 2 | name: BVLC Reference RCNN ILSVRC13 Model 3 | caffemodel: bvlc_reference_rcnn_ilsvrc13.caffemodel 4 | caffemodel_url: http://dl.caffe.berkeleyvision.org/bvlc_reference_rcnn_ilsvrc13.caffemodel 5 | license: unrestricted 6 | sha1: bdd8abb885819cba5e2fe1eb36235f2319477e64 7 | caffe_commit: a7e397abbda52c0b90323c23ab95bdeabee90a98 8 | --- 9 | 10 | The pure Caffe instantiation of the [R-CNN](https://github.com/rbgirshick/rcnn) model for ILSVRC13 detection. 11 | This model was made by transplanting the R-CNN SVM classifiers into a `fc-rcnn` classification layer, provided here as an off-the-shelf Caffe detector. 12 | Try the [detection example](http://nbviewer.ipython.org/github/BVLC/caffe/blob/master/examples/detection.ipynb) to see it in action. 13 | 14 | *N.B. For research purposes, make use of the official R-CNN package and not this example.* 15 | 16 | This model was trained by Ross Girshick @rbgirshick 17 | 18 | ## License 19 | 20 | This model is released for unrestricted use. 21 | -------------------------------------------------------------------------------- /caffe3d/models/finetune_flickr_style/readme.md: -------------------------------------------------------------------------------- 1 | --- 2 | name: Finetuning CaffeNet on Flickr Style 3 | caffemodel: finetune_flickr_style.caffemodel 4 | caffemodel_url: http://dl.caffe.berkeleyvision.org/finetune_flickr_style.caffemodel 5 | license: non-commercial 6 | sha1: b61b5cef7d771b53b0c488e78d35ccadc073e9cf 7 | caffe_commit: 737ea5e936821b5c69f9c3952d72693ae5843370 8 | gist_id: 034c6ac3865563b69e60 9 | --- 10 | 11 | This model is trained exactly as described in `docs/finetune_flickr_style/readme.md`, using all 80000 images. 12 | The final performance: 13 | 14 | I1017 07:36:17.370688 31333 solver.cpp:228] Iteration 100000, loss = 0.757952 15 | I1017 07:36:17.370730 31333 solver.cpp:247] Iteration 100000, Testing net (#0) 16 | I1017 07:36:34.248730 31333 solver.cpp:298] Test net output #0: accuracy = 0.3916 17 | 18 | This model was trained by Sergey Karayev @sergeyk 19 | 20 | ## License 21 | 22 | The Flickr Style dataset contains only URLs to images. 23 | Some of the images may have copyright. 24 | Training a category-recognition model for research/non-commercial use may constitute fair use of this data, but the result should not be used for commercial purposes. 25 | -------------------------------------------------------------------------------- /caffe3d/models/finetune_flickr_style/solver.prototxt: -------------------------------------------------------------------------------- 1 | net: "models/finetune_flickr_style/train_val.prototxt" 2 | test_iter: 100 3 | test_interval: 1000 4 | # lr for fine-tuning should be lower than when starting from scratch 5 | base_lr: 0.001 6 | lr_policy: "step" 7 | gamma: 0.1 8 | # stepsize should also be lower, as we're closer to being done 9 | stepsize: 20000 10 | display: 20 11 | max_iter: 100000 12 | momentum: 0.9 13 | weight_decay: 0.0005 14 | snapshot: 10000 15 | snapshot_prefix: "models/finetune_flickr_style/finetune_flickr_style" 16 | # uncomment the following to default to CPU mode solving 17 | # solver_mode: CPU 18 | -------------------------------------------------------------------------------- /caffe3d/python/caffe/__init__.py: -------------------------------------------------------------------------------- 1 | from .pycaffe import Net, SGDSolver, NesterovSolver, AdaGradSolver, RMSPropSolver, AdaDeltaSolver, AdamSolver 2 | from ._caffe import set_mode_cpu, set_mode_gpu, set_device, Layer, get_solver, layer_type_list, set_random_seed 3 | from ._caffe import __version__ 4 | from .proto.caffe_pb2 import TRAIN, TEST 5 | from .classifier import Classifier 6 | from .detector import Detector 7 | from . import io 8 | from .net_spec import layers, params, NetSpec, to_proto 9 | -------------------------------------------------------------------------------- /caffe3d/python/caffe/__init__.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/python/caffe/__init__.pyc -------------------------------------------------------------------------------- /caffe3d/python/caffe/classifier.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/python/caffe/classifier.pyc -------------------------------------------------------------------------------- /caffe3d/python/caffe/detector.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/python/caffe/detector.pyc -------------------------------------------------------------------------------- /caffe3d/python/caffe/draw.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/python/caffe/draw.pyc -------------------------------------------------------------------------------- /caffe3d/python/caffe/imagenet/ilsvrc_2012_mean.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/python/caffe/imagenet/ilsvrc_2012_mean.npy -------------------------------------------------------------------------------- /caffe3d/python/caffe/io.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/python/caffe/io.pyc -------------------------------------------------------------------------------- /caffe3d/python/caffe/net_spec.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/python/caffe/net_spec.pyc -------------------------------------------------------------------------------- /caffe3d/python/caffe/pycaffe.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/python/caffe/pycaffe.pyc -------------------------------------------------------------------------------- /caffe3d/python/caffe/test/test_layer_type_list.py: -------------------------------------------------------------------------------- 1 | import unittest 2 | 3 | import caffe 4 | 5 | class TestLayerTypeList(unittest.TestCase): 6 | 7 | def test_standard_types(self): 8 | #removing 'Data' from list 9 | for type_name in ['Data', 'Convolution', 'InnerProduct']: 10 | self.assertIn(type_name, caffe.layer_type_list(), 11 | '%s not in layer_type_list()' % type_name) 12 | -------------------------------------------------------------------------------- /caffe3d/python/requirements.txt: -------------------------------------------------------------------------------- 1 | Cython>=0.19.2 2 | numpy>=1.7.1 3 | scipy>=0.13.2 4 | scikit-image>=0.9.3 5 | matplotlib>=1.3.1 6 | ipython>=3.0.0 7 | h5py>=2.2.0 8 | leveldb>=0.191 9 | networkx>=1.8.1 10 | nose>=1.3.0 11 | pandas>=0.12.0 12 | python-dateutil>=1.4,<2 13 | protobuf>=2.5.0 14 | python-gflags>=2.0 15 | pyyaml>=3.10 16 | Pillow>=2.3.0 17 | six>=1.1.0 -------------------------------------------------------------------------------- /caffe3d/scripts/build_docs.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # Build documentation for display in web browser. 3 | 4 | PORT=${1:-4000} 5 | 6 | echo "usage: build_docs.sh [port]" 7 | 8 | # Find the docs dir, no matter where the script is called 9 | ROOT_DIR="$( cd "$(dirname "$0")"/.. ; pwd -P )" 10 | cd $ROOT_DIR 11 | 12 | # Gather docs. 13 | scripts/gather_examples.sh 14 | 15 | # Generate developer docs. 16 | make docs 17 | 18 | # Display docs using web server. 19 | cd docs 20 | jekyll serve -w -s . -d _site --port=$PORT 21 | -------------------------------------------------------------------------------- /caffe3d/scripts/copy_notebook.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | """ 3 | Takes as arguments: 4 | 1. the path to a JSON file (such as an IPython notebook). 5 | 2. the path to output file 6 | 7 | If 'metadata' dict in the JSON file contains 'include_in_docs': true, 8 | then copies the file to output file, appending the 'metadata' property 9 | as YAML front-matter, adding the field 'category' with value 'notebook'. 10 | """ 11 | import os 12 | import sys 13 | import json 14 | 15 | filename = sys.argv[1] 16 | output_filename = sys.argv[2] 17 | content = json.load(open(filename)) 18 | 19 | if 'include_in_docs' in content['metadata'] and content['metadata']['include_in_docs']: 20 | yaml_frontmatter = ['---'] 21 | for key, val in content['metadata'].iteritems(): 22 | if key == 'example_name': 23 | key = 'title' 24 | if val == '': 25 | val = os.path.basename(filename) 26 | yaml_frontmatter.append('{}: {}'.format(key, val)) 27 | yaml_frontmatter += ['category: notebook'] 28 | yaml_frontmatter += ['original_path: ' + filename] 29 | 30 | with open(output_filename, 'w') as fo: 31 | fo.write('\n'.join(yaml_frontmatter + ['---']) + '\n') 32 | fo.write(open(filename).read()) 33 | -------------------------------------------------------------------------------- /caffe3d/scripts/download_model_from_gist.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | 3 | GIST=$1 4 | DIRNAME=${2:-./models} 5 | 6 | if [ -z $GIST ]; then 7 | echo "usage: download_model_from_gist.sh " 8 | exit 9 | fi 10 | 11 | GIST_DIR=$(echo $GIST | tr '/' '-') 12 | MODEL_DIR="$DIRNAME/$GIST_DIR" 13 | 14 | if [ -d $MODEL_DIR ]; then 15 | echo "$MODEL_DIR already exists! Please make sure you're not overwriting anything important!" 16 | exit 17 | fi 18 | 19 | echo "Downloading Caffe model info to $MODEL_DIR ..." 20 | mkdir -p $MODEL_DIR 21 | wget https://gist.github.com/$GIST/download -O $MODEL_DIR/gist.zip 22 | unzip -j $MODEL_DIR/gist.zip -d $MODEL_DIR 23 | rm $MODEL_DIR/gist.zip 24 | echo "Done" 25 | -------------------------------------------------------------------------------- /caffe3d/scripts/gather_examples.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # Assemble documentation for the project into one directory via symbolic links. 3 | 4 | # Find the docs dir, no matter where the script is called 5 | ROOT_DIR="$( cd "$(dirname "$0")"/.. ; pwd -P )" 6 | cd $ROOT_DIR 7 | 8 | # Gather docs from examples/**/readme.md 9 | GATHERED_DIR=docs/gathered 10 | rm -r $GATHERED_DIR 11 | mkdir $GATHERED_DIR 12 | for README_FILENAME in $(find examples -iname "readme.md"); do 13 | # Only use file if it is to be included in docs. 14 | if grep -Fxq "include_in_docs: true" $README_FILENAME; then 15 | # Make link to readme.md in docs/gathered/. 16 | # Since everything is called readme.md, rename it by its dirname. 17 | README_DIRNAME=`dirname $README_FILENAME` 18 | DOCS_FILENAME=$GATHERED_DIR/$README_DIRNAME.md 19 | mkdir -p `dirname $DOCS_FILENAME` 20 | ln -s $ROOT_DIR/$README_FILENAME $DOCS_FILENAME 21 | fi 22 | done 23 | 24 | # Gather docs from examples/*.ipynb and add YAML front-matter. 25 | for NOTEBOOK_FILENAME in $(find examples -depth -iname "*.ipynb"); do 26 | DOCS_FILENAME=$GATHERED_DIR/$NOTEBOOK_FILENAME 27 | mkdir -p `dirname $DOCS_FILENAME` 28 | python scripts/copy_notebook.py $NOTEBOOK_FILENAME $DOCS_FILENAME 29 | done 30 | -------------------------------------------------------------------------------- /caffe3d/scripts/travis/build.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # build the project 3 | 4 | BASEDIR=$(dirname $0) 5 | source $BASEDIR/defaults.sh 6 | 7 | if ! $WITH_CMAKE ; then 8 | make --jobs $NUM_THREADS all test pycaffe warn 9 | else 10 | cd build 11 | make --jobs $NUM_THREADS all test.testbin 12 | fi 13 | make lint 14 | -------------------------------------------------------------------------------- /caffe3d/scripts/travis/configure-cmake.sh: -------------------------------------------------------------------------------- 1 | # CMake configuration 2 | 3 | mkdir -p build 4 | cd build 5 | 6 | ARGS="-DCMAKE_BUILD_TYPE=Release -DBLAS=Open" 7 | 8 | if $WITH_PYTHON3 ; then 9 | ARGS="$ARGS -Dpython_version=3" 10 | fi 11 | 12 | if $WITH_IO ; then 13 | ARGS="$ARGS -DUSE_OPENCV=On -DUSE_LMDB=On -DUSE_LEVELDB=On" 14 | else 15 | ARGS="$ARGS -DUSE_OPENCV=Off -DUSE_LMDB=Off -DUSE_LEVELDB=Off" 16 | fi 17 | 18 | if $WITH_CUDA ; then 19 | # Only build SM50 20 | ARGS="$ARGS -DCPU_ONLY=Off -DCUDA_ARCH_NAME=Manual -DCUDA_ARCH_BIN=\"50\" -DCUDA_ARCH_PTX=\"\"" 21 | else 22 | ARGS="$ARGS -DCPU_ONLY=On" 23 | fi 24 | 25 | if $WITH_CUDNN ; then 26 | ARGS="$ARGS -DUSE_CUDNN=On" 27 | else 28 | ARGS="$ARGS -DUSE_CUDNN=Off" 29 | fi 30 | 31 | cmake .. $ARGS 32 | 33 | -------------------------------------------------------------------------------- /caffe3d/scripts/travis/configure-make.sh: -------------------------------------------------------------------------------- 1 | # raw Makefile configuration 2 | 3 | LINE () { 4 | echo "$@" >> Makefile.config 5 | } 6 | 7 | cp Makefile.config.example Makefile.config 8 | 9 | LINE "BLAS := open" 10 | LINE "WITH_PYTHON_LAYER := 1" 11 | 12 | if $WITH_PYTHON3 ; then 13 | # TODO(lukeyeager) this path is currently disabled because of test errors like: 14 | # ImportError: dynamic module does not define init function (PyInit__caffe) 15 | LINE "PYTHON_LIBRARIES := python3.4m boost_python-py34" 16 | LINE "PYTHON_INCLUDE := /usr/include/python3.4 /usr/lib/python3/dist-packages/numpy/core/include" 17 | LINE "INCLUDE_DIRS := \$(INCLUDE_DIRS) \$(PYTHON_INCLUDE)" 18 | fi 19 | 20 | if ! $WITH_IO ; then 21 | LINE "USE_OPENCV := 0" 22 | LINE "USE_LEVELDB := 0" 23 | LINE "USE_LMDB := 0" 24 | fi 25 | 26 | if $WITH_CUDA ; then 27 | # Only build SM50 28 | LINE "CUDA_ARCH := -gencode arch=compute_50,code=sm_50" 29 | else 30 | LINE "CPU_ONLY := 1" 31 | fi 32 | 33 | if $WITH_CUDNN ; then 34 | LINE "USE_CUDNN := 1" 35 | fi 36 | 37 | -------------------------------------------------------------------------------- /caffe3d/scripts/travis/configure.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # configure the project 3 | 4 | BASEDIR=$(dirname $0) 5 | source $BASEDIR/defaults.sh 6 | 7 | if ! $WITH_CMAKE ; then 8 | source $BASEDIR/configure-make.sh 9 | else 10 | source $BASEDIR/configure-cmake.sh 11 | fi 12 | -------------------------------------------------------------------------------- /caffe3d/scripts/travis/defaults.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # set default environment variables 3 | 4 | set -e 5 | 6 | WITH_CMAKE=${WITH_CMAKE:-false} 7 | WITH_PYTHON3=${WITH_PYTHON3:-false} 8 | WITH_IO=${WITH_IO:-true} 9 | WITH_CUDA=${WITH_CUDA:-false} 10 | WITH_CUDNN=${WITH_CUDNN:-false} 11 | -------------------------------------------------------------------------------- /caffe3d/scripts/travis/install-python-deps.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # install extra Python dependencies 3 | # (must come after setup-venv) 4 | 5 | BASEDIR=$(dirname $0) 6 | source $BASEDIR/defaults.sh 7 | 8 | if ! $WITH_PYTHON3 ; then 9 | # Python2 10 | : 11 | else 12 | # Python3 13 | pip install --pre protobuf==3.0.0b3 14 | fi 15 | -------------------------------------------------------------------------------- /caffe3d/scripts/travis/setup-venv.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # setup a Python virtualenv 3 | # (must come after install-deps) 4 | 5 | BASEDIR=$(dirname $0) 6 | source $BASEDIR/defaults.sh 7 | 8 | VENV_DIR=${1:-~/venv} 9 | 10 | # setup our own virtualenv 11 | if $WITH_PYTHON3; then 12 | PYTHON_EXE='/usr/bin/python3' 13 | else 14 | PYTHON_EXE='/usr/bin/python2' 15 | fi 16 | 17 | # use --system-site-packages so that Python will use deb packages 18 | virtualenv $VENV_DIR -p $PYTHON_EXE --system-site-packages 19 | -------------------------------------------------------------------------------- /caffe3d/scripts/travis/test.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # test the project 3 | 4 | BASEDIR=$(dirname $0) 5 | source $BASEDIR/defaults.sh 6 | 7 | if $WITH_CUDA ; then 8 | echo "Skipping tests for CUDA build" 9 | exit 0 10 | fi 11 | 12 | if ! $WITH_CMAKE ; then 13 | make runtest 14 | make pytest 15 | else 16 | cd build 17 | make runtest 18 | make pytest 19 | fi 20 | -------------------------------------------------------------------------------- /caffe3d/scripts/upload_model_to_gist.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | # Check for valid directory 4 | DIRNAME=$1 5 | if [ ! -f $DIRNAME/readme.md ]; then 6 | echo "usage: upload_model_to_gist.sh " 7 | echo " /readme.md must exist" 8 | fi 9 | cd $DIRNAME 10 | FILES=`find . -maxdepth 1 -type f ! -name "*.caffemodel*" | xargs echo` 11 | 12 | # Check for gist tool. 13 | gist -v >/dev/null 2>&1 || { echo >&2 "I require 'gist' but it's not installed. Do 'gem install gist'."; exit 1; } 14 | 15 | NAME=`sed -n 's/^name:[[:space:]]*//p' readme.md` 16 | if [ -z "$NAME" ]; then 17 | echo " /readme.md must contain name field in the front-matter." 18 | fi 19 | 20 | GIST=`sed -n 's/^gist_id:[[:space:]]*//p' readme.md` 21 | if [ -z "$GIST" ]; then 22 | echo "Uploading new Gist" 23 | gist -p -d "$NAME" $FILES 24 | else 25 | echo "Updating existing Gist, id $GIST" 26 | gist -u $GIST -d "$NAME" $FILES 27 | fi 28 | 29 | RESULT=$? 30 | if [ $RESULT -eq 0 ]; then 31 | echo "You've uploaded your model!" 32 | echo "Don't forget to add the gist_id field to your /readme.md now!" 33 | echo "Run the command again after you do that, to make sure the Gist id propagates." 34 | echo "" 35 | echo "And do share your model over at https://github.com/BVLC/caffe/wiki/Model-Zoo" 36 | else 37 | echo "Something went wrong!" 38 | fi 39 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | # generate protobuf sources 2 | file(GLOB proto_files proto/*.proto) 3 | caffe_protobuf_generate_cpp_py(${proto_gen_folder} proto_srcs proto_hdrs proto_python ${proto_files}) 4 | 5 | # include python files either to force generation 6 | add_library(proto STATIC ${proto_hdrs} ${proto_srcs} ${proto_python}) 7 | set(Caffe_LINKER_LIBS proto ${Caffe_LINKER_LIBS}) # note, crucial to prepend! 8 | caffe_default_properties(proto) 9 | 10 | # --[ Caffe library 11 | 12 | # creates 'test_srcs', 'srcs', 'test_cuda', 'cuda' lists 13 | caffe_pickup_caffe_sources(${PROJECT_SOURCE_DIR}) 14 | 15 | if(HAVE_CUDA) 16 | caffe_cuda_compile(cuda_objs ${cuda}) 17 | list(APPEND srcs ${cuda_objs} ${cuda}) 18 | endif() 19 | 20 | add_library(caffe ${srcs}) 21 | target_link_libraries(caffe proto ${Caffe_LINKER_LIBS}) 22 | caffe_default_properties(caffe) 23 | set_target_properties(caffe PROPERTIES 24 | VERSION ${CAFFE_TARGET_VERSION} 25 | SOVERSION ${CAFFE_TARGET_SOVERSION} 26 | ) 27 | 28 | # ---[ Tests 29 | add_subdirectory(test) 30 | 31 | # ---[ Install 32 | install(DIRECTORY ${Caffe_INCLUDE_DIR}/caffe DESTINATION include) 33 | install(FILES ${proto_hdrs} DESTINATION include/caffe/proto) 34 | install(TARGETS caffe proto EXPORT CaffeTargets DESTINATION lib) 35 | 36 | file(WRITE ${PROJECT_BINARY_DIR}/__init__.py) 37 | list(APPEND proto_python ${PROJECT_BINARY_DIR}/__init__.py) 38 | install(PROGRAMS ${proto_python} DESTINATION python/caffe/proto) 39 | 40 | 41 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/layer.cpp: -------------------------------------------------------------------------------- 1 | #include 2 | #include "caffe/layer.hpp" 3 | 4 | namespace caffe { 5 | 6 | template 7 | void Layer::InitMutex() { 8 | forward_mutex_.reset(new boost::mutex()); 9 | } 10 | 11 | template 12 | void Layer::Lock() { 13 | if (IsShared()) { 14 | forward_mutex_->lock(); 15 | } 16 | } 17 | 18 | template 19 | void Layer::Unlock() { 20 | if (IsShared()) { 21 | forward_mutex_->unlock(); 22 | } 23 | } 24 | 25 | INSTANTIATE_CLASS(Layer); 26 | 27 | } // namespace caffe 28 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/layers/absval_layer.cu: -------------------------------------------------------------------------------- 1 | #include 2 | 3 | #include "caffe/layers/absval_layer.hpp" 4 | #include "caffe/util/math_functions.hpp" 5 | 6 | namespace caffe { 7 | 8 | template 9 | void AbsValLayer::Forward_gpu( 10 | const vector*>& bottom, const vector*>& top) { 11 | const int count = top[0]->count(); 12 | Dtype* top_data = top[0]->mutable_gpu_data(); 13 | caffe_gpu_abs(count, bottom[0]->gpu_data(), top_data); 14 | } 15 | 16 | template 17 | void AbsValLayer::Backward_gpu(const vector*>& top, 18 | const vector& propagate_down, const vector*>& bottom) { 19 | const int count = top[0]->count(); 20 | const Dtype* top_diff = top[0]->gpu_diff(); 21 | if (propagate_down[0]) { 22 | const Dtype* bottom_data = bottom[0]->gpu_data(); 23 | Dtype* bottom_diff = bottom[0]->mutable_gpu_diff(); 24 | caffe_gpu_sign(count, bottom_data, bottom_diff); 25 | caffe_gpu_mul(count, bottom_diff, top_diff, bottom_diff); 26 | } 27 | } 28 | 29 | INSTANTIATE_LAYER_GPU_FUNCS(AbsValLayer); 30 | 31 | 32 | } // namespace caffe 33 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/layers/base_data_layer.cu: -------------------------------------------------------------------------------- 1 | #include 2 | 3 | #include "caffe/layers/base_data_layer.hpp" 4 | 5 | namespace caffe { 6 | 7 | template 8 | void BasePrefetchingDataLayer::Forward_gpu( 9 | const vector*>& bottom, const vector*>& top) { 10 | Batch* batch = prefetch_full_.pop("Data layer prefetch queue empty"); 11 | // Reshape to loaded data. 12 | top[0]->ReshapeLike(batch->data_); 13 | // Copy the data 14 | caffe_copy(batch->data_.count(), batch->data_.gpu_data(), 15 | top[0]->mutable_gpu_data()); 16 | if (this->output_labels_) { 17 | // Reshape to loaded labels. 18 | top[1]->ReshapeLike(batch->label_); 19 | // Copy the labels. 20 | caffe_copy(batch->label_.count(), batch->label_.gpu_data(), 21 | top[1]->mutable_gpu_data()); 22 | } 23 | // Ensure the copy is synchronous wrt the host, so that the next batch isn't 24 | // copied in meanwhile. 25 | CUDA_CHECK(cudaStreamSynchronize(cudaStreamDefault)); 26 | prefetch_free_.push(batch); 27 | } 28 | 29 | INSTANTIATE_LAYER_GPU_FORWARD(BasePrefetchingDataLayer); 30 | 31 | } // namespace caffe 32 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/layers/cudnn_pooling_layer.cu: -------------------------------------------------------------------------------- 1 | #ifdef USE_CUDNN 2 | #include 3 | 4 | #include "caffe/layers/cudnn_pooling_layer.hpp" 5 | 6 | namespace caffe { 7 | 8 | template 9 | void CuDNNPoolingLayer::Forward_gpu(const vector*>& bottom, 10 | const vector*>& top) { 11 | const Dtype* bottom_data = bottom[0]->gpu_data(); 12 | Dtype* top_data = top[0]->mutable_gpu_data(); 13 | CUDNN_CHECK(cudnnPoolingForward(handle_, pooling_desc_, 14 | cudnn::dataType::one, 15 | bottom_desc_, bottom_data, 16 | cudnn::dataType::zero, 17 | top_desc_, top_data)); 18 | } 19 | 20 | template 21 | void CuDNNPoolingLayer::Backward_gpu(const vector*>& top, 22 | const vector& propagate_down, const vector*>& bottom) { 23 | if (!propagate_down[0]) { 24 | return; 25 | } 26 | const Dtype* top_diff = top[0]->gpu_diff(); 27 | const Dtype* top_data = top[0]->gpu_data(); 28 | const Dtype* bottom_data = bottom[0]->gpu_data(); 29 | Dtype* bottom_diff = bottom[0]->mutable_gpu_diff(); 30 | CUDNN_CHECK(cudnnPoolingBackward(handle_, pooling_desc_, 31 | cudnn::dataType::one, 32 | top_desc_, top_data, top_desc_, top_diff, 33 | bottom_desc_, bottom_data, 34 | cudnn::dataType::zero, 35 | bottom_desc_, bottom_diff)); 36 | } 37 | 38 | INSTANTIATE_LAYER_GPU_FUNCS(CuDNNPoolingLayer); 39 | 40 | } // namespace caffe 41 | #endif 42 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/layers/cudnn_relu_layer.cpp: -------------------------------------------------------------------------------- 1 | #ifdef USE_CUDNN 2 | #include 3 | 4 | #include "caffe/layers/cudnn_relu_layer.hpp" 5 | 6 | namespace caffe { 7 | 8 | template 9 | void CuDNNReLULayer::LayerSetUp(const vector*>& bottom, 10 | const vector*>& top) { 11 | ReLULayer::LayerSetUp(bottom, top); 12 | // initialize cuDNN 13 | CUDNN_CHECK(cudnnCreate(&handle_)); 14 | cudnn::createTensorDesc(&bottom_desc_); 15 | cudnn::createTensorDesc(&top_desc_); 16 | cudnn::createActivationDescriptor(&activ_desc_, CUDNN_ACTIVATION_RELU); 17 | handles_setup_ = true; 18 | } 19 | 20 | template 21 | void CuDNNReLULayer::Reshape(const vector*>& bottom, 22 | const vector*>& top) { 23 | ReLULayer::Reshape(bottom, top); 24 | cudnn::setTensorNdDesc(&bottom_desc_, bottom[0]->shape()); 25 | cudnn::setTensorNdDesc(&top_desc_, bottom[0]->shape()); 26 | } 27 | 28 | template 29 | CuDNNReLULayer::~CuDNNReLULayer() { 30 | // Check that handles have been setup before destroying. 31 | if (!handles_setup_) { return; } 32 | 33 | cudnnDestroyTensorDescriptor(this->bottom_desc_); 34 | cudnnDestroyTensorDescriptor(this->top_desc_); 35 | cudnnDestroy(this->handle_); 36 | } 37 | 38 | INSTANTIATE_CLASS(CuDNNReLULayer); 39 | 40 | } // namespace caffe 41 | #endif 42 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/layers/cudnn_sigmoid_layer.cpp: -------------------------------------------------------------------------------- 1 | #ifdef USE_CUDNN 2 | #include 3 | 4 | #include "caffe/layers/cudnn_sigmoid_layer.hpp" 5 | 6 | namespace caffe { 7 | 8 | template 9 | void CuDNNSigmoidLayer::LayerSetUp(const vector*>& bottom, 10 | const vector*>& top) { 11 | SigmoidLayer::LayerSetUp(bottom, top); 12 | // initialize cuDNN 13 | CUDNN_CHECK(cudnnCreate(&handle_)); 14 | cudnn::createTensorDesc(&bottom_desc_); 15 | cudnn::createTensorDesc(&top_desc_); 16 | cudnn::createActivationDescriptor(&activ_desc_, 17 | CUDNN_ACTIVATION_SIGMOID); 18 | handles_setup_ = true; 19 | } 20 | 21 | template 22 | void CuDNNSigmoidLayer::Reshape(const vector*>& bottom, 23 | const vector*>& top) { 24 | SigmoidLayer::Reshape(bottom, top); 25 | cudnn::setTensorNdDesc(&bottom_desc_, bottom[0]->shape()); 26 | cudnn::setTensorNdDesc(&top_desc_, bottom[0]->shape()); 27 | } 28 | 29 | template 30 | CuDNNSigmoidLayer::~CuDNNSigmoidLayer() { 31 | // Check that handles have been setup before destroying. 32 | if (!handles_setup_) { return; } 33 | 34 | cudnnDestroyTensorDescriptor(this->bottom_desc_); 35 | cudnnDestroyTensorDescriptor(this->top_desc_); 36 | cudnnDestroy(this->handle_); 37 | } 38 | 39 | INSTANTIATE_CLASS(CuDNNSigmoidLayer); 40 | 41 | } // namespace caffe 42 | #endif 43 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/layers/cudnn_softmax_layer.cpp: -------------------------------------------------------------------------------- 1 | #ifdef USE_CUDNN 2 | #include 3 | 4 | #include "thrust/device_vector.h" 5 | 6 | #include "caffe/layers/cudnn_softmax_layer.hpp" 7 | 8 | namespace caffe { 9 | 10 | template 11 | void CuDNNSoftmaxLayer::LayerSetUp(const vector*>& bottom, 12 | const vector*>& top) { 13 | SoftmaxLayer::LayerSetUp(bottom, top); 14 | // Initialize CUDNN. 15 | CUDNN_CHECK(cudnnCreate(&handle_)); 16 | cudnn::createTensor4dDesc(&bottom_desc_); 17 | cudnn::createTensor4dDesc(&top_desc_); 18 | handles_setup_ = true; 19 | } 20 | 21 | template 22 | void CuDNNSoftmaxLayer::Reshape(const vector*>& bottom, 23 | const vector*>& top) { 24 | SoftmaxLayer::Reshape(bottom, top); 25 | int N = this->outer_num_; 26 | int K = bottom[0]->shape(this->softmax_axis_); 27 | int H = this->inner_num_; 28 | int W = 1; 29 | cudnn::setTensor4dDesc(&bottom_desc_, N, K, H, W); 30 | cudnn::setTensor4dDesc(&top_desc_, N, K, H, W); 31 | } 32 | 33 | template 34 | CuDNNSoftmaxLayer::~CuDNNSoftmaxLayer() { 35 | // Check that handles have been setup before destroying. 36 | if (!handles_setup_) { return; } 37 | 38 | cudnnDestroyTensorDescriptor(bottom_desc_); 39 | cudnnDestroyTensorDescriptor(top_desc_); 40 | cudnnDestroy(handle_); 41 | } 42 | 43 | INSTANTIATE_CLASS(CuDNNSoftmaxLayer); 44 | 45 | } // namespace caffe 46 | #endif 47 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/layers/cudnn_tanh_layer.cpp: -------------------------------------------------------------------------------- 1 | #ifdef USE_CUDNN 2 | #include 3 | 4 | #include "caffe/layers/cudnn_tanh_layer.hpp" 5 | 6 | namespace caffe { 7 | 8 | template 9 | void CuDNNTanHLayer::LayerSetUp(const vector*>& bottom, 10 | const vector*>& top) { 11 | TanHLayer::LayerSetUp(bottom, top); 12 | // initialize cuDNN 13 | CUDNN_CHECK(cudnnCreate(&handle_)); 14 | cudnn::createTensorDesc(&bottom_desc_); 15 | cudnn::createTensorDesc(&top_desc_); 16 | cudnn::createActivationDescriptor(&activ_desc_, CUDNN_ACTIVATION_TANH); 17 | handles_setup_ = true; 18 | } 19 | 20 | template 21 | void CuDNNTanHLayer::Reshape(const vector*>& bottom, 22 | const vector*>& top) { 23 | TanHLayer::Reshape(bottom, top); 24 | cudnn::setTensorNdDesc(&bottom_desc_, bottom[0]->shape()); 25 | cudnn::setTensorNdDesc(&top_desc_, bottom[0]->shape()); 26 | } 27 | 28 | template 29 | CuDNNTanHLayer::~CuDNNTanHLayer() { 30 | // Check that handles have been setup before destroying. 31 | if (!handles_setup_) { return; } 32 | 33 | cudnnDestroyTensorDescriptor(this->bottom_desc_); 34 | cudnnDestroyTensorDescriptor(this->top_desc_); 35 | cudnnDestroy(this->handle_); 36 | } 37 | 38 | INSTANTIATE_CLASS(CuDNNTanHLayer); 39 | 40 | } // namespace caffe 41 | #endif 42 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/layers/exp_layer.cu: -------------------------------------------------------------------------------- 1 | #include 2 | 3 | #include "caffe/layers/exp_layer.hpp" 4 | #include "caffe/util/math_functions.hpp" 5 | 6 | namespace caffe { 7 | 8 | template 9 | void ExpLayer::Forward_gpu(const vector*>& bottom, 10 | const vector*>& top) { 11 | const int count = bottom[0]->count(); 12 | const Dtype* bottom_data = bottom[0]->gpu_data(); 13 | Dtype* top_data = top[0]->mutable_gpu_data(); 14 | if (inner_scale_ == Dtype(1)) { 15 | caffe_gpu_exp(count, bottom_data, top_data); 16 | } else { 17 | caffe_gpu_scale(count, inner_scale_, bottom_data, top_data); 18 | caffe_gpu_exp(count, top_data, top_data); 19 | } 20 | if (outer_scale_ != Dtype(1)) { 21 | caffe_gpu_scal(count, outer_scale_, top_data); 22 | } 23 | } 24 | 25 | template 26 | void ExpLayer::Backward_gpu(const vector*>& top, 27 | const vector& propagate_down, const vector*>& bottom) { 28 | if (!propagate_down[0]) { return; } 29 | const int count = bottom[0]->count(); 30 | const Dtype* top_data = top[0]->gpu_data(); 31 | const Dtype* top_diff = top[0]->gpu_diff(); 32 | Dtype* bottom_diff = bottom[0]->mutable_gpu_diff(); 33 | caffe_gpu_mul(count, top_data, top_diff, bottom_diff); 34 | if (inner_scale_ != Dtype(1)) { 35 | caffe_gpu_scal(count, inner_scale_, bottom_diff); 36 | } 37 | } 38 | 39 | INSTANTIATE_LAYER_GPU_FUNCS(ExpLayer); 40 | 41 | 42 | } // namespace caffe 43 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/layers/hdf5_output_layer.cu: -------------------------------------------------------------------------------- 1 | #include 2 | 3 | #include "hdf5.h" 4 | #include "hdf5_hl.h" 5 | 6 | #include "caffe/layers/hdf5_output_layer.hpp" 7 | 8 | namespace caffe { 9 | 10 | template 11 | void HDF5OutputLayer::Forward_gpu(const vector*>& bottom, 12 | const vector*>& top) { 13 | CHECK_GE(bottom.size(), 2); 14 | CHECK_EQ(bottom[0]->num(), bottom[1]->num()); 15 | data_blob_.Reshape(bottom[0]->num(), bottom[0]->channels(), 16 | bottom[0]->height(), bottom[0]->width()); 17 | label_blob_.Reshape(bottom[1]->num(), bottom[1]->channels(), 18 | bottom[1]->height(), bottom[1]->width()); 19 | const int data_datum_dim = bottom[0]->count() / bottom[0]->num(); 20 | const int label_datum_dim = bottom[1]->count() / bottom[1]->num(); 21 | 22 | for (int i = 0; i < bottom[0]->num(); ++i) { 23 | caffe_copy(data_datum_dim, &bottom[0]->gpu_data()[i * data_datum_dim], 24 | &data_blob_.mutable_cpu_data()[i * data_datum_dim]); 25 | caffe_copy(label_datum_dim, &bottom[1]->gpu_data()[i * label_datum_dim], 26 | &label_blob_.mutable_cpu_data()[i * label_datum_dim]); 27 | } 28 | SaveBlobs(); 29 | } 30 | 31 | template 32 | void HDF5OutputLayer::Backward_gpu(const vector*>& top, 33 | const vector& propagate_down, const vector*>& bottom) { 34 | return; 35 | } 36 | 37 | INSTANTIATE_LAYER_GPU_FUNCS(HDF5OutputLayer); 38 | 39 | } // namespace caffe 40 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/layers/input_layer.cpp: -------------------------------------------------------------------------------- 1 | #include 2 | 3 | #include "caffe/layers/input_layer.hpp" 4 | 5 | namespace caffe { 6 | 7 | template 8 | void InputLayer::LayerSetUp(const vector*>& bottom, 9 | const vector*>& top) { 10 | const int num_top = top.size(); 11 | const InputParameter& param = this->layer_param_.input_param(); 12 | const int num_shape = param.shape_size(); 13 | CHECK(num_shape == 0 || num_shape == 1 || num_shape == num_top) 14 | << "Must specify 'shape' once, once per top blob, or not at all: " 15 | << num_top << " tops vs. " << num_shape << " shapes."; 16 | if (num_shape > 0) { 17 | for (int i = 0; i < num_top; ++i) { 18 | const int shape_index = (param.shape_size() == 1) ? 0 : i; 19 | top[i]->Reshape(param.shape(shape_index)); 20 | } 21 | } 22 | } 23 | 24 | INSTANTIATE_CLASS(InputLayer); 25 | REGISTER_LAYER_CLASS(Input); 26 | 27 | } // namespace caffe 28 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/layers/loss_layer.cpp: -------------------------------------------------------------------------------- 1 | #include 2 | 3 | #include "caffe/layers/loss_layer.hpp" 4 | 5 | namespace caffe { 6 | 7 | template 8 | void LossLayer::LayerSetUp( 9 | const vector*>& bottom, const vector*>& top) { 10 | // LossLayers have a non-zero (1) loss by default. 11 | if (this->layer_param_.loss_weight_size() == 0) { 12 | this->layer_param_.add_loss_weight(Dtype(1)); 13 | } 14 | } 15 | 16 | template 17 | void LossLayer::Reshape( 18 | const vector*>& bottom, const vector*>& top) { 19 | CHECK_EQ(bottom[0]->shape(0), bottom[1]->shape(0)) 20 | << "The data and label should have the same first dimension."; 21 | vector loss_shape(0); // Loss layers output a scalar; 0 axes. 22 | top[0]->Reshape(loss_shape); 23 | } 24 | 25 | INSTANTIATE_CLASS(LossLayer); 26 | 27 | } // namespace caffe 28 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/layers/neuron_layer.cpp: -------------------------------------------------------------------------------- 1 | #include 2 | 3 | #include "caffe/layers/neuron_layer.hpp" 4 | 5 | namespace caffe { 6 | 7 | template 8 | void NeuronLayer::Reshape(const vector*>& bottom, 9 | const vector*>& top) { 10 | top[0]->ReshapeLike(*bottom[0]); 11 | } 12 | 13 | INSTANTIATE_CLASS(NeuronLayer); 14 | 15 | } // namespace caffe 16 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/layers/parameter_layer.cpp: -------------------------------------------------------------------------------- 1 | #include "caffe/layers/parameter_layer.hpp" 2 | 3 | namespace caffe { 4 | 5 | INSTANTIATE_CLASS(ParameterLayer); 6 | REGISTER_LAYER_CLASS(Parameter); 7 | 8 | } // namespace caffe 9 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/layers/sigmoid_layer.cpp: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | 4 | #include "caffe/layers/sigmoid_layer.hpp" 5 | 6 | namespace caffe { 7 | 8 | template 9 | inline Dtype sigmoid(Dtype x) { 10 | return 1. / (1. + exp(-x)); 11 | } 12 | 13 | template 14 | void SigmoidLayer::Forward_cpu(const vector*>& bottom, 15 | const vector*>& top) { 16 | const Dtype* bottom_data = bottom[0]->cpu_data(); 17 | Dtype* top_data = top[0]->mutable_cpu_data(); 18 | const int count = bottom[0]->count(); 19 | for (int i = 0; i < count; ++i) { 20 | top_data[i] = sigmoid(bottom_data[i]); 21 | } 22 | } 23 | 24 | template 25 | void SigmoidLayer::Backward_cpu(const vector*>& top, 26 | const vector& propagate_down, 27 | const vector*>& bottom) { 28 | if (propagate_down[0]) { 29 | const Dtype* top_data = top[0]->cpu_data(); 30 | const Dtype* top_diff = top[0]->cpu_diff(); 31 | Dtype* bottom_diff = bottom[0]->mutable_cpu_diff(); 32 | const int count = bottom[0]->count(); 33 | for (int i = 0; i < count; ++i) { 34 | const Dtype sigmoid_x = top_data[i]; 35 | bottom_diff[i] = top_diff[i] * sigmoid_x * (1. - sigmoid_x); 36 | } 37 | } 38 | } 39 | 40 | #ifdef CPU_ONLY 41 | STUB_GPU(SigmoidLayer); 42 | #endif 43 | 44 | INSTANTIATE_CLASS(SigmoidLayer); 45 | 46 | 47 | } // namespace caffe 48 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/layers/silence_layer.cpp: -------------------------------------------------------------------------------- 1 | #include 2 | 3 | #include "caffe/layers/silence_layer.hpp" 4 | #include "caffe/util/math_functions.hpp" 5 | 6 | namespace caffe { 7 | 8 | template 9 | void SilenceLayer::Backward_cpu(const vector*>& top, 10 | const vector& propagate_down, const vector*>& bottom) { 11 | for (int i = 0; i < bottom.size(); ++i) { 12 | if (propagate_down[i]) { 13 | caffe_set(bottom[i]->count(), Dtype(0), 14 | bottom[i]->mutable_cpu_diff()); 15 | } 16 | } 17 | } 18 | 19 | #ifdef CPU_ONLY 20 | STUB_GPU(SilenceLayer); 21 | #endif 22 | 23 | INSTANTIATE_CLASS(SilenceLayer); 24 | REGISTER_LAYER_CLASS(Silence); 25 | 26 | } // namespace caffe 27 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/layers/silence_layer.cu: -------------------------------------------------------------------------------- 1 | #include 2 | 3 | #include "caffe/layers/silence_layer.hpp" 4 | #include "caffe/util/math_functions.hpp" 5 | 6 | namespace caffe { 7 | 8 | template 9 | void SilenceLayer::Forward_gpu(const vector*>& bottom, 10 | const vector*>& top) { 11 | // Do nothing. 12 | } 13 | 14 | template 15 | void SilenceLayer::Backward_gpu(const vector*>& top, 16 | const vector& propagate_down, const vector*>& bottom) { 17 | for (int i = 0; i < bottom.size(); ++i) { 18 | if (propagate_down[i]) { 19 | caffe_gpu_set(bottom[i]->count(), Dtype(0), 20 | bottom[i]->mutable_gpu_diff()); 21 | } 22 | } 23 | } 24 | 25 | INSTANTIATE_LAYER_GPU_FUNCS(SilenceLayer); 26 | 27 | } // namespace caffe 28 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/layers/similarity_layer.cpp: -------------------------------------------------------------------------------- 1 | #include "caffe/layers/similarity_layer.hpp" 2 | 3 | namespace caffe { 4 | 5 | template 6 | void SimilarityLayer::Reshape( 7 | const vector*>& bottom, const vector*>& top) { 8 | CHECK_EQ(bottom[0]->num(), bottom[1]->num()) 9 | << "The data and label should have the same number."; 10 | top[0]->Reshape(bottom[0]->num(), 1, 1, 1); 11 | } 12 | 13 | INSTANTIATE_CLASS(SimilarityLayer); 14 | 15 | } // namespace caffe 16 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/layers/split_layer.cu: -------------------------------------------------------------------------------- 1 | #include 2 | 3 | #include "caffe/layers/split_layer.hpp" 4 | #include "caffe/util/math_functions.hpp" 5 | 6 | namespace caffe { 7 | 8 | template 9 | void SplitLayer::Forward_gpu(const vector*>& bottom, 10 | const vector*>& top) { 11 | for (int i = 0; i < top.size(); ++i) { 12 | top[i]->ShareData(*bottom[0]); 13 | } 14 | } 15 | 16 | template 17 | void SplitLayer::Backward_gpu(const vector*>& top, 18 | const vector& propagate_down, const vector*>& bottom) { 19 | if (!propagate_down[0]) { return; } 20 | if (top.size() == 1) { 21 | caffe_copy(count_, top[0]->gpu_diff(), bottom[0]->mutable_gpu_diff()); 22 | return; 23 | } 24 | caffe_gpu_add(count_, top[0]->gpu_diff(), top[1]->gpu_diff(), 25 | bottom[0]->mutable_gpu_diff()); 26 | // Add remaining top blob diffs. 27 | for (int i = 2; i < top.size(); ++i) { 28 | const Dtype* top_diff = top[i]->gpu_diff(); 29 | Dtype* bottom_diff = bottom[0]->mutable_gpu_diff(); 30 | caffe_gpu_axpy(count_, Dtype(1.), top_diff, bottom_diff); 31 | } 32 | } 33 | 34 | 35 | INSTANTIATE_LAYER_GPU_FUNCS(SplitLayer); 36 | 37 | } // namespace caffe 38 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/layers/tanh_layer.cpp: -------------------------------------------------------------------------------- 1 | // TanH neuron activation function layer. 2 | // Adapted from ReLU layer code written by Yangqing Jia 3 | 4 | #include 5 | 6 | #include "caffe/layers/tanh_layer.hpp" 7 | 8 | namespace caffe { 9 | 10 | template 11 | void TanHLayer::Forward_cpu(const vector*>& bottom, 12 | const vector*>& top) { 13 | const Dtype* bottom_data = bottom[0]->cpu_data(); 14 | Dtype* top_data = top[0]->mutable_cpu_data(); 15 | const int count = bottom[0]->count(); 16 | for (int i = 0; i < count; ++i) { 17 | top_data[i] = tanh(bottom_data[i]); 18 | } 19 | } 20 | 21 | template 22 | void TanHLayer::Backward_cpu(const vector*>& top, 23 | const vector& propagate_down, 24 | const vector*>& bottom) { 25 | if (propagate_down[0]) { 26 | const Dtype* top_data = top[0]->cpu_data(); 27 | const Dtype* top_diff = top[0]->cpu_diff(); 28 | Dtype* bottom_diff = bottom[0]->mutable_cpu_diff(); 29 | const int count = bottom[0]->count(); 30 | Dtype tanhx; 31 | for (int i = 0; i < count; ++i) { 32 | tanhx = top_data[i]; 33 | bottom_diff[i] = top_diff[i] * (1 - tanhx * tanhx); 34 | } 35 | } 36 | } 37 | 38 | #ifdef CPU_ONLY 39 | STUB_GPU(TanHLayer); 40 | #endif 41 | 42 | INSTANTIATE_CLASS(TanHLayer); 43 | 44 | } // namespace caffe 45 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/layers/threshold_layer.cpp: -------------------------------------------------------------------------------- 1 | #include 2 | 3 | #include "caffe/layers/threshold_layer.hpp" 4 | 5 | namespace caffe { 6 | 7 | template 8 | void ThresholdLayer::LayerSetUp(const vector*>& bottom, 9 | const vector*>& top) { 10 | NeuronLayer::LayerSetUp(bottom, top); 11 | threshold_ = this->layer_param_.threshold_param().threshold(); 12 | } 13 | 14 | template 15 | void ThresholdLayer::Forward_cpu(const vector*>& bottom, 16 | const vector*>& top) { 17 | const Dtype* bottom_data = bottom[0]->cpu_data(); 18 | Dtype* top_data = top[0]->mutable_cpu_data(); 19 | const int count = bottom[0]->count(); 20 | for (int i = 0; i < count; ++i) { 21 | top_data[i] = (bottom_data[i] > threshold_) ? Dtype(1) : Dtype(0); 22 | } 23 | } 24 | 25 | #ifdef CPU_ONLY 26 | STUB_GPU_FORWARD(ThresholdLayer, Forward); 27 | #endif 28 | 29 | INSTANTIATE_CLASS(ThresholdLayer); 30 | REGISTER_LAYER_CLASS(Threshold); 31 | 32 | } // namespace caffe 33 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/layers/threshold_layer.cu: -------------------------------------------------------------------------------- 1 | #include 2 | 3 | #include "caffe/layers/threshold_layer.hpp" 4 | 5 | namespace caffe { 6 | 7 | template 8 | __global__ void ThresholdForward(const int n, const Dtype threshold, 9 | const Dtype* in, Dtype* out) { 10 | CUDA_KERNEL_LOOP(index, n) { 11 | out[index] = in[index] > threshold ? 1 : 0; 12 | } 13 | } 14 | 15 | template 16 | void ThresholdLayer::Forward_gpu(const vector*>& bottom, 17 | const vector*>& top) { 18 | const Dtype* bottom_data = bottom[0]->gpu_data(); 19 | Dtype* top_data = top[0]->mutable_gpu_data(); 20 | const int count = bottom[0]->count(); 21 | // NOLINT_NEXT_LINE(whitespace/operators) 22 | ThresholdForward<<>>( 23 | count, threshold_, bottom_data, top_data); 24 | CUDA_POST_KERNEL_CHECK; 25 | } 26 | 27 | 28 | INSTANTIATE_LAYER_GPU_FORWARD(ThresholdLayer); 29 | 30 | 31 | } // namespace caffe 32 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/solvers/adadelta_solver.cu: -------------------------------------------------------------------------------- 1 | #include "caffe/util/math_functions.hpp" 2 | 3 | 4 | namespace caffe { 5 | 6 | template 7 | __global__ void AdaDeltaUpdate(int N, Dtype* g, Dtype* h, Dtype* h2, 8 | Dtype momentum, Dtype delta, Dtype local_rate) { 9 | CUDA_KERNEL_LOOP(i, N) { 10 | float gi = g[i]; 11 | float hi = h[i] = momentum * h[i] + (1-momentum) * gi * gi; 12 | gi = gi * sqrt((h2[i] + delta) / (hi + delta)); 13 | h2[i] = momentum * h2[i] + (1-momentum) * gi * gi; 14 | g[i] = local_rate * gi; 15 | } 16 | } 17 | template 18 | void adadelta_update_gpu(int N, Dtype* g, Dtype* h, Dtype* h2, Dtype momentum, 19 | Dtype delta, Dtype local_rate) { 20 | AdaDeltaUpdate // NOLINT_NEXT_LINE(whitespace/operators) 21 | <<>>( 22 | N, g, h, h2, momentum, delta, local_rate); 23 | CUDA_POST_KERNEL_CHECK; 24 | } 25 | template void adadelta_update_gpu(int , float*, float*, float*, 26 | float, float, float); 27 | template void adadelta_update_gpu(int, double*, double*, double*, 28 | double, double, double); 29 | 30 | } // namespace caffe 31 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/solvers/adagrad_solver.cu: -------------------------------------------------------------------------------- 1 | #include "caffe/util/math_functions.hpp" 2 | 3 | 4 | namespace caffe { 5 | 6 | template 7 | __global__ void AdaGradUpdate(int N, Dtype* g, Dtype* h, Dtype delta, 8 | Dtype local_rate) { 9 | CUDA_KERNEL_LOOP(i, N) { 10 | float gi = g[i]; 11 | float hi = h[i] = h[i] + gi*gi; 12 | g[i] = local_rate * gi / (sqrt(hi) + delta); 13 | } 14 | } 15 | template 16 | void adagrad_update_gpu(int N, Dtype* g, Dtype* h, Dtype delta, 17 | Dtype local_rate) { 18 | AdaGradUpdate // NOLINT_NEXT_LINE(whitespace/operators) 19 | <<>>( 20 | N, g, h, delta, local_rate); 21 | CUDA_POST_KERNEL_CHECK; 22 | } 23 | template void adagrad_update_gpu(int, float*, float*, float, float); 24 | template void adagrad_update_gpu(int, double*, double*, double, double); 25 | 26 | } // namespace caffe 27 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/solvers/adam_solver.cu: -------------------------------------------------------------------------------- 1 | #include "caffe/util/math_functions.hpp" 2 | 3 | 4 | namespace caffe { 5 | 6 | template 7 | __global__ void AdamUpdate(int N, Dtype* g, Dtype* m, Dtype* v, 8 | Dtype beta1, Dtype beta2, Dtype eps_hat, Dtype corrected_local_rate) { 9 | CUDA_KERNEL_LOOP(i, N) { 10 | float gi = g[i]; 11 | float mi = m[i] = m[i]*beta1 + gi*(1-beta1); 12 | float vi = v[i] = v[i]*beta2 + gi*gi*(1-beta2); 13 | g[i] = corrected_local_rate * mi / (sqrt(vi) + eps_hat); 14 | } 15 | } 16 | template 17 | void adam_update_gpu(int N, Dtype* g, Dtype* m, Dtype* v, Dtype beta1, 18 | Dtype beta2, Dtype eps_hat, Dtype corrected_local_rate) { 19 | AdamUpdate // NOLINT_NEXT_LINE(whitespace/operators) 20 | <<>>( 21 | N, g, m, v, beta1, beta2, eps_hat, corrected_local_rate); 22 | CUDA_POST_KERNEL_CHECK; 23 | } 24 | template void adam_update_gpu(int, float*, float*, float*, 25 | float, float, float, float); 26 | template void adam_update_gpu(int, double*, double*, double*, 27 | double, double, double, double); 28 | 29 | } // namespace caffe 30 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/solvers/nesterov_solver.cu: -------------------------------------------------------------------------------- 1 | #include "caffe/util/math_functions.hpp" 2 | 3 | 4 | namespace caffe { 5 | 6 | template 7 | __global__ void NesterovUpdate(int N, Dtype* g, Dtype* h, 8 | Dtype momentum, Dtype local_rate) { 9 | CUDA_KERNEL_LOOP(i, N) { 10 | float hi = h[i]; 11 | float hi_new = h[i] = momentum * hi + local_rate * g[i]; 12 | g[i] = (1+momentum) * hi_new - momentum * hi; 13 | } 14 | } 15 | template 16 | void nesterov_update_gpu(int N, Dtype* g, Dtype* h, Dtype momentum, 17 | Dtype local_rate) { 18 | NesterovUpdate // NOLINT_NEXT_LINE(whitespace/operators) 19 | <<>>( 20 | N, g, h, momentum, local_rate); 21 | CUDA_POST_KERNEL_CHECK; 22 | } 23 | template void nesterov_update_gpu(int, float*, float*, float, float); 24 | template void nesterov_update_gpu(int, double*, double*, double, 25 | double); 26 | 27 | } // namespace caffe 28 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/solvers/rmsprop_solver.cu: -------------------------------------------------------------------------------- 1 | #include "caffe/util/math_functions.hpp" 2 | 3 | 4 | namespace caffe { 5 | 6 | template 7 | __global__ void RMSPropUpdate(int N, Dtype* g, Dtype* h, 8 | Dtype rms_decay, Dtype delta, Dtype local_rate) { 9 | CUDA_KERNEL_LOOP(i, N) { 10 | float gi = g[i]; 11 | float hi = h[i] = rms_decay*h[i] + (1-rms_decay)*gi*gi; 12 | g[i] = local_rate * g[i] / (sqrt(hi) + delta); 13 | } 14 | } 15 | template 16 | void rmsprop_update_gpu(int N, Dtype* g, Dtype* h, Dtype rms_decay, 17 | Dtype delta, Dtype local_rate) { 18 | RMSPropUpdate // NOLINT_NEXT_LINE(whitespace/operators) 19 | <<>>( 20 | N, g, h, rms_decay, delta, local_rate); 21 | CUDA_POST_KERNEL_CHECK; 22 | } 23 | template void rmsprop_update_gpu(int, float*, float*, float, float, 24 | float); 25 | template void rmsprop_update_gpu(int, double*, double*, double, double, 26 | double); 27 | 28 | } // namespace caffe 29 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/solvers/sgd_solver.cu: -------------------------------------------------------------------------------- 1 | #include "caffe/util/math_functions.hpp" 2 | 3 | 4 | namespace caffe { 5 | 6 | template 7 | __global__ void SGDUpdate(int N, Dtype* g, Dtype* h, 8 | Dtype momentum, Dtype local_rate) { 9 | CUDA_KERNEL_LOOP(i, N) { 10 | g[i] = h[i] = momentum*h[i] + local_rate*g[i]; 11 | } 12 | } 13 | template 14 | void sgd_update_gpu(int N, Dtype* g, Dtype* h, Dtype momentum, 15 | Dtype local_rate) { 16 | SGDUpdate // NOLINT_NEXT_LINE(whitespace/operators) 17 | <<>>( 18 | N, g, h, momentum, local_rate); 19 | CUDA_POST_KERNEL_CHECK; 20 | } 21 | template void sgd_update_gpu(int, float*, float*, float, float); 22 | template void sgd_update_gpu(int, double*, double*, double, double); 23 | 24 | } // namespace caffe 25 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_caffe_main.cpp: -------------------------------------------------------------------------------- 1 | #include "caffe/caffe.hpp" 2 | #include "caffe/test/test_caffe_main.hpp" 3 | 4 | namespace caffe { 5 | #ifndef CPU_ONLY 6 | cudaDeviceProp CAFFE_TEST_CUDA_PROP; 7 | #endif 8 | } 9 | 10 | #ifndef CPU_ONLY 11 | using caffe::CAFFE_TEST_CUDA_PROP; 12 | #endif 13 | 14 | int main(int argc, char** argv) { 15 | ::testing::InitGoogleTest(&argc, argv); 16 | caffe::GlobalInit(&argc, &argv); 17 | #ifndef CPU_ONLY 18 | // Before starting testing, let's first print out a few cuda defice info. 19 | int device; 20 | cudaGetDeviceCount(&device); 21 | cout << "Cuda number of devices: " << device << endl; 22 | if (argc > 1) { 23 | // Use the given device 24 | device = atoi(argv[1]); 25 | cudaSetDevice(device); 26 | cout << "Setting to use device " << device << endl; 27 | } else if (CUDA_TEST_DEVICE >= 0) { 28 | // Use the device assigned in build configuration; but with a lower priority 29 | device = CUDA_TEST_DEVICE; 30 | } 31 | cudaGetDevice(&device); 32 | cout << "Current device id: " << device << endl; 33 | cudaGetDeviceProperties(&CAFFE_TEST_CUDA_PROP, device); 34 | cout << "Current device name: " << CAFFE_TEST_CUDA_PROP.name << endl; 35 | #endif 36 | // invoke the test. 37 | return RUN_ALL_TESTS(); 38 | } 39 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_data/UCF-101_Rowing_g16_c03.avi: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/src/caffe/test/test_data/UCF-101_Rowing_g16_c03.avi -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_data/sample_data.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/src/caffe/test/test_data/sample_data.h5 -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_data/sample_data_2_gzip.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/src/caffe/test/test_data/sample_data_2_gzip.h5 -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_data/sample_data_list.txt: -------------------------------------------------------------------------------- 1 | src/caffe/test/test_data/sample_data.h5 2 | src/caffe/test/test_data/sample_data_2_gzip.h5 3 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_data/solver_data.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/src/caffe/test/test_data/solver_data.h5 -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_data/solver_data_list.txt: -------------------------------------------------------------------------------- 1 | src/caffe/test/test_data/solver_data.h5 2 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0001.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0001.jpg -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0002.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0002.jpg -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0003.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0003.jpg -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0004.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0004.jpg -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0005.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0005.jpg -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0006.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0006.jpg -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0007.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0007.jpg -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0008.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0008.jpg -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0009.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0009.jpg -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0010.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0010.jpg -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0011.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0011.jpg -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0012.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0012.jpg -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0013.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0013.jpg -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0014.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0014.jpg -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0015.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0015.jpg -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0016.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/caffe3d/src/caffe/test/test_data/youtube_objects_dog_v0002_s006/image_0016.jpg -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_internal_thread.cpp: -------------------------------------------------------------------------------- 1 | #include "glog/logging.h" 2 | #include "gtest/gtest.h" 3 | 4 | #include "caffe/internal_thread.hpp" 5 | #include "caffe/util/math_functions.hpp" 6 | 7 | #include "caffe/test/test_caffe_main.hpp" 8 | 9 | namespace caffe { 10 | 11 | 12 | class InternalThreadTest : public ::testing::Test {}; 13 | 14 | TEST_F(InternalThreadTest, TestStartAndExit) { 15 | InternalThread thread; 16 | EXPECT_FALSE(thread.is_started()); 17 | thread.StartInternalThread(); 18 | EXPECT_TRUE(thread.is_started()); 19 | thread.StopInternalThread(); 20 | EXPECT_FALSE(thread.is_started()); 21 | } 22 | 23 | class TestThreadA : public InternalThread { 24 | void InternalThreadEntry() { 25 | EXPECT_EQ(4244559767, caffe_rng_rand()); 26 | } 27 | }; 28 | 29 | class TestThreadB : public InternalThread { 30 | void InternalThreadEntry() { 31 | EXPECT_EQ(1726478280, caffe_rng_rand()); 32 | } 33 | }; 34 | 35 | TEST_F(InternalThreadTest, TestRandomSeed) { 36 | TestThreadA t1; 37 | Caffe::set_random_seed(9658361); 38 | t1.StartInternalThread(); 39 | t1.StopInternalThread(); 40 | 41 | TestThreadA t2; 42 | Caffe::set_random_seed(9658361); 43 | t2.StartInternalThread(); 44 | t2.StopInternalThread(); 45 | 46 | TestThreadB t3; 47 | Caffe::set_random_seed(3435563); 48 | t3.StartInternalThread(); 49 | t3.StopInternalThread(); 50 | } 51 | 52 | } // namespace caffe 53 | 54 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/test/test_protobuf.cpp: -------------------------------------------------------------------------------- 1 | // This is simply a script that tries serializing protocol buffer in text 2 | // format. Nothing special here and no actual code is being tested. 3 | #include 4 | 5 | #include "google/protobuf/text_format.h" 6 | #include "gtest/gtest.h" 7 | 8 | #include "caffe/proto/caffe.pb.h" 9 | 10 | #include "caffe/test/test_caffe_main.hpp" 11 | 12 | namespace caffe { 13 | 14 | class ProtoTest : public ::testing::Test {}; 15 | 16 | TEST_F(ProtoTest, TestSerialization) { 17 | LayerParameter param; 18 | param.set_name("test"); 19 | param.set_type("Test"); 20 | std::cout << "Printing in binary format." << std::endl; 21 | std::cout << param.SerializeAsString() << std::endl; 22 | std::cout << "Printing in text format." << std::endl; 23 | std::string str; 24 | google::protobuf::TextFormat::PrintToString(param, &str); 25 | std::cout << str << std::endl; 26 | EXPECT_TRUE(true); 27 | } 28 | 29 | } // namespace caffe 30 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/util/cudnn.cpp: -------------------------------------------------------------------------------- 1 | #ifdef USE_CUDNN 2 | #include "caffe/util/cudnn.hpp" 3 | 4 | namespace caffe { 5 | namespace cudnn { 6 | 7 | float dataType::oneval = 1.0; 8 | float dataType::zeroval = 0.0; 9 | const void* dataType::one = 10 | static_cast(&dataType::oneval); 11 | const void* dataType::zero = 12 | static_cast(&dataType::zeroval); 13 | 14 | double dataType::oneval = 1.0; 15 | double dataType::zeroval = 0.0; 16 | const void* dataType::one = 17 | static_cast(&dataType::oneval); 18 | const void* dataType::zero = 19 | static_cast(&dataType::zeroval); 20 | 21 | } // namespace cudnn 22 | } // namespace caffe 23 | #endif 24 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/util/db.cpp: -------------------------------------------------------------------------------- 1 | #include "caffe/util/db.hpp" 2 | #include "caffe/util/db_leveldb.hpp" 3 | #include "caffe/util/db_lmdb.hpp" 4 | 5 | #include 6 | 7 | namespace caffe { namespace db { 8 | 9 | DB* GetDB(DataParameter::DB backend) { 10 | switch (backend) { 11 | #ifdef USE_LEVELDB 12 | case DataParameter_DB_LEVELDB: 13 | return new LevelDB(); 14 | #endif // USE_LEVELDB 15 | #ifdef USE_LMDB 16 | case DataParameter_DB_LMDB: 17 | return new LMDB(); 18 | #endif // USE_LMDB 19 | default: 20 | LOG(FATAL) << "Unknown database backend"; 21 | return NULL; 22 | } 23 | } 24 | 25 | DB* GetDB(const string& backend) { 26 | #ifdef USE_LEVELDB 27 | if (backend == "leveldb") { 28 | return new LevelDB(); 29 | } 30 | #endif // USE_LEVELDB 31 | #ifdef USE_LMDB 32 | if (backend == "lmdb") { 33 | return new LMDB(); 34 | } 35 | #endif // USE_LMDB 36 | LOG(FATAL) << "Unknown database backend"; 37 | return NULL; 38 | } 39 | 40 | } // namespace db 41 | } // namespace caffe 42 | -------------------------------------------------------------------------------- /caffe3d/src/caffe/util/db_leveldb.cpp: -------------------------------------------------------------------------------- 1 | #ifdef USE_LEVELDB 2 | #include "caffe/util/db_leveldb.hpp" 3 | 4 | #include 5 | 6 | namespace caffe { namespace db { 7 | 8 | void LevelDB::Open(const string& source, Mode mode) { 9 | leveldb::Options options; 10 | options.block_size = 65536; 11 | options.write_buffer_size = 268435456; 12 | options.max_open_files = 100; 13 | options.error_if_exists = mode == NEW; 14 | options.create_if_missing = mode != READ; 15 | leveldb::Status status = leveldb::DB::Open(options, source, &db_); 16 | CHECK(status.ok()) << "Failed to open leveldb " << source 17 | << std::endl << status.ToString(); 18 | LOG(INFO) << "Opened leveldb " << source; 19 | } 20 | 21 | } // namespace db 22 | } // namespace caffe 23 | #endif // USE_LEVELDB 24 | -------------------------------------------------------------------------------- /caffe3d/src/gtest/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_library(gtest STATIC EXCLUDE_FROM_ALL gtest.h gtest-all.cpp) 2 | caffe_default_properties(gtest) 3 | 4 | #add_library(gtest_main gtest_main.cc) 5 | #target_link_libraries(gtest_main gtest) 6 | -------------------------------------------------------------------------------- /caffe3d/tools/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | # Collect source files 2 | file(GLOB_RECURSE srcs ${CMAKE_CURRENT_SOURCE_DIR}/*.cpp) 3 | 4 | # Build each source file independently 5 | foreach(source ${srcs}) 6 | get_filename_component(name ${source} NAME_WE) 7 | 8 | # caffe target already exits 9 | if(name MATCHES "caffe") 10 | set(name ${name}.bin) 11 | endif() 12 | 13 | # target 14 | add_executable(${name} ${source}) 15 | target_link_libraries(${name} ${Caffe_LINK}) 16 | caffe_default_properties(${name}) 17 | 18 | # set back RUNTIME_OUTPUT_DIRECTORY 19 | caffe_set_runtime_directory(${name} "${PROJECT_BINARY_DIR}/tools") 20 | caffe_set_solution_folder(${name} tools) 21 | 22 | # restore output name without suffix 23 | if(name MATCHES "caffe.bin") 24 | set_target_properties(${name} PROPERTIES OUTPUT_NAME caffe) 25 | endif() 26 | 27 | # Install 28 | install(TARGETS ${name} DESTINATION bin) 29 | endforeach(source) 30 | -------------------------------------------------------------------------------- /caffe3d/tools/device_query.cpp: -------------------------------------------------------------------------------- 1 | #include "caffe/common.hpp" 2 | 3 | int main(int argc, char** argv) { 4 | LOG(FATAL) << "Deprecated. Use caffe device_query " 5 | "[--device_id=0] instead."; 6 | return 0; 7 | } 8 | -------------------------------------------------------------------------------- /caffe3d/tools/finetune_net.cpp: -------------------------------------------------------------------------------- 1 | #include "caffe/caffe.hpp" 2 | 3 | int main(int argc, char** argv) { 4 | LOG(FATAL) << "Deprecated. Use caffe train --solver=... " 5 | "[--weights=...] instead."; 6 | return 0; 7 | } 8 | -------------------------------------------------------------------------------- /caffe3d/tools/net_speed_benchmark.cpp: -------------------------------------------------------------------------------- 1 | #include "caffe/caffe.hpp" 2 | 3 | int main(int argc, char** argv) { 4 | LOG(FATAL) << "Deprecated. Use caffe time --model=... " 5 | "[--iterations=50] [--gpu] [--device_id=0]"; 6 | return 0; 7 | } 8 | -------------------------------------------------------------------------------- /caffe3d/tools/test_net.cpp: -------------------------------------------------------------------------------- 1 | #include "caffe/caffe.hpp" 2 | 3 | int main(int argc, char** argv) { 4 | LOG(FATAL) << "Deprecated. Use caffe test --model=... " 5 | "--weights=... instead."; 6 | return 0; 7 | } 8 | -------------------------------------------------------------------------------- /caffe3d/tools/train_net.cpp: -------------------------------------------------------------------------------- 1 | #include "caffe/caffe.hpp" 2 | 3 | int main(int argc, char** argv) { 4 | LOG(FATAL) << "Deprecated. Use caffe train --solver=... " 5 | "[--snapshot=...] instead."; 6 | return 0; 7 | } 8 | -------------------------------------------------------------------------------- /experiments/Text_to_Clip/_init_paths.py: -------------------------------------------------------------------------------- 1 | # -------------------------------------------------------- 2 | # Text-to-Clip Retrieval 3 | # Copyright (c) 2019 Boston Univ. 4 | # Licensed under The MIT License [see LICENSE for details] 5 | # By Huijuan Xu 6 | # -------------------------------------------------------- 7 | 8 | #!/usr/bin/env python 9 | 10 | 11 | 12 | """Set up paths.""" 13 | 14 | import os.path as osp 15 | import sys 16 | 17 | def add_path(path): 18 | if path not in sys.path: 19 | sys.path.insert(0, path) 20 | 21 | this_dir = osp.dirname(__file__) 22 | 23 | # Add caffe to PYTHONPATH 24 | caffe_path = osp.join(this_dir, '..', '..', 'caffe3d', 'python') 25 | add_path(caffe_path) 26 | 27 | # Add lib to PYTHONPATH 28 | lib_path = osp.join(this_dir, '..', '..', 'lib') 29 | add_path(lib_path) 30 | 31 | -------------------------------------------------------------------------------- /experiments/Text_to_Clip/_init_paths.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/experiments/Text_to_Clip/_init_paths.pyc -------------------------------------------------------------------------------- /experiments/Text_to_Clip/script_train.sh: -------------------------------------------------------------------------------- 1 | # -------------------------------------------------------- 2 | # Text-to-Clip Retrieval 3 | # Copyright (c) 2019 Boston Univ. 4 | # Licensed under The MIT License [see LICENSE for details] 5 | # By Huijuan Xu 6 | # -------------------------------------------------------- 7 | 8 | 9 | #export CUDA_HOME=/usr/local/cuda-7.5 10 | #export LD_LIBRARY_PATH=${CUDA_HOME}/lib64 11 | 12 | 13 | export PYTHONUNBUFFERED=true 14 | 15 | GPU_ID=0 16 | EX_DIR=Text_to_Clip 17 | 18 | LOG="./experiments/${EX_DIR}/log.txt.`date +'%Y-%m-%d_%H-%M-%S'`" 19 | 20 | 21 | time python ./experiments/${EX_DIR}/train_net.py --gpu ${GPU_ID} \ 22 | --solver ./experiments/${EX_DIR}/solver.prototxt \ 23 | --cfg ./experiments/${EX_DIR}/td_cnn_end2end.yml \ 24 | ${EXTRA_ARGS} \ 25 | 2>&1 | tee $LOG 26 | 27 | -------------------------------------------------------------------------------- /experiments/Text_to_Clip/solver.prototxt: -------------------------------------------------------------------------------- 1 | net: "./experiments/Text_to_Clip/train_lstm.prototxt" 2 | #train_state: { stage: 'embed-drop' stage: 'lstm-drop' } 3 | #test_iter: 25 4 | #test_state: { stage: 'test-on-train' } 5 | # test_iter: 25 6 | # test_state: { stage: 'test-on-val' } 7 | #test_interval: 1000 8 | 9 | 10 | # All parameters are from the cited paper above 11 | base_lr: 0.001 12 | momentum: 0.9 13 | momentum2: 0.999 14 | # since Adam dynamically changes the learning rate, we set the base learning 15 | # rate to a fixed value 16 | lr_policy: "fixed" 17 | 18 | 19 | display: 1 20 | max_iter: 271800 21 | 22 | 23 | weight_decay: 0.0000 24 | 25 | 26 | 27 | snapshot: 1000 28 | snapshot_prefix: "./experiments/Text_to_Clip/snapshot/lstm_lm" 29 | 30 | type: "Adam" 31 | solver_mode: GPU 32 | 33 | random_seed: 1701 34 | 35 | average_loss: 100 36 | clip_gradients: 10 37 | -------------------------------------------------------------------------------- /experiments/Text_to_Clip/td_cnn_end2end.yml: -------------------------------------------------------------------------------- 1 | TRAIN: 2 | HAS_RPN: True 3 | VIDEO_BATCH: 1 4 | TWIN_NORMALIZE_TARGETS_PRECOMPUTED: True 5 | RPN_POSITIVE_OVERLAP: 0.7 6 | RPN_BATCHSIZE: 64 7 | PROPOSAL_METHOD: gt 8 | BG_THRESH_LO: 0.0 9 | RPN_MIN_SIZE: 0 10 | LENGTH: [768] 11 | USE_PREFETCH: True 12 | SNAPSHOT_ITERS: 1000 13 | CAPTION_FG_THRESH: 0.7 14 | FG_FRACTION: 0.5 15 | CAPTION_TOP_N: 100 16 | CAPTION_MIN_SIZE: 0 17 | TEST: 18 | HAS_RPN: True 19 | NMS: 0.9999 20 | RPN_MIN_SIZE: 0 21 | LENGTH: [768] 22 | RPN_POST_NMS_TOP_N: 1000 23 | CAPTION_TOP_N: 1000 24 | CAPTION_MIN_SIZE: 0 25 | 26 | NUM_CLASSES: 2 27 | MAX_WORDS: 10 28 | LSTM_BATCH_SIZE: 32 29 | MAX_SENTENCE_LSTM: 20 30 | INPUT: "video" 31 | 32 | 33 | 34 | 35 | 36 | # For reproducibility 37 | # __C.RNG_SEED = 3 38 | 39 | -------------------------------------------------------------------------------- /experiments/Text_to_Clip/test_fast/_init_paths.py: -------------------------------------------------------------------------------- 1 | # -------------------------------------------------------- 2 | # Text-to-Clip Retrieval 3 | # Copyright (c) 2019 Boston Univ. 4 | # Licensed under The MIT License [see LICENSE for details] 5 | # By Huijuan Xu 6 | # -------------------------------------------------------- 7 | 8 | #!/usr/bin/env python 9 | 10 | 11 | 12 | """Set up paths.""" 13 | 14 | import os.path as osp 15 | import sys 16 | 17 | def add_path(path): 18 | if path not in sys.path: 19 | sys.path.insert(0, path) 20 | 21 | this_dir = osp.dirname(__file__) 22 | 23 | # Add caffe to PYTHONPATH 24 | caffe_path = osp.join(this_dir, '..', '..','..', 'caffe3d', 'python') 25 | add_path(caffe_path) 26 | 27 | # Add lib to PYTHONPATH 28 | lib_path = osp.join(this_dir, '..', '..', '..','lib') 29 | add_path(lib_path) 30 | -------------------------------------------------------------------------------- /experiments/Text_to_Clip/test_fast/_init_paths.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/experiments/Text_to_Clip/test_fast/_init_paths.pyc -------------------------------------------------------------------------------- /experiments/Text_to_Clip/test_fast/evaluation/bash.sh: -------------------------------------------------------------------------------- 1 | 2 | export PYTHONUNBUFFERED=1 3 | 4 | for (( i=5; i<=5; i+=1 )); do 5 | python evaluation_recall.py ../sim_pickle/sim_iter_${i}000.p > recall_results_${i}000.txt 6 | done 7 | 8 | 9 | 10 | 11 | -------------------------------------------------------------------------------- /experiments/Text_to_Clip/test_fast/evaluation/recall_results_5000.txt: -------------------------------------------------------------------------------- 1 | Namespace(gt_file='/scratch4/ds/charades_retrieval_experiments/preprocess/caption_gt_test.json', pred_file='../sim_pickle/sim_iter_5000.p', recall=[1, 5, 10], tiou=[0.1, 0.3, 0.5, 0.7]) 2 | 3 | tiou@0.1 : [1, 5, 10] 4 | 0.645967741935 5 | 0.992204301075 6 | 0.995967741935 7 | 8 | tiou@0.3 : [1, 5, 10] 9 | 0.522580645161 10 | 0.953225806452 11 | 0.991935483871 12 | 13 | tiou@0.5 : [1, 5, 10] 14 | 0.344086021505 15 | 0.770430107527 16 | 0.925268817204 17 | 18 | tiou@0.7 : [1, 5, 10] 19 | 0.156451612903 20 | 0.448924731183 21 | 0.614247311828 22 | -------------------------------------------------------------------------------- /experiments/Text_to_Clip/test_fast/script_test.sh: -------------------------------------------------------------------------------- 1 | # -------------------------------------------------------- 2 | # Text-to-Clip Retrieval 3 | # Copyright (c) 2019 Boston Univ. 4 | # Licensed under The MIT License [see LICENSE for details] 5 | # By Huijuan Xu 6 | # -------------------------------------------------------- 7 | 8 | 9 | #export CUDA_HOME=/usr/local/cuda-7.5 10 | #export LD_LIBRARY_PATH=${CUDA_HOME}/lib64 11 | 12 | GPU_ID=0 13 | 14 | EX_PATH=experiments 15 | EX_DIR=Text_to_Clip 16 | 17 | 18 | export PYTHONUNBUFFERED=true 19 | 20 | 21 | for (( i=5; i<=5; i+=1 )); do 22 | 23 | 24 | 25 | LOG="${EX_PATH}/${EX_DIR}/test_fast/test_log_${i}.txt.`date +'%Y-%m-%d_%H-%M-%S'`" 26 | 27 | 28 | time python ./${EX_PATH}/${EX_DIR}/test_fast/test_net.py --gpu ${GPU_ID} \ 29 | --def ./${EX_PATH}/${EX_DIR}/test_fast/test_rpn.prototxt \ 30 | --def-lstm ./${EX_PATH}/${EX_DIR}/test_fast/test_lstm.prototxt \ 31 | --def-retrieval ./${EX_PATH}/${EX_DIR}/test_fast/test_retrieval.prototxt \ 32 | --net ...../train_rpn/snapshot/activitynet_iter_30000.caffemodel \ 33 | --netRetrieval ./${EX_PATH}/${EX_DIR}/snapshot/lstm_lm_iter_${i}000.caffemodel \ 34 | --cfg ./${EX_PATH}/${EX_DIR}/test_fast/td_cnn_end2end.yml \ 35 | ${EXTRA_ARGS} \ 36 | 2>&1 | tee $LOG 37 | 38 | done 39 | 40 | 41 | 42 | 43 | -------------------------------------------------------------------------------- /experiments/Text_to_Clip/test_fast/td_cnn_end2end.yml: -------------------------------------------------------------------------------- 1 | TRAIN: 2 | HAS_RPN: True 3 | VIDEO_BATCH: 1 4 | TWIN_NORMALIZE_TARGETS_PRECOMPUTED: True 5 | RPN_POSITIVE_OVERLAP: 0.7 6 | RPN_BATCHSIZE: 64 7 | PROPOSAL_METHOD: gt 8 | BG_THRESH_LO: 0.0 9 | RPN_MIN_SIZE: 0 10 | LENGTH: [768] 11 | USE_PREFETCH: True 12 | FG_FRACTION: 0.5 13 | SNAPSHOT_ITERS: 1000 14 | CAPTION_FG_THRESH: 0.7 15 | CAPTION_TOP_N: 32 16 | CAPTION_MIN_SIZE: 0 17 | TEST: 18 | HAS_RPN: True 19 | NMS: 0.9999 20 | RPN_MIN_SIZE: 0 21 | LENGTH: [768] 22 | CAPTION_TOP_N: 1000 23 | CAPTION_MIN_SIZE: 0 24 | RPN_POST_NMS_TOP_N: 100 25 | 26 | NUM_CLASSES: 2 27 | MAX_WORDS: 10 28 | MAX_SENTENCE_LSTM: 20 29 | LSTM_BATCH_SIZE: 32 30 | INPUT: "video" 31 | 32 | 33 | 34 | # For reproducibility 35 | # __C.RNG_SEED = 3 36 | -------------------------------------------------------------------------------- /experiments/Text_to_Clip/test_fast/utils.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/experiments/Text_to_Clip/test_fast/utils.pyc -------------------------------------------------------------------------------- /experiments/extract_HDF_for_LSTM/_init_paths.py: -------------------------------------------------------------------------------- 1 | # -------------------------------------------------------- 2 | # Text-to-Clip Retrieval 3 | # Copyright (c) 2019 Boston Univ. 4 | # Licensed under The MIT License [see LICENSE for details] 5 | # By Huijuan Xu 6 | # -------------------------------------------------------- 7 | 8 | #!/usr/bin/env python 9 | 10 | 11 | """Set up paths for TD-CNN.""" 12 | 13 | import os.path as osp 14 | import sys 15 | 16 | def add_path(path): 17 | if path not in sys.path: 18 | sys.path.insert(0, path) 19 | 20 | this_dir = osp.dirname(__file__) 21 | 22 | # Add caffe to PYTHONPATH 23 | caffe_path = osp.join(this_dir, '..', '..','..', 'caffe3d', 'python') 24 | add_path(caffe_path) 25 | 26 | # Add lib to PYTHONPATH 27 | lib_path = osp.join(this_dir, '..', '..', '..','lib') 28 | add_path(lib_path) 29 | -------------------------------------------------------------------------------- /experiments/extract_HDF_for_LSTM/_init_paths.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/experiments/extract_HDF_for_LSTM/_init_paths.pyc -------------------------------------------------------------------------------- /experiments/extract_HDF_for_LSTM/script_test.sh: -------------------------------------------------------------------------------- 1 | # -------------------------------------------------------- 2 | # Text-to-Clip Retrieval 3 | # Copyright (c) 2019 Boston Univ. 4 | # Licensed under The MIT License [see LICENSE for details] 5 | # By Huijuan Xu 6 | # -------------------------------------------------------- 7 | 8 | 9 | #export CUDA_HOME=/usr/local/cuda-7.5 10 | #export LD_LIBRARY_PATH=${CUDA_HOME}/lib64 11 | 12 | GPU_ID=0 13 | EX_DIR=extract_HDF_for_LSTM 14 | 15 | export PYTHONUNBUFFERED=true 16 | 17 | 18 | for (( i=30; i<=30; i+=10 )); do 19 | 20 | LOG="experiments/${EX_DIR}/test_log_${i}.txt.`date +'%Y-%m-%d_%H-%M-%S'`" 21 | 22 | time python ./experiments/${EX_DIR}/test_net.py --gpu ${GPU_ID} \ 23 | --def ./experiments/${EX_DIR}/test_rpn.prototxt \ 24 | --net ../train_rpn/snapshot/activitynet_iter_${i}000.caffemodel \ 25 | --cfg ./experiments/${EX_DIR}/td_cnn_end2end.yml \ 26 | ${EXTRA_ARGS} \ 27 | 2>&1 | tee $LOG 28 | 29 | done 30 | 31 | 32 | -------------------------------------------------------------------------------- /experiments/extract_HDF_for_LSTM/td_cnn_end2end.yml: -------------------------------------------------------------------------------- 1 | TRAIN: 2 | HAS_RPN: True 3 | VIDEO_BATCH: 1 4 | TWIN_NORMALIZE_TARGETS_PRECOMPUTED: True 5 | RPN_POSITIVE_OVERLAP: 0.7 6 | RPN_BATCHSIZE: 64 7 | PROPOSAL_METHOD: gt 8 | BG_THRESH_LO: 0.0 9 | RPN_MIN_SIZE: 0 10 | LENGTH: [768] 11 | USE_PREFETCH: True 12 | SNAPSHOT_ITERS: 1000 13 | CAPTION_FG_THRESH: 0.7 14 | CAPTION_TOP_N: 32 15 | CAPTION_MIN_SIZE: 0 16 | FG_FRACTION: 0.5 17 | TEST: 18 | HAS_RPN: True 19 | NMS: 0.9999 20 | RPN_MIN_SIZE: 0 21 | LENGTH: [768] 22 | RPN_POST_NMS_TOP_N: 1000 23 | CAPTION_TOP_N: 32 24 | CAPTION_MIN_SIZE: 0 25 | 26 | NUM_CLASSES: 2 27 | MAX_WORDS: 10 28 | LSTM_BATCH_SIZE: 32 29 | MAX_SENTENCE_LSTM: 20 30 | INPUT: "video" 31 | 32 | 33 | 34 | # For reproducibility 35 | # __C.RNG_SEED = 3 36 | -------------------------------------------------------------------------------- /experiments/extract_HDF_for_LSTM/utils.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/experiments/extract_HDF_for_LSTM/utils.pyc -------------------------------------------------------------------------------- /experiments/train_rpn/_init_paths.py: -------------------------------------------------------------------------------- 1 | # -------------------------------------------------------- 2 | # Text-to-Clip Retrieval 3 | # Copyright (c) 2019 Boston Univ. 4 | # Licensed under The MIT License [see LICENSE for details] 5 | # By Huijuan Xu 6 | # -------------------------------------------------------- 7 | 8 | #!/usr/bin/env python 9 | 10 | """Set up paths for TD-CNN.""" 11 | 12 | import os.path as osp 13 | import sys 14 | 15 | def add_path(path): 16 | if path not in sys.path: 17 | sys.path.insert(0, path) 18 | 19 | this_dir = osp.dirname(__file__) 20 | 21 | # Add caffe to PYTHONPATH 22 | caffe_path = osp.join(this_dir, '..', '..', 'caffe3d', 'python') 23 | add_path(caffe_path) 24 | 25 | # Add lib to PYTHONPATH 26 | lib_path = osp.join(this_dir, '..', '..', 'lib') 27 | add_path(lib_path) 28 | -------------------------------------------------------------------------------- /experiments/train_rpn/_init_paths.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/experiments/train_rpn/_init_paths.pyc -------------------------------------------------------------------------------- /experiments/train_rpn/script_train.sh: -------------------------------------------------------------------------------- 1 | # -------------------------------------------------------- 2 | # Text-to-Clip Retrieval 3 | # Copyright (c) 2019 Boston Univ. 4 | # Licensed under The MIT License [see LICENSE for details] 5 | # Written by Huijuan Xu 6 | # -------------------------------------------------------- 7 | 8 | 9 | #export CUDA_HOME=/usr/local/cuda-7.5 10 | #export LD_LIBRARY_PATH=${CUDA_HOME}/lib64 11 | 12 | 13 | export PYTHONUNBUFFERED=true 14 | 15 | GPU_ID=0 16 | EX_DIR=train_rpn 17 | 18 | LOG="experiments/${EX_DIR}/log.txt.`date +'%Y-%m-%d_%H-%M-%S'`" 19 | 20 | 21 | time python ./experiments/${EX_DIR}/train_net.py --gpu ${GPU_ID} \ 22 | --solver ./experiments/${EX_DIR}/solver.prototxt \ 23 | --weights ./pretrain/charades_iter_25000_fps5_lrONEepoch.caffemodel \ 24 | --cfg ./experiments/${EX_DIR}/td_cnn_end2end.yml \ 25 | ${EXTRA_ARGS} \ 26 | 2>&1 | tee $LOG 27 | 28 | 29 | -------------------------------------------------------------------------------- /experiments/train_rpn/solver.prototxt: -------------------------------------------------------------------------------- 1 | train_net: "./experiments/train_rpn/train.prototxt" 2 | base_lr: 0.0001 3 | #base_lr: 0.00001 4 | lr_policy: "step" 5 | gamma: 0.1 6 | stepsize: 350000 7 | display: 1 8 | average_loss: 100 9 | momentum: 0.9 10 | weight_decay: 0.0005 11 | # We disable standard caffe solver snapshotting and implement our own 12 | # snapshot function 13 | snapshot: 0 14 | # We still use the snapshot prefix, though 15 | snapshot_prefix: "./experiments/train_rpn/snapshot/activitynet" 16 | iter_size: 1 17 | -------------------------------------------------------------------------------- /experiments/train_rpn/td_cnn_end2end.yml: -------------------------------------------------------------------------------- 1 | TRAIN: 2 | HAS_RPN: True 3 | VIDEO_BATCH: 1 4 | TWIN_NORMALIZE_TARGETS_PRECOMPUTED: True 5 | RPN_POSITIVE_OVERLAP: 0.7 6 | RPN_BATCHSIZE: 64 7 | PROPOSAL_METHOD: gt 8 | BG_THRESH_LO: 0.0 9 | RPN_MIN_SIZE: 0 10 | LENGTH: [768] 11 | USE_PREFETCH: True 12 | SNAPSHOT_ITERS: 1000 13 | CAPTION_FG_THRESH: 0.7 14 | FG_FRACTION: 0.5 15 | TEST: 16 | HAS_RPN: True 17 | NMS: 0.9999 18 | RPN_MIN_SIZE: 0 19 | LENGTH: [768] 20 | RPN_POST_NMS_TOP_N: 100 21 | 22 | NUM_CLASSES: 2 23 | MAX_WORDS: 10 24 | INPUT: "video" 25 | 26 | 27 | 28 | # For reproducibility 29 | # __C.RNG_SEED = 3 30 | 31 | -------------------------------------------------------------------------------- /lib/Makefile: -------------------------------------------------------------------------------- 1 | all: 2 | python setup.py build_ext --inplace 3 | rm -rf build 4 | -------------------------------------------------------------------------------- /lib/nms/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/nms/__init__.py -------------------------------------------------------------------------------- /lib/nms/__init__.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/nms/__init__.pyc -------------------------------------------------------------------------------- /lib/nms/cpu_nms.so: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/nms/cpu_nms.so -------------------------------------------------------------------------------- /lib/nms/gpu_nms.hpp: -------------------------------------------------------------------------------- 1 | void _nms(int* keep_out, int* num_out, const float* boxes_host, int boxes_num, 2 | int boxes_dim, float nms_overlap_thresh, int device_id); 3 | -------------------------------------------------------------------------------- /lib/nms/gpu_nms.pyx: -------------------------------------------------------------------------------- 1 | # -------------------------------------------------------- 2 | # Faster R-CNN 3 | # Copyright (c) 2015 Microsoft 4 | # Licensed under The MIT License [see LICENSE for details] 5 | # Written by Ross Girshick 6 | # Text-to-Clip Retrieval by Huijuan Xu 7 | # -------------------------------------------------------- 8 | 9 | import numpy as np 10 | cimport numpy as np 11 | 12 | assert sizeof(int) == sizeof(np.int32_t) 13 | 14 | cdef extern from "gpu_nms.hpp": 15 | void _nms(np.int32_t*, int*, np.float32_t*, int, int, float, int) 16 | 17 | def gpu_nms(np.ndarray[np.float32_t, ndim=2] dets, np.float thresh, 18 | np.int32_t device_id=0): 19 | cdef int boxes_num = dets.shape[0] 20 | cdef int boxes_dim = dets.shape[1] 21 | cdef int num_out 22 | cdef np.ndarray[np.int32_t, ndim=1] \ 23 | keep = np.zeros(boxes_num, dtype=np.int32) 24 | cdef np.ndarray[np.float32_t, ndim=1] \ 25 | scores = dets[:, 2] 26 | cdef np.ndarray[np.int_t, ndim=1] \ 27 | order = scores.argsort()[::-1] 28 | cdef np.ndarray[np.float32_t, ndim=2] \ 29 | sorted_dets = dets[order, :] 30 | _nms(&keep[0], &num_out, &sorted_dets[0, 0], boxes_num, boxes_dim, thresh, device_id) 31 | keep = keep[:num_out] 32 | return list(order[keep]) 33 | -------------------------------------------------------------------------------- /lib/nms/gpu_nms.so: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/nms/gpu_nms.so -------------------------------------------------------------------------------- /lib/nms/py_cpu_nms.py: -------------------------------------------------------------------------------- 1 | # -------------------------------------------------------- 2 | # Fast R-CNN 3 | # Copyright (c) 2015 Microsoft 4 | # Licensed under The MIT License [see LICENSE for details] 5 | # Written by Ross Girshick 6 | # Text-to-Clip Retrieval by Huijuan Xu 7 | # -------------------------------------------------------- 8 | 9 | import numpy as np 10 | 11 | def py_cpu_nms(dets, thresh): 12 | """Pure Python NMS baseline.""" 13 | x1 = dets[:, 0] 14 | x2 = dets[:, 1] 15 | scores = dets[:, 2] 16 | 17 | lengths = x2 - x1 + 1 18 | order = scores.argsort()[::-1] 19 | 20 | keep = [] 21 | while order.size > 0: 22 | i = order[0] 23 | keep.append(i) 24 | xx1 = np.maximum(x1[i], x1[order[1:]]) 25 | xx2 = np.minimum(x2[i], x2[order[1:]]) 26 | 27 | inter = np.maximum(0.0, xx2 - xx1 + 1) 28 | ovr = inter / (areas[i] + areas[order[1:]] - inter) 29 | 30 | inds = np.where(ovr <= thresh)[0] 31 | order = order[inds + 1] 32 | 33 | return keep 34 | -------------------------------------------------------------------------------- /lib/roi_data_layer/__init__.py: -------------------------------------------------------------------------------- 1 | # -------------------------------------------------------- 2 | # Fast R-CNN 3 | # Copyright (c) 2015 Microsoft 4 | # Licensed under The MIT License [see LICENSE for details] 5 | # Written by Ross Girshick 6 | # -------------------------------------------------------- 7 | -------------------------------------------------------------------------------- /lib/roi_data_layer/__init__.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/roi_data_layer/__init__.pyc -------------------------------------------------------------------------------- /lib/roi_data_layer/layer_caption.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/roi_data_layer/layer_caption.pyc -------------------------------------------------------------------------------- /lib/roi_data_layer/minibatch.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/roi_data_layer/minibatch.pyc -------------------------------------------------------------------------------- /lib/roi_data_layer/minibatch_caption.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/roi_data_layer/minibatch_caption.pyc -------------------------------------------------------------------------------- /lib/roi_data_layer/roidb.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/roi_data_layer/roidb.pyc -------------------------------------------------------------------------------- /lib/rpn/GTbox_sorted.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/rpn/GTbox_sorted.pyc -------------------------------------------------------------------------------- /lib/rpn/GTboxes_to_GTrois.py: -------------------------------------------------------------------------------- 1 | # -------------------------------------------------------- 2 | # Text-to-Clip Retrieval 3 | # Copyright (c) 2019 Boston Univ. 4 | # Licensed under The MIT License [see LICENSE for details] 5 | # By Huijuan Xu 6 | # -------------------------------------------------------- 7 | 8 | import caffe 9 | import yaml 10 | import numpy as np 11 | import numpy.random as npr 12 | from tdcnn.config import cfg 13 | from tdcnn.twin_transform import twin_transform 14 | from utils.cython_twin import twin_overlaps 15 | 16 | DEBUG = False 17 | 18 | class ProposalTargetLayer(caffe.Layer): 19 | """ 20 | Assign object detection proposals to ground-truth targets. Produces proposal 21 | classification labels and bounding-box regression targets. 22 | """ 23 | 24 | def setup(self, bottom, top): 25 | # gt_rois 26 | top[0].reshape(1, 3) 27 | 28 | def forward(self, bottom, top): 29 | gt_wins = bottom[0].data 30 | 31 | zeros = np.zeros((gt_wins.shape[0], 1), dtype=gt_wins.dtype) 32 | gt_rois = np.hstack((zeros, gt_wins[:, :-1])) 33 | top[0].reshape(*gt_rois.shape) 34 | top[0].data[...] = gt_rois 35 | 36 | def backward(self, top, propagate_down, bottom): 37 | """This layer does not propagate gradients.""" 38 | pass 39 | 40 | def reshape(self, bottom, top): 41 | """Reshaping happens during the call to forward.""" 42 | pass 43 | 44 | 45 | -------------------------------------------------------------------------------- /lib/rpn/GTboxes_to_GTrois.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/rpn/GTboxes_to_GTrois.pyc -------------------------------------------------------------------------------- /lib/rpn/__init__.py: -------------------------------------------------------------------------------- 1 | # -------------------------------------------------------- 2 | # Fast R-CNN 3 | # Copyright (c) 2015 Microsoft 4 | # Licensed under The MIT License [see LICENSE for details] 5 | # Written by Ross Girshick and Sean Bell 6 | # -------------------------------------------------------- 7 | -------------------------------------------------------------------------------- /lib/rpn/__init__.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/rpn/__init__.pyc -------------------------------------------------------------------------------- /lib/rpn/anchor_target_layer.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/rpn/anchor_target_layer.pyc -------------------------------------------------------------------------------- /lib/rpn/generate_anchors.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/rpn/generate_anchors.pyc -------------------------------------------------------------------------------- /lib/rpn/get_controller_hidden_layer.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/rpn/get_controller_hidden_layer.pyc -------------------------------------------------------------------------------- /lib/rpn/gt_caption_target_layer_hierarchical.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/rpn/gt_caption_target_layer_hierarchical.pyc -------------------------------------------------------------------------------- /lib/rpn/pad_controller_layer.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/rpn/pad_controller_layer.pyc -------------------------------------------------------------------------------- /lib/rpn/proposal_layer.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/rpn/proposal_layer.pyc -------------------------------------------------------------------------------- /lib/tdcnn/__init__.py: -------------------------------------------------------------------------------- 1 | # -------------------------------------------------------- 2 | # Fast R-CNN 3 | # Copyright (c) 2015 Microsoft 4 | # Licensed under The MIT License [see LICENSE for details] 5 | # Written by Ross Girshick 6 | # -------------------------------------------------------- 7 | -------------------------------------------------------------------------------- /lib/tdcnn/__init__.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/tdcnn/__init__.pyc -------------------------------------------------------------------------------- /lib/tdcnn/config.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/tdcnn/config.pyc -------------------------------------------------------------------------------- /lib/tdcnn/nms_wrapper.py: -------------------------------------------------------------------------------- 1 | # -------------------------------------------------------- 2 | # Fast R-CNN 3 | # Copyright (c) 2015 Microsoft 4 | # Licensed under The MIT License [see LICENSE for details] 5 | # Written by Ross Girshick 6 | # -------------------------------------------------------- 7 | 8 | from tdcnn.config import cfg 9 | from nms.gpu_nms import gpu_nms 10 | from nms.cpu_nms import cpu_nms 11 | 12 | def nms(dets, thresh, force_cpu=False): 13 | """Dispatch to either CPU or GPU NMS implementations.""" 14 | 15 | if dets.shape[0] == 0: 16 | return [] 17 | if cfg.USE_GPU_NMS and not force_cpu: 18 | return gpu_nms(dets, thresh, device_id=cfg.GPU_ID) 19 | else: 20 | return cpu_nms(dets, thresh) 21 | -------------------------------------------------------------------------------- /lib/tdcnn/nms_wrapper.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/tdcnn/nms_wrapper.pyc -------------------------------------------------------------------------------- /lib/tdcnn/test_caption_hierarchical_fc6ContextEvery_end2end.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/tdcnn/test_caption_hierarchical_fc6ContextEvery_end2end.pyc -------------------------------------------------------------------------------- /lib/tdcnn/train_end2end.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/tdcnn/train_end2end.pyc -------------------------------------------------------------------------------- /lib/tdcnn/twin_transform.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/tdcnn/twin_transform.pyc -------------------------------------------------------------------------------- /lib/utils/__init__.py: -------------------------------------------------------------------------------- 1 | # -------------------------------------------------------- 2 | # Fast R-CNN 3 | # Copyright (c) 2015 Microsoft 4 | # Licensed under The MIT License [see LICENSE for details] 5 | # Written by Ross Girshick 6 | # -------------------------------------------------------- 7 | -------------------------------------------------------------------------------- /lib/utils/__init__.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/utils/__init__.pyc -------------------------------------------------------------------------------- /lib/utils/blob.py: -------------------------------------------------------------------------------- 1 | # -------------------------------------------------------- 2 | # Text-to-Clip Retrieval 3 | # Copyright (c) 2019 Boston Univ. 4 | # Licensed under The MIT License [see LICENSE for details] 5 | # By Huijuan Xu 6 | # -------------------------------------------------------- 7 | 8 | 9 | """Blob helper functions.""" 10 | 11 | import numpy as np 12 | import cv2 13 | 14 | def video_list_to_blob(videos): 15 | """Convert a list of videos into a network input. 16 | 17 | Assumes videos are already prepared (means subtracted, BGR order, ...). 18 | """ 19 | shape = videos[0].shape 20 | num_videos = len(videos) 21 | blob = np.zeros((num_videos, shape[0], shape[1], shape[2], shape[3]), 22 | dtype=np.float32) 23 | for i in xrange(num_videos): 24 | blob[i] = videos[i] 25 | # Move channels (axis 3) to axis 1 26 | # Axis order will become: (batch elem, channel, height, width) 27 | channel_swap = (0, 4, 1, 2, 3) 28 | blob = blob.transpose(channel_swap) 29 | return blob 30 | 31 | def prep_im_for_blob(im, pixel_means, target_size, crop_size, random_idx): 32 | """Mean subtract, resize and crop an frame for use in a blob.""" 33 | im = im.astype(np.float32, copy=False) 34 | im = cv2.resize(im, target_size, interpolation=cv2.INTER_LINEAR) 35 | im -= pixel_means 36 | x = random_idx[1] 37 | y = random_idx[0] 38 | # return im[x:x+crop_size, y:y+crop_size, :] 39 | return im[x:x+crop_size, y:y+crop_size] 40 | -------------------------------------------------------------------------------- /lib/utils/blob.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/utils/blob.pyc -------------------------------------------------------------------------------- /lib/utils/caption_generator.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/utils/caption_generator.pyc -------------------------------------------------------------------------------- /lib/utils/cython_twin.so: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/utils/cython_twin.so -------------------------------------------------------------------------------- /lib/utils/timer.py: -------------------------------------------------------------------------------- 1 | # -------------------------------------------------------- 2 | # Fast R-CNN 3 | # Copyright (c) 2015 Microsoft 4 | # Licensed under The MIT License [see LICENSE for details] 5 | # Written by Ross Girshick 6 | # -------------------------------------------------------- 7 | 8 | import time 9 | 10 | class Timer(object): 11 | """A simple timer.""" 12 | def __init__(self): 13 | self.total_time = 0. 14 | self.calls = 0 15 | self.start_time = 0. 16 | self.diff = 0. 17 | self.average_time = 0. 18 | 19 | def tic(self): 20 | # using time.time instead of time.clock because time time.clock 21 | # does not normalize for multithreading 22 | self.start_time = time.time() 23 | 24 | def toc(self, average=True): 25 | self.diff = time.time() - self.start_time 26 | self.total_time += self.diff 27 | self.calls += 1 28 | self.average_time = self.total_time / self.calls 29 | if average: 30 | return self.average_time 31 | else: 32 | return self.diff 33 | -------------------------------------------------------------------------------- /lib/utils/timer.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/VisionLearningGroup/Text-to-Clip_Retrieval/f3c479d2e3380d88218785206d25a4d941b455f9/lib/utils/timer.pyc -------------------------------------------------------------------------------- /lib/utils/twin.pyx: -------------------------------------------------------------------------------- 1 | # -------------------------------------------------------- 2 | # Fast R-CNN 3 | # Copyright (c) 2015 Microsoft 4 | # Licensed under The MIT License [see LICENSE for details] 5 | # Written by Sergey Karayev 6 | # Text-to-Clip Retrieval by Huijuan Xu 7 | # -------------------------------------------------------- 8 | 9 | cimport cython 10 | import numpy as np 11 | cimport numpy as np 12 | 13 | DTYPE = np.float 14 | ctypedef np.float_t DTYPE_t 15 | 16 | def twin_overlaps( 17 | np.ndarray[DTYPE_t, ndim=2] wins, 18 | np.ndarray[DTYPE_t, ndim=2] query_wins): 19 | """ 20 | Parameters 21 | ---------- 22 | wins: (N, 2) ndarray of float 23 | query_wins: (K, 2) ndarray of float 24 | Returns 25 | ------- 26 | overlaps: (N, K) ndarray of overlap between wins and query_wins 27 | """ 28 | cdef unsigned int N = wins.shape[0] 29 | cdef unsigned int K = query_wins.shape[0] 30 | cdef np.ndarray[DTYPE_t, ndim=2] overlaps = np.zeros((N, K), dtype=DTYPE) 31 | cdef DTYPE_t it, ut, win_len 32 | cdef unsigned int k, n 33 | for k in range(K): 34 | win_len = (query_wins[k, 1] - query_wins[k, 0] + 1) 35 | for n in range(N): 36 | it = ( 37 | min(wins[n, 1], query_wins[k, 1]) - 38 | max(wins[n, 0], query_wins[k, 0]) + 1 39 | ) 40 | if it > 0: 41 | ut = float((wins[n, 1] - wins[n, 0] + 1) + win_len - it) 42 | overlaps[n, k] = it / ut 43 | return overlaps 44 | --------------------------------------------------------------------------------