├── .gitignore ├── DATASET.md ├── INSTALL.md ├── LICENSE ├── README.md ├── configs ├── DRM_e2e_relation_X_101_32_8_FPN_1x.yaml ├── caffe2 │ ├── e2e_faster_rcnn_R_101_FPN_1x_caffe2.yaml │ ├── e2e_faster_rcnn_R_50_C4_1x_caffe2.yaml │ ├── e2e_faster_rcnn_R_50_FPN_1x_caffe2.yaml │ ├── e2e_faster_rcnn_X_101_32x8d_FPN_1x_caffe2.yaml │ ├── e2e_keypoint_rcnn_R_50_FPN_1x_caffe2.yaml │ ├── e2e_mask_rcnn_R_101_FPN_1x_caffe2.yaml │ ├── e2e_mask_rcnn_R_50_C4_1x_caffe2.yaml │ ├── e2e_mask_rcnn_R_50_FPN_1x_caffe2.yaml │ ├── e2e_mask_rcnn_X-152-32x8d-FPN-IN5k_1.44x_caffe2.yaml │ └── e2e_mask_rcnn_X_101_32x8d_FPN_1x_caffe2.yaml ├── cityscapes │ ├── README.md │ ├── e2e_faster_rcnn_R_50_FPN_1x_cocostyle.yaml │ └── e2e_mask_rcnn_R_50_FPN_1x_cocostyle.yaml ├── dcn │ ├── README.md │ ├── e2e_faster_rcnn_dconv_R_50_FPN_1x.yaml │ ├── e2e_faster_rcnn_mdconv_R_50_FPN_1x.yaml │ ├── e2e_mask_rcnn_dconv_R_50_FPN_1x.yaml │ └── e2e_mask_rcnn_mdconv_R_50_FPN_1x.yaml ├── e2e_relation_R_101_FPN_1x.yaml ├── e2e_relation_VGG16_1x.yaml ├── e2e_relation_X_101_32_8_FPN_1x.yaml ├── e2e_relation_detector_R_101_FPN_1x.yaml ├── e2e_relation_detector_VGG16_1x.yaml ├── e2e_relation_detector_X_101_32_8_FPN_1x.yaml ├── gn_baselines │ ├── README.md │ ├── e2e_faster_rcnn_R_50_FPN_1x_gn.yaml │ ├── e2e_faster_rcnn_R_50_FPN_Xconv1fc_1x_gn.yaml │ ├── e2e_mask_rcnn_R_50_FPN_1x_gn.yaml │ ├── e2e_mask_rcnn_R_50_FPN_Xconv1fc_1x_gn.yaml │ ├── scratch_e2e_faster_rcnn_R_50_FPN_3x_gn.yaml │ ├── scratch_e2e_faster_rcnn_R_50_FPN_Xconv1fc_3x_gn.yaml │ ├── scratch_e2e_mask_rcnn_R_50_FPN_3x_gn.yaml │ └── scratch_e2e_mask_rcnn_R_50_FPN_Xconv1fc_3x_gn.yaml ├── maskrcnn_benchmark_models │ ├── e2e_faster_rcnn_R_101_FPN_1x.yaml │ ├── e2e_faster_rcnn_R_50_C4_1x.yaml │ ├── e2e_faster_rcnn_R_50_FPN_1x.yaml │ ├── e2e_faster_rcnn_X_101_32x8d_FPN_1x.yaml │ ├── e2e_faster_rcnn_fbnet.yaml │ ├── e2e_faster_rcnn_fbnet_600.yaml │ ├── e2e_faster_rcnn_fbnet_chamv1a_600.yaml │ ├── e2e_keypoint_rcnn_R_50_FPN_1x.yaml │ ├── e2e_mask_rcnn_R_101_FPN_1x.yaml │ ├── e2e_mask_rcnn_R_50_C4_1x.yaml │ ├── e2e_mask_rcnn_R_50_FPN_1x.yaml │ ├── e2e_mask_rcnn_X_101_32x8d_FPN_1x.yaml │ ├── e2e_mask_rcnn_fbnet.yaml │ ├── e2e_mask_rcnn_fbnet_600.yaml │ ├── e2e_mask_rcnn_fbnet_xirb16d_dsmask.yaml │ ├── e2e_mask_rcnn_fbnet_xirb16d_dsmask_600.yaml │ ├── rpn_R_101_FPN_1x.yaml │ ├── rpn_R_50_C4_1x.yaml │ ├── rpn_R_50_FPN_1x.yaml │ └── rpn_X_101_32x8d_FPN_1x.yaml ├── pascal_voc │ ├── e2e_faster_rcnn_R_50_C4_1x_1_gpu_voc.yaml │ ├── e2e_faster_rcnn_R_50_C4_1x_4_gpu_voc.yaml │ └── e2e_mask_rcnn_R_50_FPN_1x_cocostyle.yaml ├── quick_schedules │ ├── e2e_faster_rcnn_R_50_C4_quick.yaml │ ├── e2e_faster_rcnn_R_50_FPN_quick.yaml │ ├── e2e_faster_rcnn_X_101_32x8d_FPN_quick.yaml │ ├── e2e_keypoint_rcnn_R_50_FPN_quick.yaml │ ├── e2e_mask_rcnn_R_50_C4_quick.yaml │ ├── e2e_mask_rcnn_R_50_FPN_quick.yaml │ ├── e2e_mask_rcnn_X_101_32x8d_FPN_quick.yaml │ ├── rpn_R_50_C4_quick.yaml │ └── rpn_R_50_FPN_quick.yaml ├── retinanet │ ├── retinanet_R-101-FPN_1x.yaml │ ├── retinanet_R-101-FPN_P5_1x.yaml │ ├── retinanet_R-50-FPN_1x.yaml │ ├── retinanet_R-50-FPN_1x_quick.yaml │ ├── retinanet_R-50-FPN_P5_1x.yaml │ └── retinanet_X_101_32x8d_FPN_1x.yaml └── test_time_aug │ └── e2e_mask_rcnn_R_50_FPN_1x.yaml ├── convert.py ├── framework.png ├── maskrcnn_benchmark ├── __init__.py ├── config │ ├── __init__.py │ ├── defaults.py │ └── paths_catalog.py ├── csrc │ ├── ROIAlign.h │ ├── ROIPool.h │ ├── SigmoidFocalLoss.h │ ├── cpu │ │ ├── ROIAlign_cpu.cpp │ │ ├── nms_cpu.cpp │ │ └── vision.h │ ├── cuda │ │ ├── ROIAlign_cuda.cu │ │ ├── ROIPool_cuda.cu │ │ ├── SigmoidFocalLoss_cuda.cu │ │ ├── deform_conv_cuda.cu │ │ ├── deform_conv_kernel_cuda.cu │ │ ├── deform_pool_cuda.cu │ │ ├── deform_pool_kernel_cuda.cu │ │ ├── nms.cu │ │ └── vision.h │ ├── deform_conv.h │ ├── deform_pool.h │ ├── nms.h │ └── vision.cpp ├── data │ ├── README.md │ ├── __init__.py │ ├── build.py │ ├── collate_batch.py │ ├── datasets │ │ ├── __init__.py │ │ ├── coco.py │ │ ├── concat_dataset.py │ │ ├── evaluation │ │ │ ├── __init__.py │ │ │ ├── coco │ │ │ │ ├── __init__.py │ │ │ │ └── coco_eval.py │ │ │ ├── gqa │ │ │ │ ├── __init__.py │ │ │ │ └── gqa_eval.py │ │ │ ├── oi │ │ │ │ ├── __init__.py │ │ │ │ ├── ap_eval_rel.py │ │ │ │ └── oi_evaluation.py │ │ │ ├── vg │ │ │ │ ├── __init__.py │ │ │ │ ├── sgg_eval.py │ │ │ │ ├── vg_eval.py │ │ │ │ └── zeroshot_triplet_new.pytorch │ │ │ └── voc │ │ │ │ ├── __init__.py │ │ │ │ └── voc_eval.py │ │ ├── gqa.py │ │ ├── list_dataset.py │ │ ├── open_image.py │ │ ├── sample.py │ │ ├── visual_genome.py │ │ └── voc.py │ ├── samplers │ │ ├── __init__.py │ │ ├── distributed.py │ │ ├── grouped_batch_sampler.py │ │ └── iteration_based_batch_sampler.py │ └── transforms │ │ ├── __init__.py │ │ ├── build.py │ │ └── transforms.py ├── engine │ ├── __init__.py │ ├── bbox_aug.py │ ├── inference.py │ └── trainer.py ├── extra │ ├── get_your_own_group │ │ ├── basic_for_all_test.py │ │ └── get_group_splits.py │ └── group_chosen_function.py ├── image_retrieval │ ├── S2G-RETRIEVAL.md │ ├── __init__.py │ ├── dataloader.py │ ├── evaluation.py │ ├── model.py │ ├── modelv2.py │ └── preprocessing.py ├── layers │ ├── __init__.py │ ├── _utils.py │ ├── batch_norm.py │ ├── dcn │ │ ├── __init__.py │ │ ├── deform_conv_func.py │ │ ├── deform_conv_module.py │ │ ├── deform_pool_func.py │ │ └── deform_pool_module.py │ ├── entropy_loss.py │ ├── kl_div_loss.py │ ├── label_smoothing_loss.py │ ├── misc.py │ ├── nms.py │ ├── roi_align.py │ ├── roi_pool.py │ ├── sigmoid_focal_loss.py │ └── smooth_l1_loss.py ├── modeling │ ├── __init__.py │ ├── backbone │ │ ├── __init__.py │ │ ├── backbone.py │ │ ├── fbnet.py │ │ ├── fbnet_builder.py │ │ ├── fbnet_modeldef.py │ │ ├── fpn.py │ │ ├── resnet.py │ │ └── vgg.py │ ├── balanced_positive_negative_sampler.py │ ├── box_coder.py │ ├── detector │ │ ├── __init__.py │ │ ├── detectors.py │ │ └── generalized_rcnn.py │ ├── make_layers.py │ ├── matcher.py │ ├── poolers.py │ ├── registry.py │ ├── roi_heads │ │ ├── __init__.py │ │ ├── attribute_head │ │ │ ├── __init__.py │ │ │ ├── attribute_head.py │ │ │ ├── loss.py │ │ │ ├── roi_attribute_feature_extractors.py │ │ │ └── roi_attribute_predictors.py │ │ ├── box_head │ │ │ ├── __init__.py │ │ │ ├── box_head.py │ │ │ ├── inference.py │ │ │ ├── loss.py │ │ │ ├── roi_box_feature_extractors.py │ │ │ ├── roi_box_predictors.py │ │ │ └── sampling.py │ │ ├── keypoint_head │ │ │ ├── __init__.py │ │ │ ├── inference.py │ │ │ ├── keypoint_head.py │ │ │ ├── loss.py │ │ │ ├── roi_keypoint_feature_extractors.py │ │ │ └── roi_keypoint_predictors.py │ │ ├── mask_head │ │ │ ├── __init__.py │ │ │ ├── inference.py │ │ │ ├── loss.py │ │ │ ├── mask_head.py │ │ │ ├── roi_mask_feature_extractors.py │ │ │ └── roi_mask_predictors.py │ │ ├── relation_head │ │ │ ├── __init__.py │ │ │ ├── inference.py │ │ │ ├── loss.py │ │ │ ├── model_Cross_Attention.py │ │ │ ├── model_Hybrid_Attention.py │ │ │ ├── model_motifs.py │ │ │ ├── model_motifs_single.py │ │ │ ├── model_motifs_with_attribute.py │ │ │ ├── model_msg_passing.py │ │ │ ├── model_transformer.py │ │ │ ├── model_two_stream.py │ │ │ ├── model_vctree.py │ │ │ ├── model_vtranse.py │ │ │ ├── reconstruction.py │ │ │ ├── relation_head.py │ │ │ ├── roi_relation_feature_extractors.py │ │ │ ├── roi_relation_predictors.py │ │ │ ├── sampling.py │ │ │ ├── utils_co_attention.py │ │ │ ├── utils_motifs.py │ │ │ ├── utils_relation.py │ │ │ ├── utils_sample.py │ │ │ ├── utils_treelstm.py │ │ │ └── utils_vctree.py │ │ └── roi_heads.py │ ├── rpn │ │ ├── __init__.py │ │ ├── anchor_generator.py │ │ ├── inference.py │ │ ├── loss.py │ │ ├── retinanet │ │ │ ├── __init__.py │ │ │ ├── inference.py │ │ │ ├── loss.py │ │ │ └── retinanet.py │ │ ├── rpn.py │ │ └── utils.py │ └── utils.py ├── solver │ ├── __init__.py │ ├── build.py │ └── lr_scheduler.py ├── structures │ ├── __init__.py │ ├── bounding_box.py │ ├── boxlist_ops.py │ ├── image_list.py │ ├── keypoint.py │ └── segmentation_mask.py └── utils │ ├── README.md │ ├── __init__.py │ ├── c2_model_loading.py │ ├── checkpoint.py │ ├── collect_env.py │ ├── comm.py │ ├── cv2_util.py │ ├── env.py │ ├── imports.py │ ├── logger.py │ ├── metric_logger.py │ ├── miscellaneous.py │ ├── model_serialization.py │ ├── model_zoo.py │ ├── registry.py │ └── timer.py ├── setup.py ├── tests ├── checkpoint.py ├── env_tests │ └── env.py ├── test_backbones.py ├── test_box_coder.py ├── test_configs.py ├── test_data_samplers.py ├── test_detectors.py ├── test_fbnet.py ├── test_feature_extractors.py ├── test_metric_logger.py ├── test_nms.py ├── test_predictors.py ├── test_rpn_heads.py ├── test_segmentation_mask.py └── utils.py └── tools ├── cityscapes ├── convert_cityscapes_to_coco.py └── instances2dict_with_polygons.py ├── detector_pretest_net.py ├── detector_pretrain_net.py ├── image_retrieval_main.py ├── relation_infer_train.py ├── relation_test_net.py ├── relation_train_net.py ├── test_directly.py └── visualize_bbox.ipynb /.gitignore: -------------------------------------------------------------------------------- 1 | # compilation and distribution 2 | __pycache__ 3 | _ext 4 | *.pyc 5 | *.so 6 | maskrcnn_benchmark.egg-info/ 7 | build/ 8 | dist/ 9 | 10 | # ipython/jupyter notebooks 11 | #*.ipynb 12 | **/.ipynb_checkpoints/ 13 | 14 | # checkpoint 15 | checkpoint/ 16 | 17 | # dataset 18 | datasets/vg/ 19 | *.png 20 | *.jpg 21 | *.jpeg 22 | 23 | # Editor temporaries 24 | *.swn 25 | *.swo 26 | *.swp 27 | *~ 28 | 29 | # Pycharm editor settings 30 | .idea 31 | 32 | # vscode editor settings 33 | .vscode 34 | 35 | # MacOS 36 | .DS_Store 37 | 38 | -------------------------------------------------------------------------------- /DATASET.md: -------------------------------------------------------------------------------- 1 | ## DATASET 2 | 3 | If you want to use other directory, please link it in `DATASETS` of `maskrcnn_benchmark/config/paths_catelog.py`. 4 | 5 | ### For VG Dataset: 6 | 1. Download the VG images [part1 (9 Gb)](https://cs.stanford.edu/people/rak248/VG_100K_2/images.zip) [part2 (5 Gb)](https://cs.stanford.edu/people/rak248/VG_100K_2/images2.zip). Extract these images to the file `datasets/vg/VG_100K`. 7 | 2. Download the [scene graphs](https://drive.google.com/drive/folders/1XTe39pfs6IQijrWNC6-ojEI0ypmJiJ1I?usp=sharing) and extract them to `datasets/vg/VG-SGG-with-attri.h5`. 8 | 4. The former list of zero-shot triplets have overlap with train triplet types. We carefully remove them and provide the updated list of zero-shot triplets. You can check the details via our repo [T-CAR](https://github.com/jkli1998/T-CAR). 9 | 10 | ### For GQA Dataset: 11 | 1. Download the GQA images [Full (20.3 Gb)](https://downloads.cs.stanford.edu/nlp/data/gqa/images.zip). Extract these images to the file `datasets/gqa/images`. 12 | 2. In order to achieve a representative split like VG150, we use the protocol provided by [SHA-GCL](https://github.com/dongxingning/SHA-GCL-for-SGG). You can download the annotation file from [this link](https://1drv.ms/u/s!AjK8-t5JiDT1kwwKFbdBB3ZU3c49?e=06qeZc), and put all three files to `datasets/gqa/`. 13 | 3. Note the link to the original GQA200 dataset was not working, so we re-uploaded the dataset to [google drive](https://drive.google.com/drive/folders/1nO0woYfBu_tKh0TEkIt_-QIhfOmqkI_d?usp=sharing). 14 | 15 | ### For Open Image V6 Dataset: 16 | 1. We use the dataset processed by [PySGG](https://github.com/SHTUPLUS/PySGG). You can download the processed dataset [Openimage V6(38GB)](https://shanghaitecheducn-my.sharepoint.com/:u:/g/personal/lirj2_shanghaitech_edu_cn/EXdZWvR_vrpNmQVvubG7vhABbdmeKKzX6PJFlIdrCS80vw?e=uQREX3). 17 | 2. The dataset dir contains the `images` and `annotations` folder. 18 | 19 | 20 | 21 | -------------------------------------------------------------------------------- /INSTALL.md: -------------------------------------------------------------------------------- 1 | ## Installation 2 | 3 | Most of the requirements of this projects are exactly the same as [Scene-Graph-Benchmark](https://github.com/KaihuaTang/Scene-Graph-Benchmark.pytorch) and [maskrcnn-benchmark](https://github.com/facebookresearch/maskrcnn-benchmark). If you have any problem of your environment, we recommend you to check their [issues page](https://github.com/facebookresearch/maskrcnn-benchmark/issues) first. Hope you will find the answer. 4 | 5 | ### Requirements: 6 | - Python == 3.7 7 | - PyTorch >= 1.7 (Mine 1.9.1 (CUDA 11.1)) 8 | - cocoapi 9 | - yacs 10 | - matplotlib 11 | - OpenCV 12 | 13 | 14 | ### Step-by-step installation 15 | 16 | ```bash 17 | # NOTE: we assume the python version is 3.7.x, if you want use other versions, please change the 4th line of `DRM/maskrcnn_benchmark/utils/imports.py` to corresponding python version. 18 | 19 | conda create --name DRM python=3.7 20 | source activate DRM 21 | 22 | # this installs the right pip and dependencies for the fresh python 23 | conda install ipython 24 | conda install scipy 25 | conda install h5py 26 | 27 | # scene_graph_benchmark and coco api dependencies 28 | pip install ninja yacs cython matplotlib tqdm opencv-python overrides 29 | 30 | # follow PyTorch installation in https://pytorch.org/get-started/locally/ 31 | # we give the instructions for CUDA 11.1 32 | pip install torch==1.9.1+cu111 torchvision==0.10.1+cu111 torchaudio==0.9.1 -f https://download.pytorch.org/whl/torch_stable.html 33 | 34 | export INSTALL_DIR=$PWD 35 | 36 | # install pycocotools 37 | cd $INSTALL_DIR 38 | git clone https://github.com/cocodataset/cocoapi.git 39 | cd cocoapi/PythonAPI 40 | python setup.py build_ext install 41 | 42 | # install apex 43 | cd $INSTALL_DIR 44 | git clone https://github.com/NVIDIA/apex.git 45 | cd apex 46 | git reset --hard 3fe10b5597ba14a748ebb271a6ab97c09c5701ac 47 | # IMPORTANT: here you need to change the 11-th line of apex/amp/_amp_state.py 48 | # to `if TORCH_MAJOR == 0 or TORCH_MINOR > 8:` 49 | python setup.py install --cuda_ext --cpp_ext 50 | 51 | # install mmcv 52 | pip install -U openmim 53 | mim install mmcv==1.7.0 54 | 55 | # install PyTorch Detection 56 | cd $INSTALL_DIR 57 | git clone https://github.com/jkli1998/DRM.git 58 | cd DRM 59 | 60 | # the following will install the lib with 61 | # symbolic links, so that you can modify 62 | # the files if you want and won't need to 63 | # re-build it 64 | python setup.py build develop 65 | 66 | 67 | unset INSTALL_DIR 68 | 69 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2018 Facebook 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 | -------------------------------------------------------------------------------- /configs/caffe2/e2e_faster_rcnn_R_101_FPN_1x_caffe2.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://Caffe2Detectron/COCO/35857890/e2e_faster_rcnn_R-101-FPN_1x" 4 | BACKBONE: 5 | CONV_BODY: "R-101-FPN" 6 | RESNETS: 7 | BACKBONE_OUT_CHANNELS: 256 8 | RPN: 9 | USE_FPN: True 10 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 11 | PRE_NMS_TOP_N_TRAIN: 2000 12 | PRE_NMS_TOP_N_TEST: 1000 13 | POST_NMS_TOP_N_TEST: 1000 14 | FPN_POST_NMS_TOP_N_TEST: 1000 15 | ROI_HEADS: 16 | USE_FPN: True 17 | ROI_BOX_HEAD: 18 | POOLER_RESOLUTION: 7 19 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 20 | POOLER_SAMPLING_RATIO: 2 21 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 22 | PREDICTOR: "FPNPredictor" 23 | DATASETS: 24 | TEST: ("coco_2014_minival",) 25 | DATALOADER: 26 | SIZE_DIVISIBILITY: 32 27 | -------------------------------------------------------------------------------- /configs/caffe2/e2e_faster_rcnn_R_50_C4_1x_caffe2.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://Caffe2Detectron/COCO/35857197/e2e_faster_rcnn_R-50-C4_1x" 4 | DATASETS: 5 | TEST: ("coco_2014_minival",) 6 | -------------------------------------------------------------------------------- /configs/caffe2/e2e_faster_rcnn_R_50_FPN_1x_caffe2.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://Caffe2Detectron/COCO/35857345/e2e_faster_rcnn_R-50-FPN_1x" 4 | BACKBONE: 5 | CONV_BODY: "R-50-FPN" 6 | RESNETS: 7 | BACKBONE_OUT_CHANNELS: 256 8 | RPN: 9 | USE_FPN: True 10 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 11 | PRE_NMS_TOP_N_TRAIN: 2000 12 | PRE_NMS_TOP_N_TEST: 1000 13 | POST_NMS_TOP_N_TEST: 1000 14 | FPN_POST_NMS_TOP_N_TEST: 1000 15 | ROI_HEADS: 16 | USE_FPN: True 17 | ROI_BOX_HEAD: 18 | POOLER_RESOLUTION: 7 19 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 20 | POOLER_SAMPLING_RATIO: 2 21 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 22 | PREDICTOR: "FPNPredictor" 23 | DATASETS: 24 | TEST: ("coco_2014_minival",) 25 | DATALOADER: 26 | SIZE_DIVISIBILITY: 32 27 | -------------------------------------------------------------------------------- /configs/caffe2/e2e_faster_rcnn_X_101_32x8d_FPN_1x_caffe2.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://Caffe2Detectron/COCO/36761737/e2e_faster_rcnn_X-101-32x8d-FPN_1x" 4 | BACKBONE: 5 | CONV_BODY: "R-101-FPN" 6 | RESNETS: 7 | BACKBONE_OUT_CHANNELS: 256 8 | STRIDE_IN_1X1: False 9 | NUM_GROUPS: 32 10 | WIDTH_PER_GROUP: 8 11 | RPN: 12 | USE_FPN: True 13 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 14 | PRE_NMS_TOP_N_TRAIN: 2000 15 | PRE_NMS_TOP_N_TEST: 1000 16 | POST_NMS_TOP_N_TEST: 1000 17 | FPN_POST_NMS_TOP_N_TEST: 1000 18 | ROI_HEADS: 19 | USE_FPN: True 20 | ROI_BOX_HEAD: 21 | POOLER_RESOLUTION: 7 22 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 23 | POOLER_SAMPLING_RATIO: 2 24 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 25 | PREDICTOR: "FPNPredictor" 26 | DATASETS: 27 | TEST: ("coco_2014_minival",) 28 | DATALOADER: 29 | SIZE_DIVISIBILITY: 32 30 | -------------------------------------------------------------------------------- /configs/caffe2/e2e_keypoint_rcnn_R_50_FPN_1x_caffe2.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://Caffe2Detectron/COCO/37697547/e2e_keypoint_rcnn_R-50-FPN_1x" 4 | BACKBONE: 5 | CONV_BODY: "R-50-FPN" 6 | RESNETS: 7 | BACKBONE_OUT_CHANNELS: 256 8 | RPN: 9 | USE_FPN: True 10 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 11 | PRE_NMS_TOP_N_TRAIN: 2000 12 | PRE_NMS_TOP_N_TEST: 1000 13 | POST_NMS_TOP_N_TEST: 1000 14 | FPN_POST_NMS_TOP_N_TEST: 1000 15 | ROI_HEADS: 16 | USE_FPN: True 17 | ROI_BOX_HEAD: 18 | POOLER_RESOLUTION: 7 19 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 20 | POOLER_SAMPLING_RATIO: 2 21 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 22 | PREDICTOR: "FPNPredictor" 23 | NUM_CLASSES: 2 24 | ROI_KEYPOINT_HEAD: 25 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 26 | FEATURE_EXTRACTOR: "KeypointRCNNFeatureExtractor" 27 | PREDICTOR: "KeypointRCNNPredictor" 28 | POOLER_RESOLUTION: 14 29 | POOLER_SAMPLING_RATIO: 2 30 | RESOLUTION: 56 31 | SHARE_BOX_FEATURE_EXTRACTOR: False 32 | KEYPOINT_ON: True 33 | DATASETS: 34 | TRAIN: ("keypoints_coco_2014_train", "keypoints_coco_2014_valminusminival",) 35 | TEST: ("keypoints_coco_2014_minival",) 36 | INPUT: 37 | MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800) 38 | DATALOADER: 39 | SIZE_DIVISIBILITY: 32 40 | SOLVER: 41 | BASE_LR: 0.02 42 | WEIGHT_DECAY: 0.0001 43 | STEPS: (60000, 80000) 44 | MAX_ITER: 90000 45 | -------------------------------------------------------------------------------- /configs/caffe2/e2e_mask_rcnn_R_101_FPN_1x_caffe2.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://Caffe2Detectron/COCO/35861795/e2e_mask_rcnn_R-101-FPN_1x" 4 | BACKBONE: 5 | CONV_BODY: "R-101-FPN" 6 | RESNETS: 7 | BACKBONE_OUT_CHANNELS: 256 8 | RPN: 9 | USE_FPN: True 10 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 11 | PRE_NMS_TOP_N_TRAIN: 2000 12 | PRE_NMS_TOP_N_TEST: 1000 13 | POST_NMS_TOP_N_TEST: 1000 14 | FPN_POST_NMS_TOP_N_TEST: 1000 15 | ROI_HEADS: 16 | USE_FPN: True 17 | ROI_BOX_HEAD: 18 | POOLER_RESOLUTION: 7 19 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 20 | POOLER_SAMPLING_RATIO: 2 21 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 22 | PREDICTOR: "FPNPredictor" 23 | ROI_MASK_HEAD: 24 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 25 | FEATURE_EXTRACTOR: "MaskRCNNFPNFeatureExtractor" 26 | PREDICTOR: "MaskRCNNC4Predictor" 27 | POOLER_RESOLUTION: 14 28 | POOLER_SAMPLING_RATIO: 2 29 | RESOLUTION: 28 30 | SHARE_BOX_FEATURE_EXTRACTOR: False 31 | MASK_ON: True 32 | DATASETS: 33 | TEST: ("coco_2014_minival",) 34 | DATALOADER: 35 | SIZE_DIVISIBILITY: 32 36 | -------------------------------------------------------------------------------- /configs/caffe2/e2e_mask_rcnn_R_50_C4_1x_caffe2.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://Caffe2Detectron/COCO/35858791/e2e_mask_rcnn_R-50-C4_1x" 4 | ROI_MASK_HEAD: 5 | PREDICTOR: "MaskRCNNC4Predictor" 6 | SHARE_BOX_FEATURE_EXTRACTOR: True 7 | MASK_ON: True 8 | DATASETS: 9 | TEST: ("coco_2014_minival",) 10 | -------------------------------------------------------------------------------- /configs/caffe2/e2e_mask_rcnn_R_50_FPN_1x_caffe2.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://Caffe2Detectron/COCO/35858933/e2e_mask_rcnn_R-50-FPN_1x" 4 | BACKBONE: 5 | CONV_BODY: "R-50-FPN" 6 | RESNETS: 7 | BACKBONE_OUT_CHANNELS: 256 8 | RPN: 9 | USE_FPN: True 10 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 11 | PRE_NMS_TOP_N_TRAIN: 2000 12 | PRE_NMS_TOP_N_TEST: 1000 13 | POST_NMS_TOP_N_TEST: 1000 14 | FPN_POST_NMS_TOP_N_TEST: 1000 15 | ROI_HEADS: 16 | USE_FPN: True 17 | ROI_BOX_HEAD: 18 | POOLER_RESOLUTION: 7 19 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 20 | POOLER_SAMPLING_RATIO: 2 21 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 22 | PREDICTOR: "FPNPredictor" 23 | ROI_MASK_HEAD: 24 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 25 | FEATURE_EXTRACTOR: "MaskRCNNFPNFeatureExtractor" 26 | PREDICTOR: "MaskRCNNC4Predictor" 27 | POOLER_RESOLUTION: 14 28 | POOLER_SAMPLING_RATIO: 2 29 | RESOLUTION: 28 30 | SHARE_BOX_FEATURE_EXTRACTOR: False 31 | MASK_ON: True 32 | DATASETS: 33 | TEST: ("coco_2014_minival",) 34 | DATALOADER: 35 | SIZE_DIVISIBILITY: 32 36 | -------------------------------------------------------------------------------- /configs/caffe2/e2e_mask_rcnn_X-152-32x8d-FPN-IN5k_1.44x_caffe2.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://Caffe2Detectron/COCO/37129812/e2e_mask_rcnn_X-152-32x8d-FPN-IN5k_1.44x" 4 | BACKBONE: 5 | CONV_BODY: "R-152-FPN" 6 | RESNETS: 7 | BACKBONE_OUT_CHANNELS: 256 8 | STRIDE_IN_1X1: False 9 | NUM_GROUPS: 32 10 | WIDTH_PER_GROUP: 8 11 | RPN: 12 | USE_FPN: True 13 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 14 | PRE_NMS_TOP_N_TRAIN: 2000 15 | PRE_NMS_TOP_N_TEST: 1000 16 | POST_NMS_TOP_N_TEST: 1000 17 | FPN_POST_NMS_TOP_N_TEST: 1000 18 | ROI_HEADS: 19 | USE_FPN: True 20 | ROI_BOX_HEAD: 21 | POOLER_RESOLUTION: 7 22 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 23 | POOLER_SAMPLING_RATIO: 2 24 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 25 | PREDICTOR: "FPNPredictor" 26 | ROI_MASK_HEAD: 27 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 28 | FEATURE_EXTRACTOR: "MaskRCNNFPNFeatureExtractor" 29 | PREDICTOR: "MaskRCNNC4Predictor" 30 | POOLER_RESOLUTION: 14 31 | POOLER_SAMPLING_RATIO: 2 32 | RESOLUTION: 28 33 | SHARE_BOX_FEATURE_EXTRACTOR: False 34 | MASK_ON: True 35 | DATASETS: 36 | TEST: ("coco_2014_minival",) 37 | DATALOADER: 38 | SIZE_DIVISIBILITY: 32 39 | -------------------------------------------------------------------------------- /configs/caffe2/e2e_mask_rcnn_X_101_32x8d_FPN_1x_caffe2.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://Caffe2Detectron/COCO/36761843/e2e_mask_rcnn_X-101-32x8d-FPN_1x" 4 | BACKBONE: 5 | CONV_BODY: "R-101-FPN" 6 | RESNETS: 7 | BACKBONE_OUT_CHANNELS: 256 8 | STRIDE_IN_1X1: False 9 | NUM_GROUPS: 32 10 | WIDTH_PER_GROUP: 8 11 | RPN: 12 | USE_FPN: True 13 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 14 | PRE_NMS_TOP_N_TRAIN: 2000 15 | PRE_NMS_TOP_N_TEST: 1000 16 | POST_NMS_TOP_N_TEST: 1000 17 | FPN_POST_NMS_TOP_N_TEST: 1000 18 | ROI_HEADS: 19 | USE_FPN: True 20 | ROI_BOX_HEAD: 21 | POOLER_RESOLUTION: 7 22 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 23 | POOLER_SAMPLING_RATIO: 2 24 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 25 | PREDICTOR: "FPNPredictor" 26 | ROI_MASK_HEAD: 27 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 28 | FEATURE_EXTRACTOR: "MaskRCNNFPNFeatureExtractor" 29 | PREDICTOR: "MaskRCNNC4Predictor" 30 | POOLER_RESOLUTION: 14 31 | POOLER_SAMPLING_RATIO: 2 32 | RESOLUTION: 28 33 | SHARE_BOX_FEATURE_EXTRACTOR: False 34 | MASK_ON: True 35 | DATASETS: 36 | TEST: ("coco_2014_minival",) 37 | DATALOADER: 38 | SIZE_DIVISIBILITY: 32 39 | -------------------------------------------------------------------------------- /configs/cityscapes/e2e_faster_rcnn_R_50_FPN_1x_cocostyle.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 4 | BACKBONE: 5 | CONV_BODY: "R-50-FPN" 6 | RESNETS: 7 | BACKBONE_OUT_CHANNELS: 256 8 | RPN: 9 | USE_FPN: True 10 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 11 | PRE_NMS_TOP_N_TRAIN: 2000 12 | PRE_NMS_TOP_N_TEST: 1000 13 | POST_NMS_TOP_N_TEST: 1000 14 | FPN_POST_NMS_TOP_N_TEST: 1000 15 | ROI_HEADS: 16 | USE_FPN: True 17 | ROI_BOX_HEAD: 18 | POOLER_RESOLUTION: 7 19 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 20 | POOLER_SAMPLING_RATIO: 2 21 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 22 | PREDICTOR: "FPNPredictor" 23 | NUM_CLASSES: 9 24 | DATASETS: 25 | TRAIN: ("cityscapes_fine_instanceonly_seg_train_cocostyle",) 26 | TEST: ("cityscapes_fine_instanceonly_seg_val_cocostyle",) 27 | DATALOADER: 28 | SIZE_DIVISIBILITY: 32 29 | SOLVER: 30 | BASE_LR: 0.01 31 | WEIGHT_DECAY: 0.0001 32 | STEPS: (18000,) 33 | MAX_ITER: 24000 34 | -------------------------------------------------------------------------------- /configs/cityscapes/e2e_mask_rcnn_R_50_FPN_1x_cocostyle.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 4 | BACKBONE: 5 | CONV_BODY: "R-50-FPN" 6 | RESNETS: 7 | BACKBONE_OUT_CHANNELS: 256 8 | RPN: 9 | USE_FPN: True 10 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 11 | PRE_NMS_TOP_N_TRAIN: 2000 12 | PRE_NMS_TOP_N_TEST: 1000 13 | POST_NMS_TOP_N_TEST: 1000 14 | FPN_POST_NMS_TOP_N_TEST: 1000 15 | ROI_HEADS: 16 | USE_FPN: True 17 | ROI_BOX_HEAD: 18 | POOLER_RESOLUTION: 7 19 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 20 | POOLER_SAMPLING_RATIO: 2 21 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 22 | PREDICTOR: "FPNPredictor" 23 | NUM_CLASSES: 9 24 | ROI_MASK_HEAD: 25 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 26 | FEATURE_EXTRACTOR: "MaskRCNNFPNFeatureExtractor" 27 | PREDICTOR: "MaskRCNNC4Predictor" 28 | POOLER_RESOLUTION: 14 29 | POOLER_SAMPLING_RATIO: 2 30 | RESOLUTION: 28 31 | SHARE_BOX_FEATURE_EXTRACTOR: False 32 | MASK_ON: True 33 | DATASETS: 34 | TRAIN: ("cityscapes_fine_instanceonly_seg_train_cocostyle",) 35 | TEST: ("cityscapes_fine_instanceonly_seg_val_cocostyle",) 36 | DATALOADER: 37 | SIZE_DIVISIBILITY: 32 38 | SOLVER: 39 | BASE_LR: 0.01 40 | WEIGHT_DECAY: 0.0001 41 | STEPS: (18000,) 42 | MAX_ITER: 24000 43 | -------------------------------------------------------------------------------- /configs/dcn/README.md: -------------------------------------------------------------------------------- 1 | ### Reference 2 | 1 [Deformable ConvNets v2: More Deformable, Better Results](https://arxiv.org/pdf/1811.11168.pdf) 3 | 2 third-party: [mmdetection](https://github.com/open-mmlab/mmdetection/tree/master/configs/dcn) 4 | 5 | ### Performance 6 | | case | bbox AP | mask AP | 7 | |----------------------------:|--------:|:-------:| 8 | | R-50-FPN-dcn (implement) | 39.8 | - | 9 | | R-50-FPN-dcn (mmdetection) | 40.0 | - | 10 | | R-50-FPN-mdcn (implement) | 40.0 | - | 11 | | R-50-FPN-mdcn (mmdetection) | 40.3 | - | 12 | | R-50-FPN-dcn (implement) | 40.8 | 36.8 | 13 | | R-50-FPN-dcn (mmdetection) | 41.1 | 37.2 | 14 | | R-50-FPN-dcn (implement) | 40.7 | 36.7 | 15 | | R-50-FPN-dcn (mmdetection) | 41.4 | 37.4 | 16 | 17 | 18 | ### Note 19 | see [dcn-v2](https://github.com/open-mmlab/mmdetection/blob/master/MODEL_ZOO.md#deformable-convolution-v2) in `mmdetection` for more details. 20 | 21 | 22 | ### Usage 23 | add these three lines 24 | ``` 25 | MODEL: 26 | RESNETS: 27 | # corresponding to C2,C3,C4,C5 28 | STAGE_WITH_DCN: (False, True, True, True) 29 | WITH_MODULATED_DCN: True 30 | DEFORMABLE_GROUPS: 1 31 | ``` -------------------------------------------------------------------------------- /configs/dcn/e2e_faster_rcnn_dconv_R_50_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | INPUT: 2 | MIN_SIZE_TRAIN: (800,) 3 | MAX_SIZE_TRAIN: 1333 4 | MIN_SIZE_TEST: 800 5 | MAX_SIZE_TEST: 1333 6 | MODEL: 7 | META_ARCHITECTURE: "GeneralizedRCNN" 8 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 9 | BACKBONE: 10 | CONV_BODY: "R-50-FPN" 11 | RESNETS: 12 | BACKBONE_OUT_CHANNELS: 256 13 | STAGE_WITH_DCN: (False, True, True, True) 14 | WITH_MODULATED_DCN: False 15 | DEFORMABLE_GROUPS: 1 16 | RPN: 17 | USE_FPN: True 18 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 19 | PRE_NMS_TOP_N_TRAIN: 2000 20 | PRE_NMS_TOP_N_TEST: 1000 21 | POST_NMS_TOP_N_TEST: 1000 22 | FPN_POST_NMS_TOP_N_TEST: 1000 23 | ROI_HEADS: 24 | USE_FPN: True 25 | ROI_BOX_HEAD: 26 | POOLER_RESOLUTION: 7 27 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 28 | POOLER_SAMPLING_RATIO: 2 29 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 30 | PREDICTOR: "FPNPredictor" 31 | DATASETS: 32 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 33 | TEST: ("coco_2014_minival",) 34 | DATALOADER: 35 | SIZE_DIVISIBILITY: 32 36 | SOLVER: 37 | # Assume 8 gpus 38 | BASE_LR: 0.02 39 | WEIGHT_DECAY: 0.0001 40 | STEPS: (60000, 80000) 41 | MAX_ITER: 90000 42 | IMS_PER_BATCH: 16 43 | TEST: 44 | IMS_PER_BATCH: 8 45 | -------------------------------------------------------------------------------- /configs/dcn/e2e_faster_rcnn_mdconv_R_50_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | INPUT: 2 | MIN_SIZE_TRAIN: (800,) 3 | MAX_SIZE_TRAIN: 1333 4 | MIN_SIZE_TEST: 800 5 | MAX_SIZE_TEST: 1333 6 | MODEL: 7 | META_ARCHITECTURE: "GeneralizedRCNN" 8 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 9 | BACKBONE: 10 | CONV_BODY: "R-50-FPN" 11 | RESNETS: 12 | BACKBONE_OUT_CHANNELS: 256 13 | STAGE_WITH_DCN: (False, True, True, True) 14 | WITH_MODULATED_DCN: True 15 | DEFORMABLE_GROUPS: 1 16 | RPN: 17 | USE_FPN: True 18 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 19 | PRE_NMS_TOP_N_TRAIN: 2000 20 | PRE_NMS_TOP_N_TEST: 1000 21 | POST_NMS_TOP_N_TEST: 1000 22 | FPN_POST_NMS_TOP_N_TEST: 1000 23 | ROI_HEADS: 24 | USE_FPN: True 25 | ROI_BOX_HEAD: 26 | POOLER_RESOLUTION: 7 27 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 28 | POOLER_SAMPLING_RATIO: 2 29 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 30 | PREDICTOR: "FPNPredictor" 31 | DATASETS: 32 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 33 | TEST: ("coco_2014_minival",) 34 | DATALOADER: 35 | SIZE_DIVISIBILITY: 32 36 | SOLVER: 37 | # Assume 8 gpus 38 | BASE_LR: 0.02 39 | WEIGHT_DECAY: 0.0001 40 | STEPS: (60000, 80000) 41 | MAX_ITER: 90000 42 | IMS_PER_BATCH: 16 43 | TEST: 44 | IMS_PER_BATCH: 8 45 | -------------------------------------------------------------------------------- /configs/dcn/e2e_mask_rcnn_dconv_R_50_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | INPUT: 2 | MIN_SIZE_TRAIN: (800,) 3 | MAX_SIZE_TRAIN: 1333 4 | MIN_SIZE_TEST: 800 5 | MAX_SIZE_TEST: 1333 6 | MODEL: 7 | META_ARCHITECTURE: "GeneralizedRCNN" 8 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 9 | BACKBONE: 10 | CONV_BODY: "R-50-FPN" 11 | RESNETS: 12 | BACKBONE_OUT_CHANNELS: 256 13 | STAGE_WITH_DCN: (False, True, True, True) 14 | WITH_MODULATED_DCN: False 15 | DEFORMABLE_GROUPS: 1 16 | RPN: 17 | USE_FPN: True 18 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 19 | PRE_NMS_TOP_N_TRAIN: 2000 20 | PRE_NMS_TOP_N_TEST: 1000 21 | POST_NMS_TOP_N_TEST: 1000 22 | FPN_POST_NMS_TOP_N_TEST: 1000 23 | ROI_HEADS: 24 | USE_FPN: True 25 | ROI_BOX_HEAD: 26 | POOLER_RESOLUTION: 7 27 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 28 | POOLER_SAMPLING_RATIO: 2 29 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 30 | PREDICTOR: "FPNPredictor" 31 | ROI_MASK_HEAD: 32 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 33 | FEATURE_EXTRACTOR: "MaskRCNNFPNFeatureExtractor" 34 | PREDICTOR: "MaskRCNNC4Predictor" 35 | POOLER_RESOLUTION: 14 36 | POOLER_SAMPLING_RATIO: 2 37 | RESOLUTION: 28 38 | SHARE_BOX_FEATURE_EXTRACTOR: False 39 | MASK_ON: True 40 | DATASETS: 41 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 42 | TEST: ("coco_2014_minival",) 43 | DATALOADER: 44 | SIZE_DIVISIBILITY: 32 45 | SOLVER: 46 | # Assume 8 gpus 47 | BASE_LR: 0.02 48 | WEIGHT_DECAY: 0.0001 49 | STEPS: (60000, 80000) 50 | MAX_ITER: 90000 51 | IMS_PER_BATCH: 16 52 | TEST: 53 | IMS_PER_BATCH: 8 54 | 55 | -------------------------------------------------------------------------------- /configs/dcn/e2e_mask_rcnn_mdconv_R_50_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | INPUT: 2 | MIN_SIZE_TRAIN: (800,) 3 | MAX_SIZE_TRAIN: 1333 4 | MIN_SIZE_TEST: 800 5 | MAX_SIZE_TEST: 1333 6 | MODEL: 7 | META_ARCHITECTURE: "GeneralizedRCNN" 8 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 9 | BACKBONE: 10 | CONV_BODY: "R-50-FPN" 11 | RESNETS: 12 | BACKBONE_OUT_CHANNELS: 256 13 | STAGE_WITH_DCN: (False, True, True, True) 14 | WITH_MODULATED_DCN: True 15 | DEFORMABLE_GROUPS: 1 16 | RPN: 17 | USE_FPN: True 18 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 19 | PRE_NMS_TOP_N_TRAIN: 2000 20 | PRE_NMS_TOP_N_TEST: 1000 21 | POST_NMS_TOP_N_TEST: 1000 22 | FPN_POST_NMS_TOP_N_TEST: 1000 23 | ROI_HEADS: 24 | USE_FPN: True 25 | ROI_BOX_HEAD: 26 | POOLER_RESOLUTION: 7 27 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 28 | POOLER_SAMPLING_RATIO: 2 29 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 30 | PREDICTOR: "FPNPredictor" 31 | ROI_MASK_HEAD: 32 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 33 | FEATURE_EXTRACTOR: "MaskRCNNFPNFeatureExtractor" 34 | PREDICTOR: "MaskRCNNC4Predictor" 35 | POOLER_RESOLUTION: 14 36 | POOLER_SAMPLING_RATIO: 2 37 | RESOLUTION: 28 38 | SHARE_BOX_FEATURE_EXTRACTOR: False 39 | MASK_ON: True 40 | DATASETS: 41 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 42 | TEST: ("coco_2014_minival",) 43 | DATALOADER: 44 | SIZE_DIVISIBILITY: 32 45 | SOLVER: 46 | # Assume 8 gpus 47 | BASE_LR: 0.02 48 | WEIGHT_DECAY: 0.0001 49 | STEPS: (60000, 80000) 50 | MAX_ITER: 90000 51 | IMS_PER_BATCH: 16 52 | TEST: 53 | IMS_PER_BATCH: 8 54 | -------------------------------------------------------------------------------- /configs/e2e_relation_detector_R_101_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | INPUT: 2 | MIN_SIZE_TRAIN: (600,) 3 | MAX_SIZE_TRAIN: 1000 4 | MIN_SIZE_TEST: 600 5 | MAX_SIZE_TEST: 1000 6 | MODEL: 7 | META_ARCHITECTURE: "GeneralizedRCNN" 8 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-101" 9 | BACKBONE: 10 | CONV_BODY: "R-101-FPN" 11 | RESNETS: 12 | BACKBONE_OUT_CHANNELS: 512 13 | RELATION_ON: False 14 | ATTRIBUTE_ON: False 15 | FLIP_AUG: False 16 | RPN: 17 | USE_FPN: True 18 | ANCHOR_SIZES: (32, 64, 128, 256, 512) 19 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 20 | ASPECT_RATIOS: (0.23232838, 0.63365731, 1.28478321, 3.15089189) # from neural-motifs 21 | PRE_NMS_TOP_N_TRAIN: 12000 22 | PRE_NMS_TOP_N_TEST: 6000 23 | POST_NMS_TOP_N_TRAIN: 2000 24 | POST_NMS_TOP_N_TEST: 1000 25 | FPN_POST_NMS_TOP_N_TRAIN: 2000 26 | FPN_POST_NMS_TOP_N_TEST: 2000 27 | FPN_POST_NMS_PER_BATCH: False 28 | RPN_MID_CHANNEL: 512 29 | ROI_HEADS: 30 | USE_FPN: True 31 | POSITIVE_FRACTION: 0.5 32 | BG_IOU_THRESHOLD: 0.3 33 | BATCH_SIZE_PER_IMAGE: 256 34 | DETECTIONS_PER_IMG: 256 35 | ROI_BOX_HEAD: 36 | POOLER_RESOLUTION: 7 37 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 38 | POOLER_SAMPLING_RATIO: 2 39 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 40 | PREDICTOR: "FPNPredictor" 41 | NUM_CLASSES: 151 # 151 for VG, 1201 for GQA 42 | MLP_HEAD_DIM: 4096 43 | ROI_ATTRIBUTE_HEAD: 44 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 45 | PREDICTOR: "FPNPredictor" 46 | USE_BINARY_LOSS: True # choose binary, because cross_entropy loss deteriorate the box head, even with 0.1 weight 47 | POS_WEIGHT: 50.0 48 | ATTRIBUTE_LOSS_WEIGHT: 1.0 49 | NUM_ATTRIBUTES: 201 # 201 for VG, 501 for GQA 50 | MAX_ATTRIBUTES: 10 51 | ATTRIBUTE_BGFG_SAMPLE: True 52 | ATTRIBUTE_BGFG_RATIO: 3 53 | DATASETS: 54 | TRAIN: ("VG_stanford_filtered_with_attribute_train",) 55 | VAL: ("VG_stanford_filtered_with_attribute_val",) 56 | TEST: ("VG_stanford_filtered_with_attribute_test",) 57 | DATALOADER: 58 | SIZE_DIVISIBILITY: 32 59 | SOLVER: 60 | BASE_LR: 0.001 61 | WEIGHT_DECAY: 0.0001 62 | WARMUP_FACTOR: 0.1 63 | MOMENTUM: 0.9 64 | GRAD_NORM_CLIP: 5.0 65 | STEPS: (90000, 120000) 66 | MAX_ITER: 180000 67 | PRINT_GRAD_FREQ: 5000 68 | OUTPUT_DIR: './output/relation_baseline' 69 | 70 | -------------------------------------------------------------------------------- /configs/e2e_relation_detector_VGG16_1x.yaml: -------------------------------------------------------------------------------- 1 | INPUT: 2 | MIN_SIZE_TRAIN: (600,) 3 | MAX_SIZE_TRAIN: 1000 4 | MIN_SIZE_TEST: 600 5 | MAX_SIZE_TEST: 1000 6 | MODEL: 7 | META_ARCHITECTURE: "GeneralizedRCNN" 8 | BACKBONE: 9 | CONV_BODY: "VGG-16" 10 | RESNETS: 11 | BACKBONE_OUT_CHANNELS: 512 12 | RELATION_ON: False 13 | ATTRIBUTE_ON: False 14 | FLIP_AUG: False 15 | RPN: 16 | USE_FPN: False 17 | ANCHOR_SIZES: (32, 64, 128, 256, 512) 18 | ANCHOR_STRIDE: (16,) 19 | ASPECT_RATIOS: (0.23232838, 0.63365731, 1.28478321, 3.15089189) # from neural-motifs 20 | PRE_NMS_TOP_N_TRAIN: 12000 21 | PRE_NMS_TOP_N_TEST: 6000 22 | POST_NMS_TOP_N_TRAIN: 2000 23 | POST_NMS_TOP_N_TEST: 1000 24 | FPN_POST_NMS_TOP_N_TRAIN: 2000 25 | FPN_POST_NMS_TOP_N_TEST: 2000 26 | FPN_POST_NMS_PER_BATCH: False 27 | RPN_MID_CHANNEL: 512 28 | ROI_HEADS: 29 | USE_FPN: True 30 | POSITIVE_FRACTION: 0.5 31 | BG_IOU_THRESHOLD: 0.3 32 | BATCH_SIZE_PER_IMAGE: 256 33 | DETECTIONS_PER_IMG: 256 34 | ROI_BOX_HEAD: 35 | POOLER_RESOLUTION: 7 36 | POOLER_SCALES: (0.0625,) 37 | POOLER_SAMPLING_RATIO: 2 38 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 39 | PREDICTOR: "FPNPredictor" 40 | NUM_CLASSES: 151 # 151 for VG, 1201 for GQA 41 | MLP_HEAD_DIM: 2048 42 | ROI_ATTRIBUTE_HEAD: 43 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 44 | PREDICTOR: "FPNPredictor" 45 | USE_BINARY_LOSS: True # choose binary, because cross_entropy loss deteriorate the box head, even with 0.1 weight 46 | POS_WEIGHT: 50.0 47 | ATTRIBUTE_LOSS_WEIGHT: 1.0 48 | NUM_ATTRIBUTES: 201 # 201 for VG, 501 for GQA 49 | MAX_ATTRIBUTES: 10 50 | ATTRIBUTE_BGFG_SAMPLE: True 51 | ATTRIBUTE_BGFG_RATIO: 3 52 | DATASETS: 53 | TRAIN: ("VG_stanford_filtered_with_attribute_train",) 54 | VAL: ("VG_stanford_filtered_with_attribute_val",) 55 | TEST: ("VG_stanford_filtered_with_attribute_test",) 56 | DATALOADER: 57 | SIZE_DIVISIBILITY: 32 58 | SOLVER: 59 | BASE_LR: 0.001 60 | WEIGHT_DECAY: 0.0001 61 | WARMUP_FACTOR: 0.1 62 | MOMENTUM: 0.9 63 | GRAD_NORM_CLIP: 5.0 64 | STEPS: (30000, 45000) 65 | MAX_ITER: 90000 66 | PRINT_GRAD_FREQ: 5000 67 | OUTPUT_DIR: './output/relation_baseline' 68 | 69 | -------------------------------------------------------------------------------- /configs/e2e_relation_detector_X_101_32_8_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | INPUT: 2 | MIN_SIZE_TRAIN: (600,) 3 | MAX_SIZE_TRAIN: 1000 4 | MIN_SIZE_TEST: 600 5 | MAX_SIZE_TEST: 1000 6 | MODEL: 7 | META_ARCHITECTURE: "GeneralizedRCNN" 8 | WEIGHT: "catalog://ImageNetPretrained/FAIR/20171220/X-101-32x8d" 9 | BACKBONE: 10 | CONV_BODY: "R-101-FPN" 11 | RESNETS: 12 | BACKBONE_OUT_CHANNELS: 256 13 | STRIDE_IN_1X1: False 14 | NUM_GROUPS: 32 15 | WIDTH_PER_GROUP: 8 16 | RELATION_ON: False 17 | ATTRIBUTE_ON: False 18 | FLIP_AUG: False 19 | RPN: 20 | USE_FPN: True 21 | ANCHOR_SIZES: (32, 64, 128, 256, 512) 22 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 23 | ASPECT_RATIOS: (0.23232838, 0.63365731, 1.28478321, 3.15089189) # from neural-motifs 24 | PRE_NMS_TOP_N_TRAIN: 12000 25 | PRE_NMS_TOP_N_TEST: 6000 26 | POST_NMS_TOP_N_TRAIN: 2000 27 | POST_NMS_TOP_N_TEST: 1000 28 | FPN_POST_NMS_TOP_N_TRAIN: 2000 29 | FPN_POST_NMS_TOP_N_TEST: 2000 30 | FPN_POST_NMS_PER_BATCH: False 31 | RPN_MID_CHANNEL: 256 32 | ROI_HEADS: 33 | USE_FPN: True 34 | POSITIVE_FRACTION: 0.5 35 | BG_IOU_THRESHOLD: 0.3 36 | BATCH_SIZE_PER_IMAGE: 256 37 | DETECTIONS_PER_IMG: 256 38 | ROI_BOX_HEAD: 39 | POOLER_RESOLUTION: 7 40 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 41 | POOLER_SAMPLING_RATIO: 2 42 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 43 | PREDICTOR: "FPNPredictor" 44 | NUM_CLASSES: 151 # 151 for VG, 1201 for GQA 45 | MLP_HEAD_DIM: 4096 46 | ROI_ATTRIBUTE_HEAD: 47 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 48 | PREDICTOR: "FPNPredictor" 49 | USE_BINARY_LOSS: True # choose binary, because cross_entropy loss deteriorate the box head, even with 0.1 weight 50 | POS_WEIGHT: 50.0 51 | ATTRIBUTE_LOSS_WEIGHT: 1.0 52 | NUM_ATTRIBUTES: 201 # 201 for VG, 501 for GQA 53 | MAX_ATTRIBUTES: 10 54 | ATTRIBUTE_BGFG_SAMPLE: True 55 | ATTRIBUTE_BGFG_RATIO: 3 56 | DATASETS: 57 | TRAIN: ("VG_stanford_filtered_with_attribute_train",) 58 | VAL: ("VG_stanford_filtered_with_attribute_val",) 59 | TEST: ("VG_stanford_filtered_with_attribute_test",) 60 | DATALOADER: 61 | SIZE_DIVISIBILITY: 32 62 | SOLVER: 63 | BASE_LR: 0.001 64 | WEIGHT_DECAY: 0.0001 65 | WARMUP_FACTOR: 0.1 66 | MOMENTUM: 0.9 67 | GRAD_NORM_CLIP: 5.0 68 | STEPS: (90000, 120000) 69 | MAX_ITER: 180000 70 | PRINT_GRAD_FREQ: 5000 71 | OUTPUT_DIR: './output/relation_baseline' 72 | 73 | -------------------------------------------------------------------------------- /configs/gn_baselines/README.md: -------------------------------------------------------------------------------- 1 | ### Group Normalization 2 | 1 [Group Normalization](https://arxiv.org/abs/1803.08494) 3 | 2 [Rethinking ImageNet Pre-training](https://arxiv.org/abs/1811.08883) 4 | 3 [official code](https://github.com/facebookresearch/Detectron/blob/master/projects/GN/README.md) 5 | 6 | 7 | ### Performance 8 | | case | Type | lr schd | im/gpu | bbox AP | mask AP | 9 | |----------------------------|:------------:|:---------:|:-------:|:-------:|:-------:| 10 | | R-50-FPN, GN (paper) | finetune | 2x | 2 | 40.3 | 35.7 | 11 | | R-50-FPN, GN (implement) | finetune | 2x | 2 | 40.2 | 36.0 | 12 | | R-50-FPN, GN (paper) | from scratch | 3x | 2 | 39.5 | 35.2 | 13 | | R-50-FPN, GN (implement) | from scratch | 3x | 2 | 38.9 | 35.1 | 14 | -------------------------------------------------------------------------------- /configs/gn_baselines/e2e_faster_rcnn_R_50_FPN_1x_gn.yaml: -------------------------------------------------------------------------------- 1 | INPUT: 2 | MIN_SIZE_TRAIN: (800,) 3 | MAX_SIZE_TRAIN: 1333 4 | MIN_SIZE_TEST: 800 5 | MAX_SIZE_TEST: 1333 6 | MODEL: 7 | META_ARCHITECTURE: "GeneralizedRCNN" 8 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50-GN" 9 | BACKBONE: 10 | CONV_BODY: "R-50-FPN" 11 | RESNETS: # use GN for backbone 12 | BACKBONE_OUT_CHANNELS: 256 13 | STRIDE_IN_1X1: False 14 | TRANS_FUNC: "BottleneckWithGN" 15 | STEM_FUNC: "StemWithGN" 16 | FPN: 17 | USE_GN: True # use GN for FPN 18 | RPN: 19 | USE_FPN: True 20 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 21 | PRE_NMS_TOP_N_TRAIN: 2000 22 | PRE_NMS_TOP_N_TEST: 1000 23 | POST_NMS_TOP_N_TEST: 1000 24 | FPN_POST_NMS_TOP_N_TEST: 1000 25 | ROI_HEADS: 26 | USE_FPN: True 27 | BATCH_SIZE_PER_IMAGE: 512 28 | POSITIVE_FRACTION: 0.25 29 | ROI_BOX_HEAD: 30 | USE_GN: True # use GN for bbox head 31 | POOLER_RESOLUTION: 7 32 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 33 | POOLER_SAMPLING_RATIO: 2 34 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 35 | PREDICTOR: "FPNPredictor" 36 | DATASETS: 37 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 38 | TEST: ("coco_2014_minival",) 39 | DATALOADER: 40 | SIZE_DIVISIBILITY: 32 41 | SOLVER: 42 | # Assume 8 gpus 43 | BASE_LR: 0.02 44 | WEIGHT_DECAY: 0.0001 45 | STEPS: (60000, 80000) 46 | MAX_ITER: 90000 47 | IMS_PER_BATCH: 16 48 | TEST: 49 | IMS_PER_BATCH: 8 50 | -------------------------------------------------------------------------------- /configs/gn_baselines/e2e_faster_rcnn_R_50_FPN_Xconv1fc_1x_gn.yaml: -------------------------------------------------------------------------------- 1 | INPUT: 2 | MIN_SIZE_TRAIN: (800,) 3 | MAX_SIZE_TRAIN: 1333 4 | MIN_SIZE_TEST: 800 5 | MAX_SIZE_TEST: 1333 6 | MODEL: 7 | META_ARCHITECTURE: "GeneralizedRCNN" 8 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50-GN" 9 | BACKBONE: 10 | CONV_BODY: "R-50-FPN" 11 | RESNETS: # use GN for backbone 12 | BACKBONE_OUT_CHANNELS: 256 13 | STRIDE_IN_1X1: False 14 | TRANS_FUNC: "BottleneckWithGN" 15 | STEM_FUNC: "StemWithGN" 16 | FPN: 17 | USE_GN: True # use GN for FPN 18 | RPN: 19 | USE_FPN: True 20 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 21 | PRE_NMS_TOP_N_TRAIN: 2000 22 | PRE_NMS_TOP_N_TEST: 1000 23 | POST_NMS_TOP_N_TEST: 1000 24 | FPN_POST_NMS_TOP_N_TEST: 1000 25 | ROI_HEADS: 26 | USE_FPN: True 27 | BATCH_SIZE_PER_IMAGE: 512 28 | POSITIVE_FRACTION: 0.25 29 | ROI_BOX_HEAD: 30 | USE_GN: True # use GN for bbox head 31 | POOLER_RESOLUTION: 7 32 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 33 | POOLER_SAMPLING_RATIO: 2 34 | CONV_HEAD_DIM: 256 35 | NUM_STACKED_CONVS: 4 36 | FEATURE_EXTRACTOR: "FPNXconv1fcFeatureExtractor" 37 | PREDICTOR: "FPNPredictor" 38 | DATASETS: 39 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 40 | TEST: ("coco_2014_minival",) 41 | DATALOADER: 42 | SIZE_DIVISIBILITY: 32 43 | SOLVER: 44 | # Assume 8 gpus 45 | BASE_LR: 0.02 46 | WEIGHT_DECAY: 0.0001 47 | STEPS: (60000, 80000) 48 | MAX_ITER: 90000 49 | IMS_PER_BATCH: 16 50 | TEST: 51 | IMS_PER_BATCH: 8 52 | -------------------------------------------------------------------------------- /configs/gn_baselines/e2e_mask_rcnn_R_50_FPN_1x_gn.yaml: -------------------------------------------------------------------------------- 1 | INPUT: 2 | MIN_SIZE_TRAIN: (800,) 3 | MAX_SIZE_TRAIN: 1333 4 | MIN_SIZE_TEST: 800 5 | MAX_SIZE_TEST: 1333 6 | MODEL: 7 | META_ARCHITECTURE: "GeneralizedRCNN" 8 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50-GN" 9 | BACKBONE: 10 | CONV_BODY: "R-50-FPN" 11 | RESNETS: # use GN for backbone 12 | BACKBONE_OUT_CHANNELS: 256 13 | STRIDE_IN_1X1: False 14 | TRANS_FUNC: "BottleneckWithGN" 15 | STEM_FUNC: "StemWithGN" 16 | FPN: 17 | USE_GN: True # use GN for FPN 18 | RPN: 19 | USE_FPN: True 20 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 21 | PRE_NMS_TOP_N_TRAIN: 2000 22 | PRE_NMS_TOP_N_TEST: 1000 23 | POST_NMS_TOP_N_TEST: 1000 24 | FPN_POST_NMS_TOP_N_TEST: 1000 25 | ROI_HEADS: 26 | USE_FPN: True 27 | BATCH_SIZE_PER_IMAGE: 512 28 | POSITIVE_FRACTION: 0.25 29 | ROI_BOX_HEAD: 30 | USE_GN: True # use GN for bbox head 31 | POOLER_RESOLUTION: 7 32 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 33 | POOLER_SAMPLING_RATIO: 2 34 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 35 | PREDICTOR: "FPNPredictor" 36 | ROI_MASK_HEAD: 37 | USE_GN: True # use GN for mask head 38 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 39 | CONV_LAYERS: (256, 256, 256, 256) 40 | FEATURE_EXTRACTOR: "MaskRCNNFPNFeatureExtractor" 41 | PREDICTOR: "MaskRCNNC4Predictor" 42 | POOLER_RESOLUTION: 14 43 | POOLER_SAMPLING_RATIO: 2 44 | RESOLUTION: 28 45 | SHARE_BOX_FEATURE_EXTRACTOR: False 46 | MASK_ON: True 47 | DATASETS: 48 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 49 | TEST: ("coco_2014_minival",) 50 | DATALOADER: 51 | SIZE_DIVISIBILITY: 32 52 | SOLVER: 53 | # Assume 8 gpus 54 | BASE_LR: 0.02 55 | WEIGHT_DECAY: 0.0001 56 | STEPS: (60000, 80000) 57 | MAX_ITER: 90000 58 | IMS_PER_BATCH: 16 59 | TEST: 60 | IMS_PER_BATCH: 8 61 | -------------------------------------------------------------------------------- /configs/gn_baselines/e2e_mask_rcnn_R_50_FPN_Xconv1fc_1x_gn.yaml: -------------------------------------------------------------------------------- 1 | INPUT: 2 | MIN_SIZE_TRAIN: (800,) 3 | MAX_SIZE_TRAIN: 1333 4 | MIN_SIZE_TEST: 800 5 | MAX_SIZE_TEST: 1333 6 | MODEL: 7 | META_ARCHITECTURE: "GeneralizedRCNN" 8 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50-GN" 9 | BACKBONE: 10 | CONV_BODY: "R-50-FPN" 11 | RESNETS: # use GN for backbone 12 | BACKBONE_OUT_CHANNELS: 256 13 | STRIDE_IN_1X1: False 14 | TRANS_FUNC: "BottleneckWithGN" 15 | STEM_FUNC: "StemWithGN" 16 | FPN: 17 | USE_GN: True # use GN for FPN 18 | RPN: 19 | USE_FPN: True 20 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 21 | PRE_NMS_TOP_N_TRAIN: 2000 22 | PRE_NMS_TOP_N_TEST: 1000 23 | POST_NMS_TOP_N_TEST: 1000 24 | FPN_POST_NMS_TOP_N_TEST: 1000 25 | ROI_HEADS: 26 | USE_FPN: True 27 | BATCH_SIZE_PER_IMAGE: 512 28 | POSITIVE_FRACTION: 0.25 29 | ROI_BOX_HEAD: 30 | USE_GN: True # use GN for bbox head 31 | POOLER_RESOLUTION: 7 32 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 33 | POOLER_SAMPLING_RATIO: 2 34 | CONV_HEAD_DIM: 256 35 | NUM_STACKED_CONVS: 4 36 | FEATURE_EXTRACTOR: "FPNXconv1fcFeatureExtractor" 37 | PREDICTOR: "FPNPredictor" 38 | ROI_MASK_HEAD: 39 | USE_GN: True # use GN for mask head 40 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 41 | CONV_LAYERS: (256, 256, 256, 256) 42 | FEATURE_EXTRACTOR: "MaskRCNNFPNFeatureExtractor" 43 | PREDICTOR: "MaskRCNNC4Predictor" 44 | POOLER_RESOLUTION: 14 45 | POOLER_SAMPLING_RATIO: 2 46 | RESOLUTION: 28 47 | SHARE_BOX_FEATURE_EXTRACTOR: False 48 | MASK_ON: True 49 | DATASETS: 50 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 51 | TEST: ("coco_2014_minival",) 52 | DATALOADER: 53 | SIZE_DIVISIBILITY: 32 54 | SOLVER: 55 | # Assume 8 gpus 56 | BASE_LR: 0.02 57 | WEIGHT_DECAY: 0.0001 58 | STEPS: (60000, 80000) 59 | MAX_ITER: 90000 60 | IMS_PER_BATCH: 16 61 | TEST: 62 | IMS_PER_BATCH: 8 63 | -------------------------------------------------------------------------------- /configs/gn_baselines/scratch_e2e_faster_rcnn_R_50_FPN_3x_gn.yaml: -------------------------------------------------------------------------------- 1 | INPUT: 2 | MIN_SIZE_TRAIN: (800,) 3 | MAX_SIZE_TRAIN: 1333 4 | MIN_SIZE_TEST: 800 5 | MAX_SIZE_TEST: 1333 6 | MODEL: 7 | META_ARCHITECTURE: "GeneralizedRCNN" 8 | WEIGHT: "" # no pretrained model 9 | BACKBONE: 10 | CONV_BODY: "R-50-FPN" 11 | FREEZE_CONV_BODY_AT: 0 # finetune all layers 12 | RESNETS: # use GN for backbone 13 | BACKBONE_OUT_CHANNELS: 256 14 | STRIDE_IN_1X1: False 15 | TRANS_FUNC: "BottleneckWithGN" 16 | STEM_FUNC: "StemWithGN" 17 | FPN: 18 | USE_GN: True # use GN for FPN 19 | RPN: 20 | USE_FPN: True 21 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 22 | PRE_NMS_TOP_N_TRAIN: 2000 23 | PRE_NMS_TOP_N_TEST: 1000 24 | POST_NMS_TOP_N_TEST: 1000 25 | FPN_POST_NMS_TOP_N_TEST: 1000 26 | ROI_HEADS: 27 | USE_FPN: True 28 | BATCH_SIZE_PER_IMAGE: 512 29 | POSITIVE_FRACTION: 0.25 30 | ROI_BOX_HEAD: 31 | USE_GN: True # use GN for bbox head 32 | POOLER_RESOLUTION: 7 33 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 34 | POOLER_SAMPLING_RATIO: 2 35 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 36 | PREDICTOR: "FPNPredictor" 37 | DATASETS: 38 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 39 | TEST: ("coco_2014_minival",) 40 | DATALOADER: 41 | SIZE_DIVISIBILITY: 32 42 | SOLVER: 43 | # Assume 8 gpus 44 | BASE_LR: 0.02 45 | WEIGHT_DECAY: 0.0001 46 | STEPS: (210000, 250000) 47 | MAX_ITER: 270000 48 | IMS_PER_BATCH: 16 49 | TEST: 50 | IMS_PER_BATCH: 8 51 | -------------------------------------------------------------------------------- /configs/gn_baselines/scratch_e2e_faster_rcnn_R_50_FPN_Xconv1fc_3x_gn.yaml: -------------------------------------------------------------------------------- 1 | INPUT: 2 | MIN_SIZE_TRAIN: (800,) 3 | MAX_SIZE_TRAIN: 1333 4 | MIN_SIZE_TEST: 800 5 | MAX_SIZE_TEST: 1333 6 | MODEL: 7 | META_ARCHITECTURE: "GeneralizedRCNN" 8 | WEIGHT: "" # no pretrained model 9 | BACKBONE: 10 | CONV_BODY: "R-50-FPN" 11 | FREEZE_CONV_BODY_AT: 0 # finetune all layers 12 | RESNETS: # use GN for backbone 13 | BACKBONE_OUT_CHANNELS: 256 14 | STRIDE_IN_1X1: False 15 | TRANS_FUNC: "BottleneckWithGN" 16 | STEM_FUNC: "StemWithGN" 17 | FPN: 18 | USE_GN: True # use GN for FPN 19 | RPN: 20 | USE_FPN: True 21 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 22 | PRE_NMS_TOP_N_TRAIN: 2000 23 | PRE_NMS_TOP_N_TEST: 1000 24 | POST_NMS_TOP_N_TEST: 1000 25 | FPN_POST_NMS_TOP_N_TEST: 1000 26 | ROI_HEADS: 27 | USE_FPN: True 28 | BATCH_SIZE_PER_IMAGE: 512 29 | POSITIVE_FRACTION: 0.25 30 | ROI_BOX_HEAD: 31 | USE_GN: True # use GN for bbox head 32 | POOLER_RESOLUTION: 7 33 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 34 | POOLER_SAMPLING_RATIO: 2 35 | CONV_HEAD_DIM: 256 36 | NUM_STACKED_CONVS: 4 37 | FEATURE_EXTRACTOR: "FPNXconv1fcFeatureExtractor" 38 | PREDICTOR: "FPNPredictor" 39 | DATASETS: 40 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 41 | TEST: ("coco_2014_minival",) 42 | DATALOADER: 43 | SIZE_DIVISIBILITY: 32 44 | SOLVER: 45 | # Assume 8 gpus 46 | BASE_LR: 0.02 47 | WEIGHT_DECAY: 0.0001 48 | STEPS: (210000, 250000) 49 | MAX_ITER: 270000 50 | IMS_PER_BATCH: 16 51 | TEST: 52 | IMS_PER_BATCH: 8 53 | -------------------------------------------------------------------------------- /configs/gn_baselines/scratch_e2e_mask_rcnn_R_50_FPN_3x_gn.yaml: -------------------------------------------------------------------------------- 1 | INPUT: 2 | MIN_SIZE_TRAIN: (800,) 3 | MAX_SIZE_TRAIN: 1333 4 | MIN_SIZE_TEST: 800 5 | MAX_SIZE_TEST: 1333 6 | MODEL: 7 | META_ARCHITECTURE: "GeneralizedRCNN" 8 | WEIGHT: "" # no pretrained model 9 | BACKBONE: 10 | CONV_BODY: "R-50-FPN" 11 | FREEZE_CONV_BODY_AT: 0 # finetune all layers 12 | RESNETS: # use GN for backbone 13 | BACKBONE_OUT_CHANNELS: 256 14 | STRIDE_IN_1X1: False 15 | TRANS_FUNC: "BottleneckWithGN" 16 | STEM_FUNC: "StemWithGN" 17 | FPN: 18 | USE_GN: True # use GN for FPN 19 | RPN: 20 | USE_FPN: True 21 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 22 | PRE_NMS_TOP_N_TRAIN: 2000 23 | PRE_NMS_TOP_N_TEST: 1000 24 | POST_NMS_TOP_N_TEST: 1000 25 | FPN_POST_NMS_TOP_N_TEST: 1000 26 | ROI_HEADS: 27 | USE_FPN: True 28 | BATCH_SIZE_PER_IMAGE: 512 29 | POSITIVE_FRACTION: 0.25 30 | ROI_BOX_HEAD: 31 | USE_GN: True # use GN for bbox head 32 | POOLER_RESOLUTION: 7 33 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 34 | POOLER_SAMPLING_RATIO: 2 35 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 36 | PREDICTOR: "FPNPredictor" 37 | ROI_MASK_HEAD: 38 | USE_GN: True # use GN for mask head 39 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 40 | CONV_LAYERS: (256, 256, 256, 256) 41 | FEATURE_EXTRACTOR: "MaskRCNNFPNFeatureExtractor" 42 | PREDICTOR: "MaskRCNNC4Predictor" 43 | POOLER_RESOLUTION: 14 44 | POOLER_SAMPLING_RATIO: 2 45 | RESOLUTION: 28 46 | SHARE_BOX_FEATURE_EXTRACTOR: False 47 | MASK_ON: True 48 | DATASETS: 49 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 50 | TEST: ("coco_2014_minival",) 51 | DATALOADER: 52 | SIZE_DIVISIBILITY: 32 53 | SOLVER: 54 | # Assume 8 gpus 55 | BASE_LR: 0.02 56 | WEIGHT_DECAY: 0.0001 57 | STEPS: (210000, 250000) 58 | MAX_ITER: 270000 59 | IMS_PER_BATCH: 16 60 | TEST: 61 | IMS_PER_BATCH: 8 62 | -------------------------------------------------------------------------------- /configs/gn_baselines/scratch_e2e_mask_rcnn_R_50_FPN_Xconv1fc_3x_gn.yaml: -------------------------------------------------------------------------------- 1 | INPUT: 2 | MIN_SIZE_TRAIN: (800,) 3 | MAX_SIZE_TRAIN: 1333 4 | MIN_SIZE_TEST: 800 5 | MAX_SIZE_TEST: 1333 6 | MODEL: 7 | META_ARCHITECTURE: "GeneralizedRCNN" 8 | WEIGHT: "" # no pretrained model 9 | BACKBONE: 10 | CONV_BODY: "R-50-FPN" 11 | FREEZE_CONV_BODY_AT: 0 # finetune all layers 12 | RESNETS: # use GN for backbone 13 | BACKBONE_OUT_CHANNELS: 256 14 | STRIDE_IN_1X1: False 15 | TRANS_FUNC: "BottleneckWithGN" 16 | STEM_FUNC: "StemWithGN" 17 | FPN: 18 | USE_GN: True # use GN for FPN 19 | RPN: 20 | USE_FPN: True 21 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 22 | PRE_NMS_TOP_N_TRAIN: 2000 23 | PRE_NMS_TOP_N_TEST: 1000 24 | POST_NMS_TOP_N_TEST: 1000 25 | FPN_POST_NMS_TOP_N_TEST: 1000 26 | ROI_HEADS: 27 | USE_FPN: True 28 | BATCH_SIZE_PER_IMAGE: 512 29 | POSITIVE_FRACTION: 0.25 30 | ROI_BOX_HEAD: 31 | USE_GN: True # use GN for bbox head 32 | POOLER_RESOLUTION: 7 33 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 34 | POOLER_SAMPLING_RATIO: 2 35 | CONV_HEAD_DIM: 256 36 | NUM_STACKED_CONVS: 4 37 | FEATURE_EXTRACTOR: "FPNXconv1fcFeatureExtractor" 38 | PREDICTOR: "FPNPredictor" 39 | ROI_MASK_HEAD: 40 | USE_GN: True # use GN for mask head 41 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 42 | CONV_LAYERS: (256, 256, 256, 256) 43 | FEATURE_EXTRACTOR: "MaskRCNNFPNFeatureExtractor" 44 | PREDICTOR: "MaskRCNNC4Predictor" 45 | POOLER_RESOLUTION: 14 46 | POOLER_SAMPLING_RATIO: 2 47 | RESOLUTION: 28 48 | SHARE_BOX_FEATURE_EXTRACTOR: False 49 | MASK_ON: True 50 | DATASETS: 51 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 52 | TEST: ("coco_2014_minival",) 53 | DATALOADER: 54 | SIZE_DIVISIBILITY: 32 55 | SOLVER: 56 | # Assume 8 gpus 57 | BASE_LR: 0.02 58 | WEIGHT_DECAY: 0.0001 59 | STEPS: (210000, 250000) 60 | MAX_ITER: 270000 61 | IMS_PER_BATCH: 16 62 | TEST: 63 | IMS_PER_BATCH: 8 64 | -------------------------------------------------------------------------------- /configs/maskrcnn_benchmark_models/e2e_faster_rcnn_R_101_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-101" 4 | BACKBONE: 5 | CONV_BODY: "R-101-FPN" 6 | RESNETS: 7 | BACKBONE_OUT_CHANNELS: 256 8 | RPN: 9 | USE_FPN: True 10 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 11 | PRE_NMS_TOP_N_TRAIN: 2000 12 | PRE_NMS_TOP_N_TEST: 1000 13 | POST_NMS_TOP_N_TEST: 1000 14 | FPN_POST_NMS_TOP_N_TEST: 1000 15 | ROI_HEADS: 16 | USE_FPN: True 17 | ROI_BOX_HEAD: 18 | POOLER_RESOLUTION: 7 19 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 20 | POOLER_SAMPLING_RATIO: 2 21 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 22 | PREDICTOR: "FPNPredictor" 23 | DATASETS: 24 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 25 | TEST: ("coco_2014_minival",) 26 | DATALOADER: 27 | SIZE_DIVISIBILITY: 32 28 | SOLVER: 29 | BASE_LR: 0.02 30 | WEIGHT_DECAY: 0.0001 31 | STEPS: (60000, 80000) 32 | MAX_ITER: 90000 33 | -------------------------------------------------------------------------------- /configs/maskrcnn_benchmark_models/e2e_faster_rcnn_R_50_C4_1x.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 4 | RPN: 5 | PRE_NMS_TOP_N_TEST: 6000 6 | POST_NMS_TOP_N_TEST: 1000 7 | DATASETS: 8 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 9 | TEST: ("coco_2014_minival",) 10 | SOLVER: 11 | BASE_LR: 0.01 12 | WEIGHT_DECAY: 0.0001 13 | STEPS: (120000, 160000) 14 | MAX_ITER: 180000 15 | IMS_PER_BATCH: 8 16 | -------------------------------------------------------------------------------- /configs/maskrcnn_benchmark_models/e2e_faster_rcnn_R_50_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 4 | BACKBONE: 5 | CONV_BODY: "R-50-FPN" 6 | RESNETS: 7 | BACKBONE_OUT_CHANNELS: 256 8 | RPN: 9 | USE_FPN: True 10 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 11 | PRE_NMS_TOP_N_TRAIN: 2000 12 | PRE_NMS_TOP_N_TEST: 1000 13 | POST_NMS_TOP_N_TEST: 1000 14 | FPN_POST_NMS_TOP_N_TEST: 1000 15 | ROI_HEADS: 16 | USE_FPN: True 17 | ROI_BOX_HEAD: 18 | POOLER_RESOLUTION: 7 19 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 20 | POOLER_SAMPLING_RATIO: 2 21 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 22 | PREDICTOR: "FPNPredictor" 23 | DATASETS: 24 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 25 | TEST: ("coco_2014_minival",) 26 | DATALOADER: 27 | SIZE_DIVISIBILITY: 32 28 | SOLVER: 29 | BASE_LR: 0.02 30 | WEIGHT_DECAY: 0.0001 31 | STEPS: (60000, 80000) 32 | MAX_ITER: 90000 33 | -------------------------------------------------------------------------------- /configs/maskrcnn_benchmark_models/e2e_faster_rcnn_X_101_32x8d_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/FAIR/20171220/X-101-32x8d" 4 | BACKBONE: 5 | CONV_BODY: "R-101-FPN" 6 | RPN: 7 | USE_FPN: True 8 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 9 | PRE_NMS_TOP_N_TRAIN: 2000 10 | PRE_NMS_TOP_N_TEST: 1000 11 | POST_NMS_TOP_N_TEST: 1000 12 | FPN_POST_NMS_TOP_N_TEST: 1000 13 | ROI_HEADS: 14 | USE_FPN: True 15 | ROI_BOX_HEAD: 16 | POOLER_RESOLUTION: 7 17 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 18 | POOLER_SAMPLING_RATIO: 2 19 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 20 | PREDICTOR: "FPNPredictor" 21 | RESNETS: 22 | BACKBONE_OUT_CHANNELS: 256 23 | STRIDE_IN_1X1: False 24 | NUM_GROUPS: 32 25 | WIDTH_PER_GROUP: 8 26 | DATASETS: 27 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 28 | TEST: ("coco_2014_minival",) 29 | DATALOADER: 30 | SIZE_DIVISIBILITY: 32 31 | SOLVER: 32 | BASE_LR: 0.01 33 | WEIGHT_DECAY: 0.0001 34 | STEPS: (120000, 160000) 35 | MAX_ITER: 180000 36 | IMS_PER_BATCH: 8 37 | -------------------------------------------------------------------------------- /configs/maskrcnn_benchmark_models/e2e_faster_rcnn_fbnet.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | BACKBONE: 4 | CONV_BODY: FBNet 5 | FBNET: 6 | ARCH: "default" 7 | BN_TYPE: "bn" 8 | WIDTH_DIVISOR: 8 9 | DW_CONV_SKIP_BN: True 10 | DW_CONV_SKIP_RELU: True 11 | RPN: 12 | ANCHOR_SIZES: (16, 32, 64, 128, 256) 13 | ANCHOR_STRIDE: (16, ) 14 | BATCH_SIZE_PER_IMAGE: 256 15 | PRE_NMS_TOP_N_TRAIN: 6000 16 | PRE_NMS_TOP_N_TEST: 6000 17 | POST_NMS_TOP_N_TRAIN: 2000 18 | POST_NMS_TOP_N_TEST: 100 19 | RPN_HEAD: FBNet.rpn_head 20 | ROI_HEADS: 21 | BATCH_SIZE_PER_IMAGE: 512 22 | ROI_BOX_HEAD: 23 | POOLER_RESOLUTION: 6 24 | FEATURE_EXTRACTOR: FBNet.roi_head 25 | NUM_CLASSES: 81 26 | DATASETS: 27 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 28 | TEST: ("coco_2014_minival",) 29 | SOLVER: 30 | BASE_LR: 0.06 31 | WARMUP_FACTOR: 0.1 32 | WEIGHT_DECAY: 0.0001 33 | STEPS: (60000, 80000) 34 | MAX_ITER: 90000 35 | IMS_PER_BATCH: 128 # for 8GPUs 36 | # TEST: 37 | # IMS_PER_BATCH: 8 38 | INPUT: 39 | MIN_SIZE_TRAIN: (320, ) 40 | MAX_SIZE_TRAIN: 640 41 | MIN_SIZE_TEST: 320 42 | MAX_SIZE_TEST: 640 43 | PIXEL_MEAN: [103.53, 116.28, 123.675] 44 | PIXEL_STD: [57.375, 57.12, 58.395] 45 | -------------------------------------------------------------------------------- /configs/maskrcnn_benchmark_models/e2e_faster_rcnn_fbnet_600.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | BACKBONE: 4 | CONV_BODY: FBNet 5 | FBNET: 6 | ARCH: "default" 7 | BN_TYPE: "bn" 8 | WIDTH_DIVISOR: 8 9 | DW_CONV_SKIP_BN: True 10 | DW_CONV_SKIP_RELU: True 11 | RPN: 12 | ANCHOR_SIZES: (32, 64, 128, 256, 512) 13 | ANCHOR_STRIDE: (16, ) 14 | BATCH_SIZE_PER_IMAGE: 256 15 | PRE_NMS_TOP_N_TRAIN: 6000 16 | PRE_NMS_TOP_N_TEST: 6000 17 | POST_NMS_TOP_N_TRAIN: 2000 18 | POST_NMS_TOP_N_TEST: 200 19 | RPN_HEAD: FBNet.rpn_head 20 | ROI_HEADS: 21 | BATCH_SIZE_PER_IMAGE: 256 22 | ROI_BOX_HEAD: 23 | POOLER_RESOLUTION: 6 24 | FEATURE_EXTRACTOR: FBNet.roi_head 25 | NUM_CLASSES: 81 26 | DATASETS: 27 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 28 | TEST: ("coco_2014_minival",) 29 | SOLVER: 30 | BASE_LR: 0.06 31 | WARMUP_FACTOR: 0.1 32 | WEIGHT_DECAY: 0.0001 33 | STEPS: (60000, 80000) 34 | MAX_ITER: 90000 35 | IMS_PER_BATCH: 128 # for 8GPUs 36 | # TEST: 37 | # IMS_PER_BATCH: 8 38 | INPUT: 39 | MIN_SIZE_TRAIN: (600, ) 40 | MAX_SIZE_TRAIN: 1000 41 | MIN_SIZE_TEST: 600 42 | MAX_SIZE_TEST: 1000 43 | PIXEL_MEAN: [103.53, 116.28, 123.675] 44 | PIXEL_STD: [57.375, 57.12, 58.395] 45 | -------------------------------------------------------------------------------- /configs/maskrcnn_benchmark_models/e2e_faster_rcnn_fbnet_chamv1a_600.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | BACKBONE: 4 | CONV_BODY: FBNet 5 | FBNET: 6 | ARCH: "cham_v1a" 7 | BN_TYPE: "bn" 8 | WIDTH_DIVISOR: 8 9 | DW_CONV_SKIP_BN: True 10 | DW_CONV_SKIP_RELU: True 11 | RPN: 12 | ANCHOR_SIZES: (32, 64, 128, 256, 512) 13 | ANCHOR_STRIDE: (16, ) 14 | BATCH_SIZE_PER_IMAGE: 256 15 | PRE_NMS_TOP_N_TRAIN: 6000 16 | PRE_NMS_TOP_N_TEST: 6000 17 | POST_NMS_TOP_N_TRAIN: 2000 18 | POST_NMS_TOP_N_TEST: 200 19 | RPN_HEAD: FBNet.rpn_head 20 | ROI_HEADS: 21 | BATCH_SIZE_PER_IMAGE: 128 22 | ROI_BOX_HEAD: 23 | POOLER_RESOLUTION: 6 24 | FEATURE_EXTRACTOR: FBNet.roi_head 25 | NUM_CLASSES: 81 26 | DATASETS: 27 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 28 | TEST: ("coco_2014_minival",) 29 | SOLVER: 30 | BASE_LR: 0.045 31 | WARMUP_FACTOR: 0.1 32 | WEIGHT_DECAY: 0.0001 33 | STEPS: (90000, 120000) 34 | MAX_ITER: 135000 35 | IMS_PER_BATCH: 96 # for 8GPUs 36 | # TEST: 37 | # IMS_PER_BATCH: 8 38 | INPUT: 39 | MIN_SIZE_TRAIN: (600, ) 40 | MAX_SIZE_TRAIN: 1000 41 | MIN_SIZE_TEST: 600 42 | MAX_SIZE_TEST: 1000 43 | PIXEL_MEAN: [103.53, 116.28, 123.675] 44 | PIXEL_STD: [57.375, 57.12, 58.395] 45 | -------------------------------------------------------------------------------- /configs/maskrcnn_benchmark_models/e2e_keypoint_rcnn_R_50_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 4 | BACKBONE: 5 | CONV_BODY: "R-50-FPN" 6 | RESNETS: 7 | BACKBONE_OUT_CHANNELS: 256 8 | RPN: 9 | USE_FPN: True 10 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 11 | PRE_NMS_TOP_N_TRAIN: 2000 12 | PRE_NMS_TOP_N_TEST: 1000 13 | POST_NMS_TOP_N_TEST: 1000 14 | FPN_POST_NMS_TOP_N_TEST: 1000 15 | ROI_HEADS: 16 | USE_FPN: True 17 | ROI_BOX_HEAD: 18 | POOLER_RESOLUTION: 7 19 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 20 | POOLER_SAMPLING_RATIO: 2 21 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 22 | PREDICTOR: "FPNPredictor" 23 | NUM_CLASSES: 2 24 | ROI_KEYPOINT_HEAD: 25 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 26 | FEATURE_EXTRACTOR: "KeypointRCNNFeatureExtractor" 27 | PREDICTOR: "KeypointRCNNPredictor" 28 | POOLER_RESOLUTION: 14 29 | POOLER_SAMPLING_RATIO: 2 30 | RESOLUTION: 56 31 | SHARE_BOX_FEATURE_EXTRACTOR: False 32 | KEYPOINT_ON: True 33 | DATASETS: 34 | TRAIN: ("keypoints_coco_2014_train", "keypoints_coco_2014_valminusminival",) 35 | TEST: ("keypoints_coco_2014_minival",) 36 | INPUT: 37 | MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800) 38 | DATALOADER: 39 | SIZE_DIVISIBILITY: 32 40 | SOLVER: 41 | BASE_LR: 0.02 42 | WEIGHT_DECAY: 0.0001 43 | STEPS: (60000, 80000) 44 | MAX_ITER: 90000 45 | -------------------------------------------------------------------------------- /configs/maskrcnn_benchmark_models/e2e_mask_rcnn_R_101_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-101" 4 | BACKBONE: 5 | CONV_BODY: "R-101-FPN" 6 | RESNETS: 7 | BACKBONE_OUT_CHANNELS: 256 8 | RPN: 9 | USE_FPN: True 10 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 11 | PRE_NMS_TOP_N_TRAIN: 2000 12 | PRE_NMS_TOP_N_TEST: 1000 13 | POST_NMS_TOP_N_TEST: 1000 14 | FPN_POST_NMS_TOP_N_TEST: 1000 15 | ROI_HEADS: 16 | USE_FPN: True 17 | ROI_BOX_HEAD: 18 | POOLER_RESOLUTION: 7 19 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 20 | POOLER_SAMPLING_RATIO: 2 21 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 22 | PREDICTOR: "FPNPredictor" 23 | ROI_MASK_HEAD: 24 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 25 | FEATURE_EXTRACTOR: "MaskRCNNFPNFeatureExtractor" 26 | PREDICTOR: "MaskRCNNC4Predictor" 27 | POOLER_RESOLUTION: 14 28 | POOLER_SAMPLING_RATIO: 2 29 | RESOLUTION: 28 30 | SHARE_BOX_FEATURE_EXTRACTOR: False 31 | MASK_ON: True 32 | DATASETS: 33 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 34 | TEST: ("coco_2014_minival",) 35 | DATALOADER: 36 | SIZE_DIVISIBILITY: 32 37 | SOLVER: 38 | BASE_LR: 0.02 39 | WEIGHT_DECAY: 0.0001 40 | STEPS: (60000, 80000) 41 | MAX_ITER: 90000 42 | -------------------------------------------------------------------------------- /configs/maskrcnn_benchmark_models/e2e_mask_rcnn_R_50_C4_1x.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 4 | RPN: 5 | PRE_NMS_TOP_N_TEST: 6000 6 | POST_NMS_TOP_N_TEST: 1000 7 | ROI_MASK_HEAD: 8 | PREDICTOR: "MaskRCNNC4Predictor" 9 | SHARE_BOX_FEATURE_EXTRACTOR: True 10 | MASK_ON: True 11 | DATASETS: 12 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 13 | TEST: ("coco_2014_minival",) 14 | SOLVER: 15 | BASE_LR: 0.01 16 | WEIGHT_DECAY: 0.0001 17 | STEPS: (120000, 160000) 18 | MAX_ITER: 180000 19 | IMS_PER_BATCH: 8 20 | -------------------------------------------------------------------------------- /configs/maskrcnn_benchmark_models/e2e_mask_rcnn_R_50_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 4 | BACKBONE: 5 | CONV_BODY: "R-50-FPN" 6 | RESNETS: 7 | BACKBONE_OUT_CHANNELS: 256 8 | RPN: 9 | USE_FPN: True 10 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 11 | PRE_NMS_TOP_N_TRAIN: 2000 12 | PRE_NMS_TOP_N_TEST: 1000 13 | POST_NMS_TOP_N_TEST: 1000 14 | FPN_POST_NMS_TOP_N_TEST: 1000 15 | ROI_HEADS: 16 | USE_FPN: True 17 | ROI_BOX_HEAD: 18 | POOLER_RESOLUTION: 7 19 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 20 | POOLER_SAMPLING_RATIO: 2 21 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 22 | PREDICTOR: "FPNPredictor" 23 | ROI_MASK_HEAD: 24 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 25 | FEATURE_EXTRACTOR: "MaskRCNNFPNFeatureExtractor" 26 | PREDICTOR: "MaskRCNNC4Predictor" 27 | POOLER_RESOLUTION: 14 28 | POOLER_SAMPLING_RATIO: 2 29 | RESOLUTION: 28 30 | SHARE_BOX_FEATURE_EXTRACTOR: False 31 | MASK_ON: True 32 | DATASETS: 33 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 34 | TEST: ("coco_2014_minival",) 35 | DATALOADER: 36 | SIZE_DIVISIBILITY: 32 37 | SOLVER: 38 | BASE_LR: 0.02 39 | WEIGHT_DECAY: 0.0001 40 | STEPS: (60000, 80000) 41 | MAX_ITER: 90000 42 | -------------------------------------------------------------------------------- /configs/maskrcnn_benchmark_models/e2e_mask_rcnn_X_101_32x8d_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/FAIR/20171220/X-101-32x8d" 4 | BACKBONE: 5 | CONV_BODY: "R-101-FPN" 6 | RESNETS: 7 | BACKBONE_OUT_CHANNELS: 256 8 | STRIDE_IN_1X1: False 9 | NUM_GROUPS: 32 10 | WIDTH_PER_GROUP: 8 11 | RPN: 12 | USE_FPN: True 13 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 14 | PRE_NMS_TOP_N_TRAIN: 2000 15 | PRE_NMS_TOP_N_TEST: 1000 16 | POST_NMS_TOP_N_TEST: 1000 17 | FPN_POST_NMS_TOP_N_TEST: 1000 18 | ROI_HEADS: 19 | USE_FPN: True 20 | ROI_BOX_HEAD: 21 | POOLER_RESOLUTION: 7 22 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 23 | POOLER_SAMPLING_RATIO: 2 24 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 25 | PREDICTOR: "FPNPredictor" 26 | ROI_MASK_HEAD: 27 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 28 | FEATURE_EXTRACTOR: "MaskRCNNFPNFeatureExtractor" 29 | PREDICTOR: "MaskRCNNC4Predictor" 30 | POOLER_RESOLUTION: 14 31 | POOLER_SAMPLING_RATIO: 2 32 | RESOLUTION: 28 33 | SHARE_BOX_FEATURE_EXTRACTOR: False 34 | MASK_ON: True 35 | DATASETS: 36 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 37 | TEST: ("coco_2014_minival",) 38 | DATALOADER: 39 | SIZE_DIVISIBILITY: 32 40 | SOLVER: 41 | BASE_LR: 0.01 42 | WEIGHT_DECAY: 0.0001 43 | STEPS: (120000, 160000) 44 | MAX_ITER: 180000 45 | IMS_PER_BATCH: 8 46 | -------------------------------------------------------------------------------- /configs/maskrcnn_benchmark_models/e2e_mask_rcnn_fbnet.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | BACKBONE: 4 | CONV_BODY: FBNet 5 | FBNET: 6 | ARCH: "default" 7 | BN_TYPE: "bn" 8 | WIDTH_DIVISOR: 8 9 | DW_CONV_SKIP_BN: True 10 | DW_CONV_SKIP_RELU: True 11 | DET_HEAD_LAST_SCALE: 0.0 12 | RPN: 13 | ANCHOR_SIZES: (16, 32, 64, 128, 256) 14 | ANCHOR_STRIDE: (16, ) 15 | BATCH_SIZE_PER_IMAGE: 256 16 | PRE_NMS_TOP_N_TRAIN: 6000 17 | PRE_NMS_TOP_N_TEST: 6000 18 | POST_NMS_TOP_N_TRAIN: 2000 19 | POST_NMS_TOP_N_TEST: 100 20 | RPN_HEAD: FBNet.rpn_head 21 | ROI_HEADS: 22 | BATCH_SIZE_PER_IMAGE: 256 23 | ROI_BOX_HEAD: 24 | POOLER_RESOLUTION: 6 25 | FEATURE_EXTRACTOR: FBNet.roi_head 26 | NUM_CLASSES: 81 27 | ROI_MASK_HEAD: 28 | POOLER_RESOLUTION: 6 29 | FEATURE_EXTRACTOR: FBNet.roi_head_mask 30 | PREDICTOR: "MaskRCNNConv1x1Predictor" 31 | RESOLUTION: 12 32 | SHARE_BOX_FEATURE_EXTRACTOR: False 33 | MASK_ON: True 34 | DATASETS: 35 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 36 | TEST: ("coco_2014_minival",) 37 | SOLVER: 38 | BASE_LR: 0.06 39 | WARMUP_FACTOR: 0.1 40 | WEIGHT_DECAY: 0.0001 41 | STEPS: (60000, 80000) 42 | MAX_ITER: 90000 43 | IMS_PER_BATCH: 128 # for 8GPUs 44 | # TEST: 45 | # IMS_PER_BATCH: 8 46 | INPUT: 47 | MIN_SIZE_TRAIN: (320, ) 48 | MAX_SIZE_TRAIN: 640 49 | MIN_SIZE_TEST: 320 50 | MAX_SIZE_TEST: 640 51 | PIXEL_MEAN: [103.53, 116.28, 123.675] 52 | PIXEL_STD: [57.375, 57.12, 58.395] 53 | -------------------------------------------------------------------------------- /configs/maskrcnn_benchmark_models/e2e_mask_rcnn_fbnet_600.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | BACKBONE: 4 | CONV_BODY: FBNet 5 | FBNET: 6 | ARCH: "default" 7 | BN_TYPE: "bn" 8 | WIDTH_DIVISOR: 8 9 | DW_CONV_SKIP_BN: True 10 | DW_CONV_SKIP_RELU: True 11 | DET_HEAD_LAST_SCALE: 0.0 12 | RPN: 13 | ANCHOR_SIZES: (32, 64, 128, 256, 512) 14 | ANCHOR_STRIDE: (16, ) 15 | BATCH_SIZE_PER_IMAGE: 256 16 | PRE_NMS_TOP_N_TRAIN: 6000 17 | PRE_NMS_TOP_N_TEST: 6000 18 | POST_NMS_TOP_N_TRAIN: 2000 19 | POST_NMS_TOP_N_TEST: 200 20 | RPN_HEAD: FBNet.rpn_head 21 | ROI_HEADS: 22 | BATCH_SIZE_PER_IMAGE: 256 23 | ROI_BOX_HEAD: 24 | POOLER_RESOLUTION: 6 25 | FEATURE_EXTRACTOR: FBNet.roi_head 26 | NUM_CLASSES: 81 27 | ROI_MASK_HEAD: 28 | POOLER_RESOLUTION: 6 29 | FEATURE_EXTRACTOR: FBNet.roi_head_mask 30 | PREDICTOR: "MaskRCNNConv1x1Predictor" 31 | RESOLUTION: 12 32 | SHARE_BOX_FEATURE_EXTRACTOR: False 33 | MASK_ON: True 34 | DATASETS: 35 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 36 | TEST: ("coco_2014_minival",) 37 | SOLVER: 38 | BASE_LR: 0.06 39 | WARMUP_FACTOR: 0.1 40 | WEIGHT_DECAY: 0.0001 41 | STEPS: (60000, 80000) 42 | MAX_ITER: 90000 43 | IMS_PER_BATCH: 128 # for 8GPUs 44 | # TEST: 45 | # IMS_PER_BATCH: 8 46 | INPUT: 47 | MIN_SIZE_TRAIN: (600, ) 48 | MAX_SIZE_TRAIN: 1000 49 | MIN_SIZE_TEST: 600 50 | MAX_SIZE_TEST: 1000 51 | PIXEL_MEAN: [103.53, 116.28, 123.675] 52 | PIXEL_STD: [57.375, 57.12, 58.395] 53 | -------------------------------------------------------------------------------- /configs/maskrcnn_benchmark_models/e2e_mask_rcnn_fbnet_xirb16d_dsmask.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | BACKBONE: 4 | CONV_BODY: FBNet 5 | FBNET: 6 | ARCH: "xirb16d_dsmask" 7 | BN_TYPE: "bn" 8 | WIDTH_DIVISOR: 8 9 | DW_CONV_SKIP_BN: True 10 | DW_CONV_SKIP_RELU: True 11 | DET_HEAD_LAST_SCALE: -1.0 12 | RPN: 13 | ANCHOR_SIZES: (16, 32, 64, 128, 256) 14 | ANCHOR_STRIDE: (16, ) 15 | BATCH_SIZE_PER_IMAGE: 256 16 | PRE_NMS_TOP_N_TRAIN: 6000 17 | PRE_NMS_TOP_N_TEST: 6000 18 | POST_NMS_TOP_N_TRAIN: 2000 19 | POST_NMS_TOP_N_TEST: 100 20 | RPN_HEAD: FBNet.rpn_head 21 | ROI_HEADS: 22 | BATCH_SIZE_PER_IMAGE: 512 23 | ROI_BOX_HEAD: 24 | POOLER_RESOLUTION: 6 25 | FEATURE_EXTRACTOR: FBNet.roi_head 26 | NUM_CLASSES: 81 27 | ROI_MASK_HEAD: 28 | POOLER_RESOLUTION: 6 29 | FEATURE_EXTRACTOR: FBNet.roi_head_mask 30 | PREDICTOR: "MaskRCNNConv1x1Predictor" 31 | RESOLUTION: 12 32 | SHARE_BOX_FEATURE_EXTRACTOR: False 33 | MASK_ON: True 34 | DATASETS: 35 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 36 | TEST: ("coco_2014_minival",) 37 | SOLVER: 38 | BASE_LR: 0.06 39 | WARMUP_FACTOR: 0.1 40 | WEIGHT_DECAY: 0.0001 41 | STEPS: (60000, 80000) 42 | MAX_ITER: 90000 43 | IMS_PER_BATCH: 128 # for 8GPUs 44 | # TEST: 45 | # IMS_PER_BATCH: 8 46 | INPUT: 47 | MIN_SIZE_TRAIN: (320, ) 48 | MAX_SIZE_TRAIN: 640 49 | MIN_SIZE_TEST: 320 50 | MAX_SIZE_TEST: 640 51 | PIXEL_MEAN: [103.53, 116.28, 123.675] 52 | PIXEL_STD: [57.375, 57.12, 58.395] 53 | -------------------------------------------------------------------------------- /configs/maskrcnn_benchmark_models/e2e_mask_rcnn_fbnet_xirb16d_dsmask_600.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | BACKBONE: 4 | CONV_BODY: FBNet 5 | FBNET: 6 | ARCH: "xirb16d_dsmask" 7 | BN_TYPE: "bn" 8 | WIDTH_DIVISOR: 8 9 | DW_CONV_SKIP_BN: True 10 | DW_CONV_SKIP_RELU: True 11 | DET_HEAD_LAST_SCALE: 0.0 12 | RPN: 13 | ANCHOR_SIZES: (32, 64, 128, 256, 512) 14 | ANCHOR_STRIDE: (16, ) 15 | BATCH_SIZE_PER_IMAGE: 256 16 | PRE_NMS_TOP_N_TRAIN: 6000 17 | PRE_NMS_TOP_N_TEST: 6000 18 | POST_NMS_TOP_N_TRAIN: 2000 19 | POST_NMS_TOP_N_TEST: 200 20 | RPN_HEAD: FBNet.rpn_head 21 | ROI_HEADS: 22 | BATCH_SIZE_PER_IMAGE: 256 23 | ROI_BOX_HEAD: 24 | POOLER_RESOLUTION: 6 25 | FEATURE_EXTRACTOR: FBNet.roi_head 26 | NUM_CLASSES: 81 27 | ROI_MASK_HEAD: 28 | POOLER_RESOLUTION: 6 29 | FEATURE_EXTRACTOR: FBNet.roi_head_mask 30 | PREDICTOR: "MaskRCNNConv1x1Predictor" 31 | RESOLUTION: 12 32 | SHARE_BOX_FEATURE_EXTRACTOR: False 33 | MASK_ON: True 34 | DATASETS: 35 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 36 | TEST: ("coco_2014_minival",) 37 | SOLVER: 38 | BASE_LR: 0.06 39 | WARMUP_FACTOR: 0.1 40 | WEIGHT_DECAY: 0.0001 41 | STEPS: (60000, 80000) 42 | MAX_ITER: 90000 43 | IMS_PER_BATCH: 128 # for 8GPUs 44 | # TEST: 45 | # IMS_PER_BATCH: 8 46 | INPUT: 47 | MIN_SIZE_TRAIN: (600, ) 48 | MAX_SIZE_TRAIN: 1000 49 | MIN_SIZE_TEST: 600 50 | MAX_SIZE_TEST: 1000 51 | PIXEL_MEAN: [103.53, 116.28, 123.675] 52 | PIXEL_STD: [57.375, 57.12, 58.395] 53 | -------------------------------------------------------------------------------- /configs/maskrcnn_benchmark_models/rpn_R_101_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-101" 4 | RPN_ONLY: True 5 | BACKBONE: 6 | CONV_BODY: "R-101-FPN" 7 | RESNETS: 8 | BACKBONE_OUT_CHANNELS: 256 9 | RPN: 10 | USE_FPN: True 11 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 12 | PRE_NMS_TOP_N_TEST: 1000 13 | POST_NMS_TOP_N_TEST: 2000 14 | FPN_POST_NMS_TOP_N_TEST: 2000 15 | DATASETS: 16 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 17 | TEST: ("coco_2014_minival",) 18 | DATALOADER: 19 | SIZE_DIVISIBILITY: 32 20 | SOLVER: 21 | BASE_LR: 0.02 22 | WEIGHT_DECAY: 0.0001 23 | STEPS: (60000, 80000) 24 | MAX_ITER: 90000 25 | -------------------------------------------------------------------------------- /configs/maskrcnn_benchmark_models/rpn_R_50_C4_1x.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 4 | RPN_ONLY: True 5 | RPN: 6 | PRE_NMS_TOP_N_TEST: 12000 7 | POST_NMS_TOP_N_TEST: 2000 8 | DATASETS: 9 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 10 | TEST: ("coco_2014_minival",) 11 | SOLVER: 12 | BASE_LR: 0.02 13 | WEIGHT_DECAY: 0.0001 14 | STEPS: (60000, 80000) 15 | MAX_ITER: 90000 16 | -------------------------------------------------------------------------------- /configs/maskrcnn_benchmark_models/rpn_R_50_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 4 | RPN_ONLY: True 5 | BACKBONE: 6 | CONV_BODY: "R-50-FPN" 7 | RESNETS: 8 | BACKBONE_OUT_CHANNELS: 256 9 | RPN: 10 | USE_FPN: True 11 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 12 | PRE_NMS_TOP_N_TEST: 1000 13 | POST_NMS_TOP_N_TEST: 2000 14 | FPN_POST_NMS_TOP_N_TEST: 2000 15 | DATASETS: 16 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 17 | TEST: ("coco_2014_minival",) 18 | DATALOADER: 19 | SIZE_DIVISIBILITY: 32 20 | SOLVER: 21 | BASE_LR: 0.02 22 | WEIGHT_DECAY: 0.0001 23 | STEPS: (60000, 80000) 24 | MAX_ITER: 90000 25 | -------------------------------------------------------------------------------- /configs/maskrcnn_benchmark_models/rpn_X_101_32x8d_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/FAIR/20171220/X-101-32x8d" 4 | RPN_ONLY: True 5 | BACKBONE: 6 | CONV_BODY: "R-101-FPN" 7 | RESNETS: 8 | BACKBONE_OUT_CHANNELS: 256 9 | STRIDE_IN_1X1: False 10 | NUM_GROUPS: 32 11 | WIDTH_PER_GROUP: 8 12 | RPN: 13 | USE_FPN: True 14 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 15 | PRE_NMS_TOP_N_TEST: 1000 16 | POST_NMS_TOP_N_TEST: 2000 17 | FPN_POST_NMS_TOP_N_TEST: 2000 18 | DATASETS: 19 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 20 | TEST: ("coco_2014_minival",) 21 | DATALOADER: 22 | SIZE_DIVISIBILITY: 32 23 | SOLVER: 24 | BASE_LR: 0.02 25 | WEIGHT_DECAY: 0.0001 26 | STEPS: (60000, 80000) 27 | MAX_ITER: 90000 28 | -------------------------------------------------------------------------------- /configs/pascal_voc/e2e_faster_rcnn_R_50_C4_1x_1_gpu_voc.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 4 | RPN: 5 | PRE_NMS_TOP_N_TEST: 6000 6 | POST_NMS_TOP_N_TEST: 300 7 | ANCHOR_SIZES: (128, 256, 512) 8 | ROI_BOX_HEAD: 9 | NUM_CLASSES: 21 10 | DATASETS: 11 | TRAIN: ("voc_2007_train", "voc_2007_val") 12 | TEST: ("voc_2007_test",) 13 | SOLVER: 14 | BASE_LR: 0.001 15 | WEIGHT_DECAY: 0.0001 16 | STEPS: (50000, ) 17 | MAX_ITER: 70000 18 | IMS_PER_BATCH: 1 19 | TEST: 20 | IMS_PER_BATCH: 1 21 | -------------------------------------------------------------------------------- /configs/pascal_voc/e2e_faster_rcnn_R_50_C4_1x_4_gpu_voc.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 4 | RPN: 5 | PRE_NMS_TOP_N_TEST: 6000 6 | POST_NMS_TOP_N_TEST: 300 7 | ANCHOR_SIZES: (128, 256, 512) 8 | ROI_BOX_HEAD: 9 | NUM_CLASSES: 21 10 | DATASETS: 11 | TRAIN: ("voc_2007_train", "voc_2007_val") 12 | TEST: ("voc_2007_test",) 13 | SOLVER: 14 | BASE_LR: 0.004 15 | WEIGHT_DECAY: 0.0001 16 | STEPS: (12500, ) 17 | MAX_ITER: 17500 18 | IMS_PER_BATCH: 4 19 | TEST: 20 | IMS_PER_BATCH: 4 21 | -------------------------------------------------------------------------------- /configs/pascal_voc/e2e_mask_rcnn_R_50_FPN_1x_cocostyle.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 4 | BACKBONE: 5 | CONV_BODY: "R-50-FPN" 6 | RESNETS: 7 | BACKBONE_OUT_CHANNELS: 256 8 | RPN: 9 | USE_FPN: True 10 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 11 | PRE_NMS_TOP_N_TRAIN: 2000 12 | PRE_NMS_TOP_N_TEST: 1000 13 | POST_NMS_TOP_N_TEST: 1000 14 | FPN_POST_NMS_TOP_N_TEST: 1000 15 | ROI_HEADS: 16 | USE_FPN: True 17 | ROI_BOX_HEAD: 18 | POOLER_RESOLUTION: 7 19 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 20 | POOLER_SAMPLING_RATIO: 2 21 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 22 | PREDICTOR: "FPNPredictor" 23 | NUM_CLASSES: 21 24 | ROI_MASK_HEAD: 25 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 26 | FEATURE_EXTRACTOR: "MaskRCNNFPNFeatureExtractor" 27 | PREDICTOR: "MaskRCNNC4Predictor" 28 | POOLER_RESOLUTION: 14 29 | POOLER_SAMPLING_RATIO: 2 30 | RESOLUTION: 28 31 | SHARE_BOX_FEATURE_EXTRACTOR: False 32 | MASK_ON: True 33 | DATASETS: 34 | TRAIN: ("voc_2012_train_cocostyle",) 35 | TEST: ("voc_2012_val_cocostyle",) 36 | DATALOADER: 37 | SIZE_DIVISIBILITY: 32 38 | SOLVER: 39 | BASE_LR: 0.01 40 | WEIGHT_DECAY: 0.0001 41 | STEPS: (18000,) 42 | MAX_ITER: 24000 43 | -------------------------------------------------------------------------------- /configs/quick_schedules/e2e_faster_rcnn_R_50_C4_quick.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 4 | RPN: 5 | PRE_NMS_TOP_N_TEST: 6000 6 | POST_NMS_TOP_N_TEST: 1000 7 | ROI_HEADS: 8 | BATCH_SIZE_PER_IMAGE: 256 9 | DATASETS: 10 | TRAIN: ("coco_2014_minival",) 11 | TEST: ("coco_2014_minival",) 12 | INPUT: 13 | MIN_SIZE_TRAIN: (600,) 14 | MAX_SIZE_TRAIN: 1000 15 | MIN_SIZE_TEST: 800 16 | MAX_SIZE_TEST: 1000 17 | SOLVER: 18 | BASE_LR: 0.005 19 | WEIGHT_DECAY: 0.0001 20 | STEPS: (1500,) 21 | MAX_ITER: 2000 22 | IMS_PER_BATCH: 2 23 | TEST: 24 | IMS_PER_BATCH: 2 25 | -------------------------------------------------------------------------------- /configs/quick_schedules/e2e_faster_rcnn_R_50_FPN_quick.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 4 | BACKBONE: 5 | CONV_BODY: "R-50-FPN" 6 | RESNETS: 7 | BACKBONE_OUT_CHANNELS: 256 8 | RPN: 9 | USE_FPN: True 10 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 11 | PRE_NMS_TOP_N_TRAIN: 2000 12 | PRE_NMS_TOP_N_TEST: 1000 13 | POST_NMS_TOP_N_TEST: 1000 14 | FPN_POST_NMS_TOP_N_TEST: 1000 15 | ROI_HEADS: 16 | USE_FPN: True 17 | BATCH_SIZE_PER_IMAGE: 256 18 | ROI_BOX_HEAD: 19 | POOLER_RESOLUTION: 7 20 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 21 | POOLER_SAMPLING_RATIO: 2 22 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 23 | PREDICTOR: "FPNPredictor" 24 | DATASETS: 25 | TRAIN: ("coco_2014_minival",) 26 | TEST: ("coco_2014_minival",) 27 | INPUT: 28 | MIN_SIZE_TRAIN: (600,) 29 | MAX_SIZE_TRAIN: 1000 30 | MIN_SIZE_TEST: 800 31 | MAX_SIZE_TEST: 1000 32 | DATALOADER: 33 | SIZE_DIVISIBILITY: 32 34 | SOLVER: 35 | BASE_LR: 0.005 36 | WEIGHT_DECAY: 0.0001 37 | STEPS: (1500,) 38 | MAX_ITER: 2000 39 | IMS_PER_BATCH: 4 40 | TEST: 41 | IMS_PER_BATCH: 2 42 | -------------------------------------------------------------------------------- /configs/quick_schedules/e2e_faster_rcnn_X_101_32x8d_FPN_quick.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/FAIR/20171220/X-101-32x8d" 4 | BACKBONE: 5 | CONV_BODY: "R-101-FPN" 6 | RESNETS: 7 | BACKBONE_OUT_CHANNELS: 256 8 | STRIDE_IN_1X1: False 9 | NUM_GROUPS: 32 10 | WIDTH_PER_GROUP: 8 11 | RPN: 12 | USE_FPN: True 13 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 14 | PRE_NMS_TOP_N_TRAIN: 2000 15 | PRE_NMS_TOP_N_TEST: 1000 16 | POST_NMS_TOP_N_TEST: 1000 17 | FPN_POST_NMS_TOP_N_TEST: 1000 18 | ROI_HEADS: 19 | USE_FPN: True 20 | BATCH_SIZE_PER_IMAGE: 256 21 | ROI_BOX_HEAD: 22 | POOLER_RESOLUTION: 7 23 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 24 | POOLER_SAMPLING_RATIO: 2 25 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 26 | PREDICTOR: "FPNPredictor" 27 | DATASETS: 28 | TRAIN: ("coco_2014_minival",) 29 | TEST: ("coco_2014_minival",) 30 | INPUT: 31 | MIN_SIZE_TRAIN: (600,) 32 | MAX_SIZE_TRAIN: 1000 33 | MIN_SIZE_TEST: 800 34 | MAX_SIZE_TEST: 1000 35 | DATALOADER: 36 | SIZE_DIVISIBILITY: 32 37 | SOLVER: 38 | BASE_LR: 0.005 39 | WEIGHT_DECAY: 0.0001 40 | STEPS: (1500,) 41 | MAX_ITER: 2000 42 | IMS_PER_BATCH: 2 43 | TEST: 44 | IMS_PER_BATCH: 2 45 | -------------------------------------------------------------------------------- /configs/quick_schedules/e2e_keypoint_rcnn_R_50_FPN_quick.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 4 | BACKBONE: 5 | CONV_BODY: "R-50-FPN" 6 | RESNETS: 7 | BACKBONE_OUT_CHANNELS: 256 8 | RPN: 9 | USE_FPN: True 10 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 11 | PRE_NMS_TOP_N_TRAIN: 2000 12 | PRE_NMS_TOP_N_TEST: 1000 13 | POST_NMS_TOP_N_TEST: 1000 14 | FPN_POST_NMS_TOP_N_TEST: 1000 15 | ROI_HEADS: 16 | USE_FPN: True 17 | BATCH_SIZE_PER_IMAGE: 256 18 | ROI_BOX_HEAD: 19 | POOLER_RESOLUTION: 7 20 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 21 | POOLER_SAMPLING_RATIO: 2 22 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 23 | PREDICTOR: "FPNPredictor" 24 | NUM_CLASSES: 2 25 | ROI_KEYPOINT_HEAD: 26 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 27 | FEATURE_EXTRACTOR: "KeypointRCNNFeatureExtractor" 28 | PREDICTOR: "KeypointRCNNPredictor" 29 | POOLER_RESOLUTION: 14 30 | POOLER_SAMPLING_RATIO: 2 31 | RESOLUTION: 56 32 | SHARE_BOX_FEATURE_EXTRACTOR: False 33 | KEYPOINT_ON: True 34 | DATASETS: 35 | TRAIN: ("keypoints_coco_2014_minival",) 36 | TEST: ("keypoints_coco_2014_minival",) 37 | INPUT: 38 | MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800) 39 | MAX_SIZE_TRAIN: 1000 40 | MIN_SIZE_TEST: 800 41 | MAX_SIZE_TEST: 1000 42 | DATALOADER: 43 | SIZE_DIVISIBILITY: 32 44 | SOLVER: 45 | BASE_LR: 0.005 46 | WEIGHT_DECAY: 0.0001 47 | STEPS: (1500,) 48 | MAX_ITER: 2000 49 | IMS_PER_BATCH: 4 50 | TEST: 51 | IMS_PER_BATCH: 2 52 | -------------------------------------------------------------------------------- /configs/quick_schedules/e2e_mask_rcnn_R_50_C4_quick.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 4 | RPN: 5 | PRE_NMS_TOP_N_TEST: 6000 6 | POST_NMS_TOP_N_TEST: 1000 7 | ROI_HEADS: 8 | BATCH_SIZE_PER_IMAGE: 256 9 | ROI_MASK_HEAD: 10 | PREDICTOR: "MaskRCNNC4Predictor" 11 | SHARE_BOX_FEATURE_EXTRACTOR: True 12 | MASK_ON: True 13 | DATASETS: 14 | TRAIN: ("coco_2014_minival",) 15 | TEST: ("coco_2014_minival",) 16 | INPUT: 17 | MIN_SIZE_TRAIN: (600,) 18 | MAX_SIZE_TRAIN: 1000 19 | MIN_SIZE_TEST: 800 20 | MAX_SIZE_TEST: 1000 21 | SOLVER: 22 | BASE_LR: 0.005 23 | WEIGHT_DECAY: 0.0001 24 | STEPS: (1500,) 25 | MAX_ITER: 2000 26 | IMS_PER_BATCH: 4 27 | TEST: 28 | IMS_PER_BATCH: 2 29 | -------------------------------------------------------------------------------- /configs/quick_schedules/e2e_mask_rcnn_R_50_FPN_quick.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 4 | BACKBONE: 5 | CONV_BODY: "R-50-FPN" 6 | RESNETS: 7 | BACKBONE_OUT_CHANNELS: 256 8 | RPN: 9 | USE_FPN: True 10 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 11 | PRE_NMS_TOP_N_TRAIN: 2000 12 | PRE_NMS_TOP_N_TEST: 1000 13 | POST_NMS_TOP_N_TEST: 1000 14 | FPN_POST_NMS_TOP_N_TEST: 1000 15 | ROI_HEADS: 16 | USE_FPN: True 17 | BATCH_SIZE_PER_IMAGE: 256 18 | ROI_BOX_HEAD: 19 | POOLER_RESOLUTION: 7 20 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 21 | POOLER_SAMPLING_RATIO: 2 22 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 23 | PREDICTOR: "FPNPredictor" 24 | ROI_MASK_HEAD: 25 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 26 | FEATURE_EXTRACTOR: "MaskRCNNFPNFeatureExtractor" 27 | PREDICTOR: "MaskRCNNC4Predictor" 28 | POOLER_RESOLUTION: 14 29 | POOLER_SAMPLING_RATIO: 2 30 | RESOLUTION: 28 31 | SHARE_BOX_FEATURE_EXTRACTOR: False 32 | MASK_ON: True 33 | DATASETS: 34 | TRAIN: ("coco_2014_minival",) 35 | TEST: ("coco_2014_minival",) 36 | INPUT: 37 | MIN_SIZE_TRAIN: (600,) 38 | MAX_SIZE_TRAIN: 1000 39 | MIN_SIZE_TEST: 800 40 | MAX_SIZE_TEST: 1000 41 | DATALOADER: 42 | SIZE_DIVISIBILITY: 32 43 | SOLVER: 44 | BASE_LR: 0.005 45 | WEIGHT_DECAY: 0.0001 46 | STEPS: (1500,) 47 | MAX_ITER: 2000 48 | IMS_PER_BATCH: 4 49 | TEST: 50 | IMS_PER_BATCH: 2 51 | -------------------------------------------------------------------------------- /configs/quick_schedules/e2e_mask_rcnn_X_101_32x8d_FPN_quick.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/FAIR/20171220/X-101-32x8d" 4 | BACKBONE: 5 | CONV_BODY: "R-101-FPN" 6 | RESNETS: 7 | BACKBONE_OUT_CHANNELS: 256 8 | STRIDE_IN_1X1: False 9 | NUM_GROUPS: 32 10 | WIDTH_PER_GROUP: 8 11 | RPN: 12 | USE_FPN: True 13 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 14 | PRE_NMS_TOP_N_TRAIN: 2000 15 | PRE_NMS_TOP_N_TEST: 1000 16 | POST_NMS_TOP_N_TEST: 1000 17 | FPN_POST_NMS_TOP_N_TEST: 1000 18 | ROI_HEADS: 19 | USE_FPN: True 20 | BATCH_SIZE_PER_IMAGE: 256 21 | ROI_BOX_HEAD: 22 | POOLER_RESOLUTION: 7 23 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 24 | POOLER_SAMPLING_RATIO: 2 25 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 26 | PREDICTOR: "FPNPredictor" 27 | ROI_MASK_HEAD: 28 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 29 | FEATURE_EXTRACTOR: "MaskRCNNFPNFeatureExtractor" 30 | PREDICTOR: "MaskRCNNC4Predictor" 31 | POOLER_RESOLUTION: 14 32 | POOLER_SAMPLING_RATIO: 2 33 | RESOLUTION: 28 34 | SHARE_BOX_FEATURE_EXTRACTOR: False 35 | MASK_ON: True 36 | DATASETS: 37 | TRAIN: ("coco_2014_minival",) 38 | TEST: ("coco_2014_minival",) 39 | INPUT: 40 | MIN_SIZE_TRAIN: (600,) 41 | MAX_SIZE_TRAIN: 1000 42 | MIN_SIZE_TEST: 800 43 | MAX_SIZE_TEST: 1000 44 | DATALOADER: 45 | SIZE_DIVISIBILITY: 32 46 | SOLVER: 47 | BASE_LR: 0.005 48 | WEIGHT_DECAY: 0.0001 49 | STEPS: (1500,) 50 | MAX_ITER: 2000 51 | IMS_PER_BATCH: 2 52 | TEST: 53 | IMS_PER_BATCH: 2 54 | -------------------------------------------------------------------------------- /configs/quick_schedules/rpn_R_50_C4_quick.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 4 | RPN_ONLY: True 5 | RPN: 6 | PRE_NMS_TOP_N_TEST: 12000 7 | POST_NMS_TOP_N_TEST: 2000 8 | DATASETS: 9 | TRAIN: ("coco_2014_minival",) 10 | TEST: ("coco_2014_minival",) 11 | INPUT: 12 | MIN_SIZE_TRAIN: (600,) 13 | MAX_SIZE_TRAIN: 1000 14 | MIN_SIZE_TEST: 800 15 | MAX_SIZE_TEST: 1000 16 | SOLVER: 17 | BASE_LR: 0.005 18 | WEIGHT_DECAY: 0.0001 19 | STEPS: (1500,) 20 | MAX_ITER: 2000 21 | IMS_PER_BATCH: 4 22 | TEST: 23 | IMS_PER_BATCH: 2 24 | -------------------------------------------------------------------------------- /configs/quick_schedules/rpn_R_50_FPN_quick.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 4 | RPN_ONLY: True 5 | BACKBONE: 6 | CONV_BODY: "R-50-FPN" 7 | RESNETS: 8 | BACKBONE_OUT_CHANNELS: 256 9 | RPN: 10 | USE_FPN: True 11 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 12 | PRE_NMS_TOP_N_TEST: 1000 13 | POST_NMS_TOP_N_TEST: 2000 14 | FPN_POST_NMS_TOP_N_TEST: 2000 15 | DATASETS: 16 | TRAIN: ("coco_2014_minival",) 17 | TEST: ("coco_2014_minival",) 18 | INPUT: 19 | MIN_SIZE_TRAIN: (600,) 20 | MAX_SIZE_TRAIN: 1000 21 | MIN_SIZE_TEST: 800 22 | MAX_SIZE_TEST: 1000 23 | DATALOADER: 24 | SIZE_DIVISIBILITY: 32 25 | SOLVER: 26 | BASE_LR: 0.005 27 | WEIGHT_DECAY: 0.0001 28 | STEPS: (1500,) 29 | MAX_ITER: 2000 30 | IMS_PER_BATCH: 4 31 | TEST: 32 | IMS_PER_BATCH: 2 33 | -------------------------------------------------------------------------------- /configs/retinanet/retinanet_R-101-FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-101" 4 | RPN_ONLY: True 5 | RETINANET_ON: True 6 | BACKBONE: 7 | CONV_BODY: "R-101-FPN-RETINANET" 8 | RESNETS: 9 | BACKBONE_OUT_CHANNELS: 256 10 | RPN: 11 | USE_FPN: True 12 | FG_IOU_THRESHOLD: 0.5 13 | BG_IOU_THRESHOLD: 0.4 14 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 15 | PRE_NMS_TOP_N_TRAIN: 2000 16 | PRE_NMS_TOP_N_TEST: 1000 17 | POST_NMS_TOP_N_TEST: 1000 18 | FPN_POST_NMS_TOP_N_TEST: 1000 19 | ROI_HEADS: 20 | USE_FPN: True 21 | BATCH_SIZE_PER_IMAGE: 256 22 | ROI_BOX_HEAD: 23 | POOLER_RESOLUTION: 7 24 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 25 | POOLER_SAMPLING_RATIO: 2 26 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 27 | PREDICTOR: "FPNPredictor" 28 | RETINANET: 29 | SCALES_PER_OCTAVE: 3 30 | STRADDLE_THRESH: -1 31 | FG_IOU_THRESHOLD: 0.5 32 | BG_IOU_THRESHOLD: 0.4 33 | DATASETS: 34 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 35 | TEST: ("coco_2014_minival",) 36 | INPUT: 37 | MIN_SIZE_TRAIN: (800, ) 38 | MAX_SIZE_TRAIN: 1333 39 | MIN_SIZE_TEST: 800 40 | MAX_SIZE_TEST: 1333 41 | DATALOADER: 42 | SIZE_DIVISIBILITY: 32 43 | SOLVER: 44 | # Assume 4 gpus 45 | BASE_LR: 0.005 46 | WEIGHT_DECAY: 0.0001 47 | STEPS: (120000, 160000) 48 | MAX_ITER: 180000 49 | IMS_PER_BATCH: 8 50 | -------------------------------------------------------------------------------- /configs/retinanet/retinanet_R-101-FPN_P5_1x.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-101" 4 | RPN_ONLY: True 5 | RETINANET_ON: True 6 | BACKBONE: 7 | CONV_BODY: "R-101-FPN-RETINANET" 8 | RESNETS: 9 | BACKBONE_OUT_CHANNELS: 256 10 | RPN: 11 | USE_FPN: True 12 | FG_IOU_THRESHOLD: 0.5 13 | BG_IOU_THRESHOLD: 0.4 14 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 15 | PRE_NMS_TOP_N_TRAIN: 2000 16 | PRE_NMS_TOP_N_TEST: 1000 17 | POST_NMS_TOP_N_TEST: 1000 18 | FPN_POST_NMS_TOP_N_TEST: 1000 19 | ROI_HEADS: 20 | USE_FPN: True 21 | BATCH_SIZE_PER_IMAGE: 256 22 | ROI_BOX_HEAD: 23 | POOLER_RESOLUTION: 7 24 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 25 | POOLER_SAMPLING_RATIO: 2 26 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 27 | PREDICTOR: "FPNPredictor" 28 | RETINANET: 29 | SCALES_PER_OCTAVE: 3 30 | STRADDLE_THRESH: -1 31 | USE_C5: False 32 | FG_IOU_THRESHOLD: 0.5 33 | BG_IOU_THRESHOLD: 0.4 34 | DATASETS: 35 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 36 | TEST: ("coco_2014_minival",) 37 | INPUT: 38 | MIN_SIZE_TRAIN: (800, ) 39 | MAX_SIZE_TRAIN: 1333 40 | MIN_SIZE_TEST: 800 41 | MAX_SIZE_TEST: 1333 42 | DATALOADER: 43 | SIZE_DIVISIBILITY: 32 44 | SOLVER: 45 | # Assume 4 gpus 46 | BASE_LR: 0.005 47 | WEIGHT_DECAY: 0.0001 48 | STEPS: (120000, 160000) 49 | MAX_ITER: 180000 50 | IMS_PER_BATCH: 8 51 | -------------------------------------------------------------------------------- /configs/retinanet/retinanet_R-50-FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 4 | RPN_ONLY: True 5 | RETINANET_ON: True 6 | BACKBONE: 7 | CONV_BODY: "R-50-FPN-RETINANET" 8 | RESNETS: 9 | BACKBONE_OUT_CHANNELS: 256 10 | RPN: 11 | USE_FPN: True 12 | FG_IOU_THRESHOLD: 0.5 13 | BG_IOU_THRESHOLD: 0.4 14 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 15 | PRE_NMS_TOP_N_TRAIN: 2000 16 | PRE_NMS_TOP_N_TEST: 1000 17 | POST_NMS_TOP_N_TEST: 1000 18 | FPN_POST_NMS_TOP_N_TEST: 1000 19 | ROI_HEADS: 20 | USE_FPN: True 21 | BATCH_SIZE_PER_IMAGE: 256 22 | ROI_BOX_HEAD: 23 | POOLER_RESOLUTION: 7 24 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 25 | POOLER_SAMPLING_RATIO: 2 26 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 27 | PREDICTOR: "FPNPredictor" 28 | RETINANET: 29 | SCALES_PER_OCTAVE: 3 30 | STRADDLE_THRESH: -1 31 | FG_IOU_THRESHOLD: 0.5 32 | BG_IOU_THRESHOLD: 0.4 33 | DATASETS: 34 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 35 | TEST: ("coco_2014_minival",) 36 | INPUT: 37 | MIN_SIZE_TRAIN: (800,) 38 | MAX_SIZE_TRAIN: 1333 39 | MIN_SIZE_TEST: 800 40 | MAX_SIZE_TEST: 1333 41 | DATALOADER: 42 | SIZE_DIVISIBILITY: 32 43 | SOLVER: 44 | # Assume 4 gpus 45 | BASE_LR: 0.005 46 | WEIGHT_DECAY: 0.0001 47 | STEPS: (120000, 160000) 48 | MAX_ITER: 180000 49 | IMS_PER_BATCH: 8 50 | -------------------------------------------------------------------------------- /configs/retinanet/retinanet_R-50-FPN_1x_quick.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 4 | RPN_ONLY: True 5 | RETINANET_ON: True 6 | BACKBONE: 7 | CONV_BODY: "R-50-FPN-RETINANET" 8 | RESNETS: 9 | BACKBONE_OUT_CHANNELS: 256 10 | RPN: 11 | USE_FPN: True 12 | FG_IOU_THRESHOLD: 0.5 13 | BG_IOU_THRESHOLD: 0.4 14 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 15 | PRE_NMS_TOP_N_TRAIN: 2000 16 | PRE_NMS_TOP_N_TEST: 1000 17 | POST_NMS_TOP_N_TEST: 1000 18 | FPN_POST_NMS_TOP_N_TEST: 1000 19 | ROI_HEADS: 20 | USE_FPN: True 21 | BATCH_SIZE_PER_IMAGE: 256 22 | ROI_BOX_HEAD: 23 | POOLER_RESOLUTION: 7 24 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 25 | POOLER_SAMPLING_RATIO: 2 26 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 27 | PREDICTOR: "FPNPredictor" 28 | RETINANET: 29 | SCALES_PER_OCTAVE: 3 30 | STRADDLE_THRESH: -1 31 | FG_IOU_THRESHOLD: 0.5 32 | BG_IOU_THRESHOLD: 0.4 33 | DATASETS: 34 | TRAIN: ("coco_2014_minival",) 35 | TEST: ("coco_2014_minival",) 36 | INPUT: 37 | MIN_SIZE_TRAIN: (600,) 38 | MAX_SIZE_TRAIN: 1000 39 | MIN_SIZE_TEST: 800 40 | MAX_SIZE_TEST: 1000 41 | DATALOADER: 42 | SIZE_DIVISIBILITY: 32 43 | SOLVER: 44 | BASE_LR: 0.005 45 | WEIGHT_DECAY: 0.0001 46 | STEPS: (3500,) 47 | MAX_ITER: 4000 48 | IMS_PER_BATCH: 4 49 | -------------------------------------------------------------------------------- /configs/retinanet/retinanet_R-50-FPN_P5_1x.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 4 | RPN_ONLY: True 5 | RETINANET_ON: True 6 | BACKBONE: 7 | CONV_BODY: "R-50-FPN-RETINANET" 8 | RESNETS: 9 | BACKBONE_OUT_CHANNELS: 256 10 | RPN: 11 | USE_FPN: True 12 | FG_IOU_THRESHOLD: 0.5 13 | BG_IOU_THRESHOLD: 0.4 14 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 15 | PRE_NMS_TOP_N_TRAIN: 2000 16 | PRE_NMS_TOP_N_TEST: 1000 17 | POST_NMS_TOP_N_TEST: 1000 18 | FPN_POST_NMS_TOP_N_TEST: 1000 19 | ROI_HEADS: 20 | USE_FPN: True 21 | BATCH_SIZE_PER_IMAGE: 256 22 | ROI_BOX_HEAD: 23 | POOLER_RESOLUTION: 7 24 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 25 | POOLER_SAMPLING_RATIO: 2 26 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 27 | PREDICTOR: "FPNPredictor" 28 | RETINANET: 29 | SCALES_PER_OCTAVE: 3 30 | STRADDLE_THRESH: -1 31 | USE_C5: False 32 | FG_IOU_THRESHOLD: 0.5 33 | BG_IOU_THRESHOLD: 0.4 34 | DATASETS: 35 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 36 | TEST: ("coco_2014_minival",) 37 | INPUT: 38 | MIN_SIZE_TRAIN: (800,) 39 | MAX_SIZE_TRAIN: 1333 40 | MIN_SIZE_TEST: 800 41 | MAX_SIZE_TEST: 1333 42 | DATALOADER: 43 | SIZE_DIVISIBILITY: 32 44 | SOLVER: 45 | # Assume 4 gpus 46 | BASE_LR: 0.005 47 | WEIGHT_DECAY: 0.0001 48 | STEPS: (120000, 160000) 49 | MAX_ITER: 180000 50 | IMS_PER_BATCH: 8 51 | -------------------------------------------------------------------------------- /configs/retinanet/retinanet_X_101_32x8d_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/FAIR/20171220/X-101-32x8d" 4 | RPN_ONLY: True 5 | RETINANET_ON: True 6 | BACKBONE: 7 | CONV_BODY: "R-101-FPN-RETINANET" 8 | RESNETS: 9 | BACKBONE_OUT_CHANNELS: 256 10 | STRIDE_IN_1X1: False 11 | NUM_GROUPS: 32 12 | WIDTH_PER_GROUP: 8 13 | RPN: 14 | USE_FPN: True 15 | FG_IOU_THRESHOLD: 0.5 16 | BG_IOU_THRESHOLD: 0.4 17 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 18 | PRE_NMS_TOP_N_TRAIN: 2000 19 | PRE_NMS_TOP_N_TEST: 1000 20 | POST_NMS_TOP_N_TEST: 1000 21 | FPN_POST_NMS_TOP_N_TEST: 1000 22 | ROI_HEADS: 23 | USE_FPN: True 24 | BATCH_SIZE_PER_IMAGE: 256 25 | ROI_BOX_HEAD: 26 | POOLER_RESOLUTION: 7 27 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 28 | POOLER_SAMPLING_RATIO: 2 29 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 30 | PREDICTOR: "FPNPredictor" 31 | RETINANET: 32 | SCALES_PER_OCTAVE: 3 33 | STRADDLE_THRESH: -1 34 | FG_IOU_THRESHOLD: 0.5 35 | BG_IOU_THRESHOLD: 0.4 36 | DATASETS: 37 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 38 | TEST: ("coco_2014_minival",) 39 | INPUT: 40 | MIN_SIZE_TRAIN: (800, ) 41 | MAX_SIZE_TRAIN: 1333 42 | MIN_SIZE_TEST: 800 43 | MAX_SIZE_TEST: 1333 44 | DATALOADER: 45 | SIZE_DIVISIBILITY: 32 46 | SOLVER: 47 | # Assume 4 gpus 48 | BASE_LR: 0.0025 49 | WEIGHT_DECAY: 0.0001 50 | STEPS: (240000, 320000) 51 | MAX_ITER: 360000 52 | IMS_PER_BATCH: 4 53 | -------------------------------------------------------------------------------- /configs/test_time_aug/e2e_mask_rcnn_R_50_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 4 | BACKBONE: 5 | CONV_BODY: "R-50-FPN" 6 | RESNETS: 7 | BACKBONE_OUT_CHANNELS: 256 8 | RPN: 9 | USE_FPN: True 10 | ANCHOR_STRIDE: (4, 8, 16, 32, 64) 11 | PRE_NMS_TOP_N_TRAIN: 2000 12 | PRE_NMS_TOP_N_TEST: 1000 13 | POST_NMS_TOP_N_TEST: 1000 14 | FPN_POST_NMS_TOP_N_TEST: 1000 15 | ROI_HEADS: 16 | USE_FPN: True 17 | ROI_BOX_HEAD: 18 | POOLER_RESOLUTION: 7 19 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 20 | POOLER_SAMPLING_RATIO: 2 21 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 22 | PREDICTOR: "FPNPredictor" 23 | ROI_MASK_HEAD: 24 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 25 | FEATURE_EXTRACTOR: "MaskRCNNFPNFeatureExtractor" 26 | PREDICTOR: "MaskRCNNC4Predictor" 27 | POOLER_RESOLUTION: 14 28 | POOLER_SAMPLING_RATIO: 2 29 | RESOLUTION: 28 30 | SHARE_BOX_FEATURE_EXTRACTOR: False 31 | MASK_ON: True 32 | DATASETS: 33 | TRAIN: ("coco_2014_train", "coco_2014_valminusminival") 34 | TEST: ("coco_2014_minival",) 35 | DATALOADER: 36 | SIZE_DIVISIBILITY: 32 37 | SOLVER: 38 | BASE_LR: 0.02 39 | WEIGHT_DECAY: 0.0001 40 | STEPS: (60000, 80000) 41 | MAX_ITER: 90000 42 | TEST: 43 | BBOX_AUG: 44 | ENABLED: True 45 | H_FLIP: True 46 | SCALES: (400, 500, 600, 700, 900, 1000, 1100, 1200) 47 | MAX_SIZE: 2000 48 | SCALE_H_FLIP: True 49 | -------------------------------------------------------------------------------- /convert.py: -------------------------------------------------------------------------------- 1 | import os 2 | import sys 3 | 4 | 5 | output = [] 6 | n_gpu = 0 7 | test_tag = False 8 | 9 | if len(sys.argv) >= 5: 10 | if sys.argv[4] == 'test': 11 | test_tag = True 12 | assert len(sys.argv) == 6 13 | 14 | with open(sys.argv[1], 'r') as fp: 15 | 16 | for line in fp.readlines(): 17 | line = line.split("\\")[0] 18 | line = " ".join(line.split()) 19 | if 'train_net.py' in line and test_tag: 20 | line = line.replace('train_net.py', 'test_net.py') 21 | if 'nproc_per_node' in line: 22 | n_gpu = int(line.split('=')[-1]) 23 | if 'OUTPUT_DIR' in line and test_tag: 24 | out_dir = line.split()[-1] 25 | line += ' > ' + os.path.join(out_dir, sys.argv[5]) 26 | output.append(line) 27 | 28 | n_node = int(sys.argv[2]) 29 | 30 | mem = int(sys.argv[3]) 31 | 32 | prefix = "srun -w irip-c1-compute-{} --gres=gpu:a800:{} -c {} --mem {}G nohup ".format(n_node, n_gpu, n_gpu*6, mem) 33 | 34 | print(prefix + " ".join(output)) 35 | 36 | 37 | 38 | 39 | -------------------------------------------------------------------------------- /framework.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jkli1998/DRM/1dd943bd911f505ef5838c7b4d138ab3301e3fc0/framework.png -------------------------------------------------------------------------------- /maskrcnn_benchmark/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/config/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | from .defaults import _C as cfg 3 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/csrc/ROIAlign.h: -------------------------------------------------------------------------------- 1 | // Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | #pragma once 3 | 4 | #include "cpu/vision.h" 5 | 6 | #ifdef WITH_CUDA 7 | #include "cuda/vision.h" 8 | #endif 9 | 10 | // Interface for Python 11 | at::Tensor ROIAlign_forward(const at::Tensor& input, 12 | const at::Tensor& rois, 13 | const float spatial_scale, 14 | const int pooled_height, 15 | const int pooled_width, 16 | const int sampling_ratio) { 17 | if (input.type().is_cuda()) { 18 | #ifdef WITH_CUDA 19 | return ROIAlign_forward_cuda(input, rois, spatial_scale, pooled_height, pooled_width, sampling_ratio); 20 | #else 21 | AT_ERROR("Not compiled with GPU support"); 22 | #endif 23 | } 24 | return ROIAlign_forward_cpu(input, rois, spatial_scale, pooled_height, pooled_width, sampling_ratio); 25 | } 26 | 27 | at::Tensor ROIAlign_backward(const at::Tensor& grad, 28 | const at::Tensor& rois, 29 | const float spatial_scale, 30 | const int pooled_height, 31 | const int pooled_width, 32 | const int batch_size, 33 | const int channels, 34 | const int height, 35 | const int width, 36 | const int sampling_ratio) { 37 | if (grad.type().is_cuda()) { 38 | #ifdef WITH_CUDA 39 | return ROIAlign_backward_cuda(grad, rois, spatial_scale, pooled_height, pooled_width, batch_size, channels, height, width, sampling_ratio); 40 | #else 41 | AT_ERROR("Not compiled with GPU support"); 42 | #endif 43 | } 44 | AT_ERROR("Not implemented on the CPU"); 45 | } 46 | 47 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/csrc/ROIPool.h: -------------------------------------------------------------------------------- 1 | // Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | #pragma once 3 | 4 | #include "cpu/vision.h" 5 | 6 | #ifdef WITH_CUDA 7 | #include "cuda/vision.h" 8 | #endif 9 | 10 | 11 | std::tuple ROIPool_forward(const at::Tensor& input, 12 | const at::Tensor& rois, 13 | const float spatial_scale, 14 | const int pooled_height, 15 | const int pooled_width) { 16 | if (input.type().is_cuda()) { 17 | #ifdef WITH_CUDA 18 | return ROIPool_forward_cuda(input, rois, spatial_scale, pooled_height, pooled_width); 19 | #else 20 | AT_ERROR("Not compiled with GPU support"); 21 | #endif 22 | } 23 | AT_ERROR("Not implemented on the CPU"); 24 | } 25 | 26 | at::Tensor ROIPool_backward(const at::Tensor& grad, 27 | const at::Tensor& input, 28 | const at::Tensor& rois, 29 | const at::Tensor& argmax, 30 | const float spatial_scale, 31 | const int pooled_height, 32 | const int pooled_width, 33 | const int batch_size, 34 | const int channels, 35 | const int height, 36 | const int width) { 37 | if (grad.type().is_cuda()) { 38 | #ifdef WITH_CUDA 39 | return ROIPool_backward_cuda(grad, input, rois, argmax, spatial_scale, pooled_height, pooled_width, batch_size, channels, height, width); 40 | #else 41 | AT_ERROR("Not compiled with GPU support"); 42 | #endif 43 | } 44 | AT_ERROR("Not implemented on the CPU"); 45 | } 46 | 47 | 48 | 49 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/csrc/SigmoidFocalLoss.h: -------------------------------------------------------------------------------- 1 | #pragma once 2 | 3 | #include "cpu/vision.h" 4 | 5 | #ifdef WITH_CUDA 6 | #include "cuda/vision.h" 7 | #endif 8 | 9 | // Interface for Python 10 | at::Tensor SigmoidFocalLoss_forward( 11 | const at::Tensor& logits, 12 | const at::Tensor& targets, 13 | const int num_classes, 14 | const float gamma, 15 | const float alpha) { 16 | if (logits.type().is_cuda()) { 17 | #ifdef WITH_CUDA 18 | return SigmoidFocalLoss_forward_cuda(logits, targets, num_classes, gamma, alpha); 19 | #else 20 | AT_ERROR("Not compiled with GPU support"); 21 | #endif 22 | } 23 | AT_ERROR("Not implemented on the CPU"); 24 | } 25 | 26 | at::Tensor SigmoidFocalLoss_backward( 27 | const at::Tensor& logits, 28 | const at::Tensor& targets, 29 | const at::Tensor& d_losses, 30 | const int num_classes, 31 | const float gamma, 32 | const float alpha) { 33 | if (logits.type().is_cuda()) { 34 | #ifdef WITH_CUDA 35 | return SigmoidFocalLoss_backward_cuda(logits, targets, d_losses, num_classes, gamma, alpha); 36 | #else 37 | AT_ERROR("Not compiled with GPU support"); 38 | #endif 39 | } 40 | AT_ERROR("Not implemented on the CPU"); 41 | } 42 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/csrc/cpu/nms_cpu.cpp: -------------------------------------------------------------------------------- 1 | // Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | #include "cpu/vision.h" 3 | 4 | 5 | template 6 | at::Tensor nms_cpu_kernel(const at::Tensor& dets, 7 | const at::Tensor& scores, 8 | const float threshold) { 9 | AT_ASSERTM(!dets.type().is_cuda(), "dets must be a CPU tensor"); 10 | AT_ASSERTM(!scores.type().is_cuda(), "scores must be a CPU tensor"); 11 | AT_ASSERTM(dets.type() == scores.type(), "dets should have the same type as scores"); 12 | 13 | if (dets.numel() == 0) { 14 | return at::empty({0}, dets.options().dtype(at::kLong).device(at::kCPU)); 15 | } 16 | 17 | auto x1_t = dets.select(1, 0).contiguous(); 18 | auto y1_t = dets.select(1, 1).contiguous(); 19 | auto x2_t = dets.select(1, 2).contiguous(); 20 | auto y2_t = dets.select(1, 3).contiguous(); 21 | 22 | at::Tensor areas_t = (x2_t - x1_t + 1) * (y2_t - y1_t + 1); 23 | 24 | auto order_t = std::get<1>(scores.sort(0, /* descending=*/true)); 25 | 26 | auto ndets = dets.size(0); 27 | at::Tensor suppressed_t = at::zeros({ndets}, dets.options().dtype(at::kByte).device(at::kCPU)); 28 | 29 | auto suppressed = suppressed_t.data(); 30 | auto order = order_t.data(); 31 | auto x1 = x1_t.data(); 32 | auto y1 = y1_t.data(); 33 | auto x2 = x2_t.data(); 34 | auto y2 = y2_t.data(); 35 | auto areas = areas_t.data(); 36 | 37 | for (int64_t _i = 0; _i < ndets; _i++) { 38 | auto i = order[_i]; 39 | if (suppressed[i] == 1) 40 | continue; 41 | auto ix1 = x1[i]; 42 | auto iy1 = y1[i]; 43 | auto ix2 = x2[i]; 44 | auto iy2 = y2[i]; 45 | auto iarea = areas[i]; 46 | 47 | for (int64_t _j = _i + 1; _j < ndets; _j++) { 48 | auto j = order[_j]; 49 | if (suppressed[j] == 1) 50 | continue; 51 | auto xx1 = std::max(ix1, x1[j]); 52 | auto yy1 = std::max(iy1, y1[j]); 53 | auto xx2 = std::min(ix2, x2[j]); 54 | auto yy2 = std::min(iy2, y2[j]); 55 | 56 | auto w = std::max(static_cast(0), xx2 - xx1 + 1); 57 | auto h = std::max(static_cast(0), yy2 - yy1 + 1); 58 | auto inter = w * h; 59 | auto ovr = inter / (iarea + areas[j] - inter); 60 | if (ovr >= threshold) 61 | suppressed[j] = 1; 62 | } 63 | } 64 | return at::nonzero(suppressed_t == 0).squeeze(1); 65 | } 66 | 67 | at::Tensor nms_cpu(const at::Tensor& dets, 68 | const at::Tensor& scores, 69 | const float threshold) { 70 | at::Tensor result; 71 | AT_DISPATCH_FLOATING_TYPES(dets.type(), "nms", [&] { 72 | result = nms_cpu_kernel(dets, scores, threshold); 73 | }); 74 | return result; 75 | } 76 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/csrc/cpu/vision.h: -------------------------------------------------------------------------------- 1 | // Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | #pragma once 3 | #include 4 | 5 | 6 | at::Tensor ROIAlign_forward_cpu(const at::Tensor& input, 7 | const at::Tensor& rois, 8 | const float spatial_scale, 9 | const int pooled_height, 10 | const int pooled_width, 11 | const int sampling_ratio); 12 | 13 | 14 | at::Tensor nms_cpu(const at::Tensor& dets, 15 | const at::Tensor& scores, 16 | const float threshold); 17 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/csrc/deform_pool.h: -------------------------------------------------------------------------------- 1 | // Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | #pragma once 3 | #include "cpu/vision.h" 4 | 5 | #ifdef WITH_CUDA 6 | #include "cuda/vision.h" 7 | #endif 8 | 9 | 10 | // Interface for Python 11 | void deform_psroi_pooling_forward( 12 | at::Tensor input, 13 | at::Tensor bbox, 14 | at::Tensor trans, 15 | at::Tensor out, 16 | at::Tensor top_count, 17 | const int no_trans, 18 | const float spatial_scale, 19 | const int output_dim, 20 | const int group_size, 21 | const int pooled_size, 22 | const int part_size, 23 | const int sample_per_part, 24 | const float trans_std) 25 | { 26 | if (input.type().is_cuda()) { 27 | #ifdef WITH_CUDA 28 | return deform_psroi_pooling_cuda_forward( 29 | input, bbox, trans, out, top_count, 30 | no_trans, spatial_scale, output_dim, group_size, 31 | pooled_size, part_size, sample_per_part, trans_std 32 | ); 33 | #else 34 | AT_ERROR("Not compiled with GPU support"); 35 | #endif 36 | } 37 | AT_ERROR("Not implemented on the CPU"); 38 | } 39 | 40 | 41 | void deform_psroi_pooling_backward( 42 | at::Tensor out_grad, 43 | at::Tensor input, 44 | at::Tensor bbox, 45 | at::Tensor trans, 46 | at::Tensor top_count, 47 | at::Tensor input_grad, 48 | at::Tensor trans_grad, 49 | const int no_trans, 50 | const float spatial_scale, 51 | const int output_dim, 52 | const int group_size, 53 | const int pooled_size, 54 | const int part_size, 55 | const int sample_per_part, 56 | const float trans_std) 57 | { 58 | if (input.type().is_cuda()) { 59 | #ifdef WITH_CUDA 60 | return deform_psroi_pooling_cuda_backward( 61 | out_grad, input, bbox, trans, top_count, input_grad, trans_grad, 62 | no_trans, spatial_scale, output_dim, group_size, pooled_size, 63 | part_size, sample_per_part, trans_std 64 | ); 65 | #else 66 | AT_ERROR("Not compiled with GPU support"); 67 | #endif 68 | } 69 | AT_ERROR("Not implemented on the CPU"); 70 | } 71 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/csrc/nms.h: -------------------------------------------------------------------------------- 1 | // Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | #pragma once 3 | #include "cpu/vision.h" 4 | 5 | #ifdef WITH_CUDA 6 | #include "cuda/vision.h" 7 | #endif 8 | 9 | 10 | at::Tensor nms(const at::Tensor& dets, 11 | const at::Tensor& scores, 12 | const float threshold) { 13 | 14 | if (dets.type().is_cuda()) { 15 | #ifdef WITH_CUDA 16 | // TODO raise error if not compiled with CUDA 17 | if (dets.numel() == 0) 18 | return at::empty({0}, dets.options().dtype(at::kLong).device(at::kCPU)); 19 | auto b = at::cat({dets, scores.unsqueeze(1)}, 1); 20 | return nms_cuda(b, threshold); 21 | #else 22 | AT_ERROR("Not compiled with GPU support"); 23 | #endif 24 | } 25 | 26 | at::Tensor result = nms_cpu(dets, scores, threshold); 27 | return result; 28 | } 29 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/csrc/vision.cpp: -------------------------------------------------------------------------------- 1 | // Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | #include "nms.h" 3 | #include "ROIAlign.h" 4 | #include "ROIPool.h" 5 | #include "SigmoidFocalLoss.h" 6 | #include "deform_conv.h" 7 | #include "deform_pool.h" 8 | 9 | PYBIND11_MODULE(TORCH_EXTENSION_NAME, m) { 10 | m.def("nms", &nms, "non-maximum suppression"); 11 | m.def("roi_align_forward", &ROIAlign_forward, "ROIAlign_forward"); 12 | m.def("roi_align_backward", &ROIAlign_backward, "ROIAlign_backward"); 13 | m.def("roi_pool_forward", &ROIPool_forward, "ROIPool_forward"); 14 | m.def("roi_pool_backward", &ROIPool_backward, "ROIPool_backward"); 15 | m.def("sigmoid_focalloss_forward", &SigmoidFocalLoss_forward, "SigmoidFocalLoss_forward"); 16 | m.def("sigmoid_focalloss_backward", &SigmoidFocalLoss_backward, "SigmoidFocalLoss_backward"); 17 | // dcn-v2 18 | m.def("deform_conv_forward", &deform_conv_forward, "deform_conv_forward"); 19 | m.def("deform_conv_backward_input", &deform_conv_backward_input, "deform_conv_backward_input"); 20 | m.def("deform_conv_backward_parameters", &deform_conv_backward_parameters, "deform_conv_backward_parameters"); 21 | m.def("modulated_deform_conv_forward", &modulated_deform_conv_forward, "modulated_deform_conv_forward"); 22 | m.def("modulated_deform_conv_backward", &modulated_deform_conv_backward, "modulated_deform_conv_backward"); 23 | m.def("deform_psroi_pooling_forward", &deform_psroi_pooling_forward, "deform_psroi_pooling_forward"); 24 | m.def("deform_psroi_pooling_backward", &deform_psroi_pooling_backward, "deform_psroi_pooling_backward"); 25 | } -------------------------------------------------------------------------------- /maskrcnn_benchmark/data/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | from .build import make_data_loader, get_dataset_statistics, make_data_infer_loader 3 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/data/datasets/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | from .coco import COCODataset 3 | from .voc import PascalVOCDataset 4 | from .concat_dataset import ConcatDataset 5 | from .visual_genome import VGDataset 6 | from .gqa import GQADataset 7 | from .open_image import OIDataset 8 | 9 | __all__ = ["COCODataset", "ConcatDataset", "PascalVOCDataset", 10 | "VGDataset", "GQADataset", "OIDataset"] 11 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/data/datasets/concat_dataset.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | import bisect 3 | 4 | from torch.utils.data.dataset import ConcatDataset as _ConcatDataset 5 | 6 | 7 | class ConcatDataset(_ConcatDataset): 8 | """ 9 | Same as torch.utils.data.dataset.ConcatDataset, but exposes an extra 10 | method for querying the sizes of the image 11 | """ 12 | 13 | def get_idxs(self, idx): 14 | dataset_idx = bisect.bisect_right(self.cumulative_sizes, idx) 15 | if dataset_idx == 0: 16 | sample_idx = idx 17 | else: 18 | sample_idx = idx - self.cumulative_sizes[dataset_idx - 1] 19 | return dataset_idx, sample_idx 20 | 21 | def get_img_info(self, idx): 22 | dataset_idx, sample_idx = self.get_idxs(idx) 23 | return self.datasets[dataset_idx].get_img_info(sample_idx) 24 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/data/datasets/evaluation/__init__.py: -------------------------------------------------------------------------------- 1 | from maskrcnn_benchmark.data import datasets 2 | 3 | from .coco import coco_evaluation 4 | from .oi import oi_evaluation 5 | from .voc import voc_evaluation 6 | from .vg import vg_evaluation 7 | from .gqa import gqa_evaluation 8 | 9 | 10 | def evaluate(cfg, dataset, predictions, output_folder, logger, **kwargs): 11 | """evaluate dataset using different methods based on dataset type. 12 | Args: 13 | dataset: Dataset object 14 | predictions(list[BoxList]): each item in the list represents the 15 | prediction results for one image. 16 | output_folder: output folder, to save evaluation files or results. 17 | **kwargs: other args. 18 | Returns: 19 | evaluation result 20 | """ 21 | args = dict( 22 | cfg=cfg, dataset=dataset, predictions=predictions, output_folder=output_folder, logger=logger, **kwargs 23 | ) 24 | if isinstance(dataset, datasets.COCODataset): 25 | return coco_evaluation(**args) 26 | elif isinstance(dataset, datasets.PascalVOCDataset): 27 | return voc_evaluation(**args) 28 | elif isinstance(dataset, datasets.VGDataset): 29 | return vg_evaluation(**args) 30 | elif isinstance(dataset, datasets.OIDataset): 31 | return oi_evaluation(**args) 32 | elif isinstance(dataset, datasets.GQADataset): 33 | return gqa_evaluation(**args) 34 | else: 35 | dataset_name = dataset.__class__.__name__ 36 | raise NotImplementedError("Unsupported dataset type {}.".format(dataset_name)) 37 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/data/datasets/evaluation/coco/__init__.py: -------------------------------------------------------------------------------- 1 | from .coco_eval import do_coco_evaluation 2 | 3 | 4 | def coco_evaluation( 5 | cfg, 6 | dataset, 7 | predictions, 8 | output_folder, 9 | logger, 10 | box_only, 11 | iou_types, 12 | expected_results, 13 | expected_results_sigma_tol, 14 | ): 15 | return do_coco_evaluation( 16 | dataset=dataset, 17 | predictions=predictions, 18 | box_only=box_only, 19 | output_folder=output_folder, 20 | logger=logger, 21 | iou_types=iou_types, 22 | expected_results=expected_results, 23 | expected_results_sigma_tol=expected_results_sigma_tol, 24 | ) 25 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/data/datasets/evaluation/gqa/__init__.py: -------------------------------------------------------------------------------- 1 | from .gqa_eval import do_gqa_evaluation 2 | 3 | 4 | def gqa_evaluation( 5 | cfg, 6 | dataset, 7 | predictions, 8 | output_folder, 9 | logger, 10 | iou_types, 11 | **_ 12 | ): 13 | return do_gqa_evaluation( 14 | cfg=cfg, 15 | dataset=dataset, 16 | predictions=predictions, 17 | output_folder=output_folder, 18 | logger=logger, 19 | iou_types=iou_types, 20 | ) 21 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/data/datasets/evaluation/vg/__init__.py: -------------------------------------------------------------------------------- 1 | from .vg_eval import do_vg_evaluation 2 | 3 | 4 | def vg_evaluation( 5 | cfg, 6 | dataset, 7 | predictions, 8 | output_folder, 9 | logger, 10 | iou_types, 11 | **_ 12 | ): 13 | return do_vg_evaluation( 14 | cfg=cfg, 15 | dataset=dataset, 16 | predictions=predictions, 17 | output_folder=output_folder, 18 | logger=logger, 19 | iou_types=iou_types, 20 | ) 21 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/data/datasets/evaluation/vg/zeroshot_triplet_new.pytorch: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jkli1998/DRM/1dd943bd911f505ef5838c7b4d138ab3301e3fc0/maskrcnn_benchmark/data/datasets/evaluation/vg/zeroshot_triplet_new.pytorch -------------------------------------------------------------------------------- /maskrcnn_benchmark/data/datasets/evaluation/voc/__init__.py: -------------------------------------------------------------------------------- 1 | import logging 2 | 3 | from .voc_eval import do_voc_evaluation 4 | 5 | 6 | def voc_evaluation(cfg, dataset, predictions, output_folder, logger, box_only, **_): 7 | if box_only: 8 | logger.warning("voc evaluation doesn't support box_only, ignored.") 9 | logger.info("performing voc evaluation, ignored iou_types.") 10 | return do_voc_evaluation( 11 | dataset=dataset, 12 | predictions=predictions, 13 | output_folder=output_folder, 14 | logger=logger, 15 | ) 16 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/data/datasets/list_dataset.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | """ 3 | Simple dataset class that wraps a list of path names 4 | """ 5 | 6 | from PIL import Image 7 | 8 | from maskrcnn_benchmark.structures.bounding_box import BoxList 9 | 10 | 11 | class ListDataset(object): 12 | def __init__(self, image_lists, transforms=None): 13 | self.image_lists = image_lists 14 | self.transforms = transforms 15 | 16 | def __getitem__(self, item): 17 | img = Image.open(self.image_lists[item]).convert("RGB") 18 | 19 | # dummy target 20 | w, h = img.size 21 | target = BoxList([[0, 0, w, h]], img.size, mode="xyxy") 22 | 23 | if self.transforms is not None: 24 | img, target = self.transforms(img, target) 25 | 26 | return img, target 27 | 28 | def __len__(self): 29 | return len(self.image_lists) 30 | 31 | def get_img_info(self, item): 32 | """ 33 | Return the image dimensions for the image, without 34 | loading and pre-processing it 35 | """ 36 | pass 37 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/data/samplers/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | from .distributed import DistributedSampler 3 | from .grouped_batch_sampler import GroupedBatchSampler 4 | from .iteration_based_batch_sampler import IterationBasedBatchSampler 5 | 6 | __all__ = ["DistributedSampler", "GroupedBatchSampler", "IterationBasedBatchSampler"] 7 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/data/samplers/distributed.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | # Code is copy-pasted exactly as in torch.utils.data.distributed. 3 | # FIXME remove this once c10d fixes the bug it has 4 | import math 5 | import torch 6 | import torch.distributed as dist 7 | from torch.utils.data.sampler import Sampler 8 | 9 | 10 | class DistributedSampler(Sampler): 11 | """Sampler that restricts data loading to a subset of the dataset. 12 | It is especially useful in conjunction with 13 | :class:`torch.nn.parallel.DistributedDataParallel`. In such case, each 14 | process can pass a DistributedSampler instance as a DataLoader sampler, 15 | and load a subset of the original dataset that is exclusive to it. 16 | .. note:: 17 | Dataset is assumed to be of constant size. 18 | Arguments: 19 | dataset: Dataset used for sampling. 20 | num_replicas (optional): Number of processes participating in 21 | distributed training. 22 | rank (optional): Rank of the current process within num_replicas. 23 | """ 24 | 25 | def __init__(self, dataset, num_replicas=None, rank=None, shuffle=True): 26 | if num_replicas is None: 27 | if not dist.is_available(): 28 | raise RuntimeError("Requires distributed package to be available") 29 | num_replicas = dist.get_world_size() 30 | if rank is None: 31 | if not dist.is_available(): 32 | raise RuntimeError("Requires distributed package to be available") 33 | rank = dist.get_rank() 34 | self.dataset = dataset 35 | self.num_replicas = num_replicas 36 | self.rank = rank 37 | self.epoch = 0 38 | self.num_samples = int(math.ceil(len(self.dataset) * 1.0 / self.num_replicas)) 39 | self.total_size = self.num_samples * self.num_replicas 40 | self.shuffle = shuffle 41 | 42 | def __iter__(self): 43 | if self.shuffle: 44 | # deterministically shuffle based on epoch 45 | g = torch.Generator() 46 | g.manual_seed(self.epoch) 47 | indices = torch.randperm(len(self.dataset), generator=g).tolist() 48 | else: 49 | indices = torch.arange(len(self.dataset)).tolist() 50 | 51 | # add extra samples to make it evenly divisible 52 | indices += indices[: (self.total_size - len(indices))] 53 | assert len(indices) == self.total_size 54 | 55 | # subsample 56 | offset = self.num_samples * self.rank 57 | indices = indices[offset : offset + self.num_samples] 58 | assert len(indices) == self.num_samples 59 | 60 | return iter(indices) 61 | 62 | def __len__(self): 63 | return self.num_samples 64 | 65 | def set_epoch(self, epoch): 66 | self.epoch = epoch 67 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/data/samplers/iteration_based_batch_sampler.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | from torch.utils.data.sampler import BatchSampler 3 | 4 | 5 | class IterationBasedBatchSampler(BatchSampler): 6 | """ 7 | Wraps a BatchSampler, resampling from it until 8 | a specified number of iterations have been sampled 9 | """ 10 | 11 | def __init__(self, batch_sampler, num_iterations, start_iter=0): 12 | self.batch_sampler = batch_sampler 13 | self.num_iterations = num_iterations 14 | self.start_iter = start_iter 15 | 16 | def __iter__(self): 17 | iteration = self.start_iter 18 | while iteration <= self.num_iterations: 19 | # if the underlying sampler has a set_epoch method, like 20 | # DistributedSampler, used for making each process see 21 | # a different split of the dataset, then set it 22 | if hasattr(self.batch_sampler.sampler, "set_epoch"): 23 | self.batch_sampler.sampler.set_epoch(iteration) 24 | for batch in self.batch_sampler: 25 | iteration += 1 26 | if iteration > self.num_iterations: 27 | break 28 | yield batch 29 | 30 | def __len__(self): 31 | return self.num_iterations 32 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/data/transforms/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | from .transforms import Compose 3 | from .transforms import Resize 4 | from .transforms import RandomHorizontalFlip 5 | from .transforms import ToTensor 6 | from .transforms import Normalize 7 | 8 | from .build import build_transforms 9 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/engine/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/engine/trainer.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | import datetime 3 | import logging 4 | import time 5 | 6 | import numpy as np 7 | import copy 8 | import torch 9 | import torch.distributed as dist 10 | 11 | from maskrcnn_benchmark.utils.comm import get_world_size, all_gather 12 | from maskrcnn_benchmark.utils.metric_logger import MetricLogger 13 | 14 | from apex import amp 15 | 16 | def reduce_loss_dict(loss_dict): 17 | """ 18 | Reduce the loss dictionary from all processes so that process with rank 19 | 0 has the averaged results. Returns a dict with the same fields as 20 | loss_dict, after reduction. 21 | """ 22 | world_size = get_world_size() 23 | if world_size < 2: 24 | return loss_dict 25 | with torch.no_grad(): 26 | loss_names = [] 27 | all_losses = [] 28 | for k in sorted(loss_dict.keys()): 29 | loss_names.append(k) 30 | all_losses.append(loss_dict[k]) 31 | # all_losses = torch.stack(all_losses, dim=0) 32 | gather_loss_names = all_gather(loss_names) 33 | max_idx = np.argmax(np.array([len(x) for x in gather_loss_names])) 34 | if len(loss_names) < len(gather_loss_names[max_idx]): 35 | all_losses = [] 36 | for k in sorted(gather_loss_names[max_idx]): 37 | if k in loss_names: 38 | all_losses.append(loss_dict[k]) 39 | else: 40 | dup_idx = sorted(loss_dict.keys())[0] 41 | all_losses.append(copy.deepcopy(loss_dict[dup_idx].detach())) 42 | all_losses = torch.stack(all_losses, dim=0) 43 | dist.reduce(all_losses, dst=0) 44 | if dist.get_rank() == 0: 45 | # only main process gets accumulated, so only divide by 46 | # world_size in this case 47 | all_losses /= world_size 48 | reduced_losses = {k: v for k, v in zip(loss_names, all_losses)} 49 | return reduced_losses 50 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/extra/get_your_own_group/basic_for_all_test.py: -------------------------------------------------------------------------------- 1 | '''predicate name and list''' 2 | predicate_lists = ['__background__', 'above', 'across', 'against', 'along', 'and', 'at', 'attached to', 'behind', 'belonging to', 'between', 'carrying', 'covered in', 'covering', 'eating', 'flying in', 'for', 'from', 'growing on', 'hanging from', 'has', 'holding', 'in', 'in front of', 'laying on', 'looking at', 'lying on', 'made of', 'mounted on', 'near', 'of', 'on', 'on back of', 'over', 'painted on', 'parked on', 'part of', 'playing', 'riding', 'says', 'sitting on', 'standing on', 'to', 'under', 'using', 'walking in', 'walking on', 'watching', 'wearing', 'wears', 'with'] 3 | predicate_dict = {'__background__': 0, 'above': 1, 'across': 2, 'against': 3, 'along': 4, 'and': 5, 'at': 6, 'attached to': 7, 'behind': 8, 'belonging to': 9, 'between': 10, 'carrying': 11, 'covered in': 12, 'covering': 13, 'eating': 14, 'flying in': 15, 'for': 16, 'from': 17, 'growing on': 18, 'hanging from': 19, 'has': 20, 'holding': 21, 'in': 22, 'in front of': 23, 'laying on': 24, 'looking at': 25, 'lying on': 26, 'made of': 27, 'mounted on': 28, 'near': 29, 'of': 30, 'on': 31, 'on back of': 32, 'over': 33, 'painted on': 34, 'parked on': 35, 'part of': 36, 'playing': 37, 'riding': 38, 'says': 39, 'sitting on': 40, 'standing on': 41, 'to': 42, 'under': 43, 'using': 44, 'walking in': 45, 'walking on': 46, 'watching': 47, 'wearing': 48, 'wears': 49, 'with': 50} 4 | 5 | indeed_train_sor = [['on', 109355], ['has', 67144], ['wearing', 47326], ['of', 31347], 6 | ['in', 21748], ['near', 15300], ['behind', 10011], ['with', 11059], ['holding', 10764], 7 | ['above', 6712], ['sitting on', 5086], ['wears', 4810], ['under', 3757], ['riding', 4260], ['in front of', 3167], ['standing on', 2273], ['at', 1829], ['carrying', 1603], ['attached to', 1413], ['walking on', 1225], 8 | ['over', 793], ['for', 809], ['looking at', 676], ['watching', 352], ['hanging from', 663], ['laying on', 752], ['eating', 565], ['and', 504], ['belonging to', 644], ['parked on', 601], ['using', 551], ['covering', 460], ['between', 394], ['along', 379], ['covered in', 397], ['part of', 429], ['lying on', 364], ['on back of', 333], ['to', 299], ['walking in', 270], ['mounted on', 234], ['across', 171], ['against', 208], ['from', 163], ['growing on', 157], ['painted on', 151], ['playing', 71], ['made of', 114], ['says', 44], ['flying in', 4]] -------------------------------------------------------------------------------- /maskrcnn_benchmark/image_retrieval/S2G-RETRIEVAL.md: -------------------------------------------------------------------------------- 1 | # Sentence-to-Graph Retrieval (S2G) 2 | 3 | Forgive me, this part of code is ugly and less organized. 4 | 5 | ## Preprocessing 6 | 7 | Run the ```maskrcnn_benchmark/image_retrieval/preprocessing.py``` to process the annotations and checkpoints, where ```detected_path``` should be set to the corresponding checkpoints you want to use, ```vg_data, vg_dict, vg_info``` should have already downloaded if you followed DATASET.md, ```cap_graph``` is the ground-truth captions and generated sentence graphs (you can download it from [here](https://onedrive.live.com/embed?cid=22376FFAD72C4B64&resid=22376FFAD72C4B64%21779999&authkey=AGW0Wxjb1JSDFnc)). We use [SceneGraphParser](https://github.com/vacancy/SceneGraphParser) to generate these sentence graphs. 8 | 9 | You also need to set the ```cap_graph``` PATH and ```vg_dict``` PATH in ```maskrcnn_benchmark/image_retrieval/dataloader.py``` manually. 10 | 11 | ## Training and Evaluation 12 | 13 | Run the ```tools/image_retrieval_main.py``` for both training and evaluation. 14 | 15 | To load the generated scene graphs of the given SGG checkpoints, you need to manually set ```sg_train_path``` and ```sg_test_path``` in ```tools/image_retrieval_main.py```, which means you need to evaluate your model on **both training and testing set** to get the generated crude scene graphs. Our evaluation code will automatically saves the crude SGGs into ```checkpoints/MODEL_NAME/inference/VG_stanford_filtered_wth_attribute_test/``` or ```checkpoints/MODEL_NAME/inference/VG_stanford_filtered_wth_attribute_train/```, which will be further processed to generate the input of ```sg_train_path``` and ```sg_test_path``` by our preprocessing code ```maskrcnn_benchmark/image_retrieval/preprocessing.py```. 16 | 17 | ## Results 18 | 19 | Sentence-to-Graph Retrieval (S2G) results are given in the paper [Unbiased Scene Graph Generation from Biased Training](https://arxiv.org/abs/2002.11949): 20 | 21 | ![alt text](../../demo/TDE_Results3.png "from 'Unbiased Scene Graph Generation from Biased Training'") 22 | 23 | ## Acknowledgement 24 | 25 | Since I lost part of the code when I merged several jupyter notes into the preprocessing.py files, the "image_graph" and "text_graph" are missing in the original txt_img_sg dictionary. Thanks to the [Haeyong Kang](https://scholar.google.com/citations?user=v_tUj4oAAAAJ&hl=ko) from KAIST, he filled in the missing part of preprocessing.py. 26 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/image_retrieval/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/image_retrieval/evaluation.py: -------------------------------------------------------------------------------- 1 | from maskrcnn_benchmark.utils.env import setup_environment # noqa F401 isort:skip 2 | 3 | import argparse 4 | import os 5 | import time 6 | import datetime 7 | import json 8 | import random 9 | 10 | import torch 11 | import torch.nn as nn 12 | import torch.nn.functional as F 13 | from torch.nn.utils import clip_grad_norm_ 14 | import torch.utils.data as data 15 | from torch.nn.utils import weight_norm 16 | from tqdm import tqdm 17 | 18 | from maskrcnn_benchmark.config import cfg 19 | from maskrcnn_benchmark.data import make_data_loader 20 | from maskrcnn_benchmark.solver import make_lr_scheduler 21 | from maskrcnn_benchmark.solver import make_optimizer 22 | from maskrcnn_benchmark.engine.trainer import reduce_loss_dict 23 | from maskrcnn_benchmark.engine.inference import inference 24 | from maskrcnn_benchmark.modeling.detector import build_detection_model 25 | from maskrcnn_benchmark.utils.checkpoint import DetectronCheckpointer 26 | from maskrcnn_benchmark.utils.checkpoint import clip_grad_norm 27 | from maskrcnn_benchmark.utils.collect_env import collect_env_info 28 | from maskrcnn_benchmark.utils.comm import synchronize, get_rank, all_gather 29 | from maskrcnn_benchmark.utils.imports import import_file 30 | from maskrcnn_benchmark.utils.logger import setup_logger, debug_print 31 | from maskrcnn_benchmark.utils.miscellaneous import mkdir, save_config 32 | from maskrcnn_benchmark.utils.metric_logger import MetricLogger 33 | 34 | def evaluator(logger, input_lists): 35 | cat_data = [] 36 | for item in input_lists: 37 | cat_data.append(item[0]) 38 | # shape [num_image, 2, hidden_dim] 39 | cat_data = torch.cat(cat_data, dim=0).squeeze(2) 40 | 41 | similarity = cat_data[:, 0, :] @ (cat_data[:, 1, :].transpose(0,1)) # img to txt 42 | similarity = similarity.transpose(0,1) # txt to img 43 | 44 | pred_rank = (similarity > similarity.diag().view(-1, 1)).sum(-1) 45 | 46 | num_sample = pred_rank.shape[0] 47 | thres = [1, 5, 10, 20, 50, 100] 48 | for k in thres: 49 | logger.info('Recall @ %d: %.4f; ' % (k, float((pred_rank= 0)).float() * term2 * (1 - alpha) 53 | 54 | 55 | class SigmoidFocalLoss(nn.Module): 56 | def __init__(self, gamma, alpha): 57 | super(SigmoidFocalLoss, self).__init__() 58 | self.gamma = gamma 59 | self.alpha = alpha 60 | 61 | def forward(self, logits, targets): 62 | device = logits.device 63 | if logits.is_cuda: 64 | loss_func = sigmoid_focal_loss_cuda 65 | else: 66 | loss_func = sigmoid_focal_loss_cpu 67 | 68 | loss = loss_func(logits, targets, self.gamma, self.alpha) 69 | return loss.sum() 70 | 71 | def __repr__(self): 72 | tmpstr = self.__class__.__name__ + "(" 73 | tmpstr += "gamma=" + str(self.gamma) 74 | tmpstr += ", alpha=" + str(self.alpha) 75 | tmpstr += ")" 76 | return tmpstr 77 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/layers/smooth_l1_loss.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | import torch 3 | 4 | 5 | # TODO maybe push this to nn? 6 | def smooth_l1_loss(input, target, beta=1. / 9, size_average=True): 7 | """ 8 | very similar to the smooth_l1_loss from pytorch, but with 9 | the extra beta parameter 10 | """ 11 | n = torch.abs(input - target) 12 | cond = n < beta 13 | loss = torch.where(cond, 0.5 * n ** 2 / beta, n - 0.5 * beta) 14 | if size_average: 15 | return loss.mean() 16 | return loss.sum() 17 | 18 | 19 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jkli1998/DRM/1dd943bd911f505ef5838c7b4d138ab3301e3fc0/maskrcnn_benchmark/modeling/__init__.py -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/backbone/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | from .backbone import build_backbone 3 | from . import fbnet 4 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/backbone/vgg.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | """ 3 | Variant of the resnet module that takes cfg as an argument. 4 | Example usage. Strings may be specified in the config file. 5 | model = ResNet( 6 | "StemWithFixedBatchNorm", 7 | "BottleneckWithFixedBatchNorm", 8 | "ResNet50StagesTo4", 9 | ) 10 | OR: 11 | model = ResNet( 12 | "StemWithGN", 13 | "BottleneckWithGN", 14 | "ResNet50StagesTo4", 15 | ) 16 | Custom implementations may be written in user code and hooked in via the 17 | `register_*` functions. 18 | """ 19 | from collections import namedtuple 20 | 21 | import torch 22 | import torch.nn.functional as F 23 | from torch import nn 24 | 25 | import torchvision.models as models 26 | from maskrcnn_benchmark.layers import FrozenBatchNorm2d 27 | from maskrcnn_benchmark.layers import Conv2d 28 | from maskrcnn_benchmark.layers import DFConv2d 29 | from maskrcnn_benchmark.modeling.make_layers import group_norm 30 | from maskrcnn_benchmark.utils.registry import Registry 31 | 32 | 33 | class VGG16(nn.Module): 34 | def __init__(self, cfg): 35 | super(VGG16, self).__init__() 36 | vgg = models.vgg16(pretrained=True) 37 | self.conv_body = nn.Sequential(*list(vgg.features._modules.values())[:-1]) 38 | 39 | def forward(self, x): 40 | output = [] 41 | output.append(self.conv_body(x)) 42 | return output 43 | 44 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/balanced_positive_negative_sampler.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | import torch 3 | 4 | 5 | class BalancedPositiveNegativeSampler(object): 6 | """ 7 | This class samples batches, ensuring that they contain a fixed proportion of positives 8 | """ 9 | 10 | def __init__(self, batch_size_per_image, positive_fraction): 11 | """ 12 | Arguments: 13 | batch_size_per_image (int): number of elements to be selected per image 14 | positive_fraction (float): percentace of positive elements per batch 15 | """ 16 | self.batch_size_per_image = batch_size_per_image 17 | self.positive_fraction = positive_fraction 18 | 19 | def __call__(self, matched_idxs): 20 | """ 21 | Arguments: 22 | matched idxs: list of tensors containing -1, 0 or positive values. 23 | Each tensor corresponds to a specific image. 24 | -1 values are ignored, 0 are considered as negatives and > 0 as 25 | positives. 26 | 27 | Returns: 28 | pos_idx (list[tensor]) 29 | neg_idx (list[tensor]) 30 | 31 | Returns two lists of binary masks for each image. 32 | The first list contains the positive elements that were selected, 33 | and the second list the negative example. 34 | """ 35 | pos_idx = [] 36 | neg_idx = [] 37 | for matched_idxs_per_image in matched_idxs: 38 | positive = torch.nonzero(matched_idxs_per_image >= 1).squeeze(1) 39 | negative = torch.nonzero(matched_idxs_per_image == 0).squeeze(1) 40 | 41 | num_pos = int(self.batch_size_per_image * self.positive_fraction) 42 | # protect against not enough positive examples 43 | num_pos = min(positive.numel(), num_pos) 44 | num_neg = self.batch_size_per_image - num_pos 45 | # protect against not enough negative examples 46 | num_neg = min(negative.numel(), num_neg) 47 | 48 | # randomly select positive and negative examples 49 | perm1 = torch.randperm(positive.numel(), device=positive.device)[:num_pos] 50 | perm2 = torch.randperm(negative.numel(), device=negative.device)[:num_neg] 51 | 52 | pos_idx_per_image = positive[perm1] 53 | neg_idx_per_image = negative[perm2] 54 | 55 | # create binary mask from indices 56 | pos_idx_per_image_mask = torch.zeros_like( 57 | matched_idxs_per_image, dtype=torch.uint8 58 | ) 59 | neg_idx_per_image_mask = torch.zeros_like( 60 | matched_idxs_per_image, dtype=torch.uint8 61 | ) 62 | pos_idx_per_image_mask[pos_idx_per_image] = 1 63 | neg_idx_per_image_mask[neg_idx_per_image] = 1 64 | 65 | pos_idx.append(pos_idx_per_image_mask) 66 | neg_idx.append(neg_idx_per_image_mask) 67 | 68 | return pos_idx, neg_idx 69 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/detector/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | from .detectors import build_detection_model 3 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/detector/detectors.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | from .generalized_rcnn import GeneralizedRCNN 3 | 4 | 5 | _DETECTION_META_ARCHITECTURES = {"GeneralizedRCNN": GeneralizedRCNN} 6 | 7 | 8 | def build_detection_model(cfg): 9 | meta_arch = _DETECTION_META_ARCHITECTURES[cfg.MODEL.META_ARCHITECTURE] 10 | return meta_arch(cfg) 11 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/detector/generalized_rcnn.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | """ 3 | Implements the Generalized R-CNN framework 4 | """ 5 | 6 | import torch 7 | from torch import nn 8 | 9 | from maskrcnn_benchmark.structures.image_list import to_image_list 10 | 11 | from ..backbone import build_backbone 12 | from ..rpn.rpn import build_rpn 13 | from ..roi_heads.roi_heads import build_roi_heads 14 | 15 | 16 | class GeneralizedRCNN(nn.Module): 17 | def __init__(self, cfg): 18 | super(GeneralizedRCNN, self).__init__() 19 | self.cfg = cfg.clone() 20 | self.backbone = build_backbone(cfg) 21 | self.rpn = build_rpn(cfg, self.backbone.out_channels) 22 | self.roi_heads = build_roi_heads(cfg, self.backbone.out_channels) 23 | 24 | def forward(self, images, targets=None, logger=None): 25 | if self.training and targets is None: 26 | raise ValueError("In training mode, targets should be passed") 27 | images = to_image_list(images) 28 | if self.cfg.MODEL.STAGE == "stage1": 29 | features = self.backbone(images.tensors) 30 | if self.cfg.DATASETS.DIR_LOAD_PRECOMPUTE_DETECTION_BOX and self.training: 31 | proposals, proposal_losses = self.rpn(images, features, targets[0]) 32 | else: 33 | proposals, proposal_losses = self.rpn(images, features, targets) 34 | else: 35 | with torch.no_grad(): 36 | features = self.backbone(images.tensors) 37 | if self.cfg.DATASETS.DIR_LOAD_PRECOMPUTE_DETECTION_BOX and self.training: 38 | proposals, proposal_losses = self.rpn(images, features, targets[0]) 39 | else: 40 | proposals, proposal_losses = self.rpn(images, features, targets) 41 | 42 | x, result, detector_losses = self.roi_heads(features, proposals, targets, logger) 43 | 44 | 45 | if self.training: 46 | losses = {} 47 | losses.update(detector_losses) 48 | if not self.cfg.MODEL.RELATION_ON: 49 | # During the relationship training stage, the rpn_head should be fixed, and no loss. 50 | losses.update(proposal_losses) 51 | return losses 52 | 53 | return result 54 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/registry.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | 3 | from maskrcnn_benchmark.utils.registry import Registry 4 | 5 | BACKBONES = Registry() 6 | RPN_HEADS = Registry() 7 | ROI_BOX_FEATURE_EXTRACTORS = Registry() 8 | ROI_BOX_PREDICTOR = Registry() 9 | ROI_ATTRIBUTE_FEATURE_EXTRACTORS = Registry() 10 | ROI_ATTRIBUTE_PREDICTOR = Registry() 11 | ROI_KEYPOINT_FEATURE_EXTRACTORS = Registry() 12 | ROI_KEYPOINT_PREDICTOR = Registry() 13 | ROI_MASK_FEATURE_EXTRACTORS = Registry() 14 | ROI_MASK_PREDICTOR = Registry() 15 | ROI_RELATION_FEATURE_EXTRACTORS = Registry() 16 | ROI_RELATION_PREDICTOR = Registry() 17 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/roi_heads/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jkli1998/DRM/1dd943bd911f505ef5838c7b4d138ab3301e3fc0/maskrcnn_benchmark/modeling/roi_heads/__init__.py -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/roi_heads/attribute_head/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jkli1998/DRM/1dd943bd911f505ef5838c7b4d138ab3301e3fc0/maskrcnn_benchmark/modeling/roi_heads/attribute_head/__init__.py -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/roi_heads/attribute_head/roi_attribute_predictors.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | from maskrcnn_benchmark.modeling import registry 3 | from torch import nn 4 | 5 | 6 | @registry.ROI_ATTRIBUTE_PREDICTOR.register("FastRCNNPredictor") 7 | class FastRCNNPredictor(nn.Module): 8 | def __init__(self, config, in_channels): 9 | super(FastRCNNPredictor, self).__init__() 10 | assert in_channels is not None 11 | num_inputs = in_channels 12 | 13 | num_attributes = cfg.MODEL.ROI_ATTRIBUTE_HEAD.NUM_ATTRIBUTES 14 | self.avgpool = nn.AdaptiveAvgPool2d(1) 15 | self.att_score = nn.Linear(num_inputs, num_attributes) 16 | 17 | nn.init.normal_(self.att_score.weight, mean=0, std=0.01) 18 | nn.init.constant_(self.att_score.bias, 0) 19 | 20 | def forward(self, x): 21 | x = self.avgpool(x) 22 | x = x.view(x.size(0), -1) 23 | att_logit = self.att_score(x) 24 | 25 | return att_logit 26 | 27 | 28 | @registry.ROI_ATTRIBUTE_PREDICTOR.register("FPNPredictor") 29 | class FPNPredictor(nn.Module): 30 | def __init__(self, cfg, in_channels): 31 | super(FPNPredictor, self).__init__() 32 | num_attributes = cfg.MODEL.ROI_ATTRIBUTE_HEAD.NUM_ATTRIBUTES 33 | representation_size = in_channels 34 | 35 | self.att_score = nn.Linear(representation_size, num_attributes) 36 | 37 | nn.init.normal_(self.att_score.weight, std=0.01) 38 | nn.init.constant_(self.att_score.bias, 0) 39 | 40 | def forward(self, x): 41 | if x.ndimension() == 4: 42 | assert list(x.shape[2:]) == [1, 1] 43 | x = x.view(x.size(0), -1) 44 | 45 | att_logit = self.att_score(x) 46 | 47 | return att_logit 48 | 49 | 50 | def make_roi_attribute_predictor(cfg, in_channels): 51 | func = registry.ROI_ATTRIBUTE_PREDICTOR[cfg.MODEL.ROI_ATTRIBUTE_HEAD.PREDICTOR] 52 | return func(cfg, in_channels) 53 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/roi_heads/box_head/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jkli1998/DRM/1dd943bd911f505ef5838c7b4d138ab3301e3fc0/maskrcnn_benchmark/modeling/roi_heads/box_head/__init__.py -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/roi_heads/keypoint_head/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jkli1998/DRM/1dd943bd911f505ef5838c7b4d138ab3301e3fc0/maskrcnn_benchmark/modeling/roi_heads/keypoint_head/__init__.py -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/roi_heads/keypoint_head/keypoint_head.py: -------------------------------------------------------------------------------- 1 | import torch 2 | 3 | from .roi_keypoint_feature_extractors import make_roi_keypoint_feature_extractor 4 | from .roi_keypoint_predictors import make_roi_keypoint_predictor 5 | from .inference import make_roi_keypoint_post_processor 6 | from .loss import make_roi_keypoint_loss_evaluator 7 | 8 | 9 | class ROIKeypointHead(torch.nn.Module): 10 | def __init__(self, cfg, in_channels): 11 | super(ROIKeypointHead, self).__init__() 12 | self.cfg = cfg.clone() 13 | self.feature_extractor = make_roi_keypoint_feature_extractor(cfg, in_channels) 14 | self.predictor = make_roi_keypoint_predictor( 15 | cfg, self.feature_extractor.out_channels) 16 | self.post_processor = make_roi_keypoint_post_processor(cfg) 17 | self.loss_evaluator = make_roi_keypoint_loss_evaluator(cfg) 18 | 19 | def forward(self, features, proposals, targets=None): 20 | """ 21 | Arguments: 22 | features (list[Tensor]): feature-maps from possibly several levels 23 | proposals (list[BoxList]): proposal boxes 24 | targets (list[BoxList], optional): the ground-truth targets. 25 | 26 | Returns: 27 | x (Tensor): the result of the feature extractor 28 | proposals (list[BoxList]): during training, the original proposals 29 | are returned. During testing, the predicted boxlists are returned 30 | with the `mask` field set 31 | losses (dict[Tensor]): During training, returns the losses for the 32 | head. During testing, returns an empty dict. 33 | """ 34 | if self.training: 35 | with torch.no_grad(): 36 | proposals = self.loss_evaluator.subsample(proposals, targets) 37 | 38 | x = self.feature_extractor(features, proposals) 39 | kp_logits = self.predictor(x) 40 | 41 | if not self.training: 42 | result = self.post_processor(kp_logits, proposals) 43 | return x, result, {} 44 | 45 | loss_kp = self.loss_evaluator(proposals, kp_logits) 46 | 47 | return x, proposals, dict(loss_kp=loss_kp) 48 | 49 | 50 | def build_roi_keypoint_head(cfg, in_channels): 51 | return ROIKeypointHead(cfg, in_channels) 52 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/roi_heads/keypoint_head/roi_keypoint_feature_extractors.py: -------------------------------------------------------------------------------- 1 | from torch import nn 2 | from torch.nn import functional as F 3 | 4 | from maskrcnn_benchmark.modeling import registry 5 | from maskrcnn_benchmark.modeling.poolers import Pooler 6 | 7 | from maskrcnn_benchmark.layers import Conv2d 8 | 9 | 10 | @registry.ROI_KEYPOINT_FEATURE_EXTRACTORS.register("KeypointRCNNFeatureExtractor") 11 | class KeypointRCNNFeatureExtractor(nn.Module): 12 | def __init__(self, cfg, in_channels): 13 | super(KeypointRCNNFeatureExtractor, self).__init__() 14 | 15 | resolution = cfg.MODEL.ROI_KEYPOINT_HEAD.POOLER_RESOLUTION 16 | scales = cfg.MODEL.ROI_KEYPOINT_HEAD.POOLER_SCALES 17 | sampling_ratio = cfg.MODEL.ROI_KEYPOINT_HEAD.POOLER_SAMPLING_RATIO 18 | pooler = Pooler( 19 | output_size=(resolution, resolution), 20 | scales=scales, 21 | sampling_ratio=sampling_ratio, 22 | ) 23 | self.pooler = pooler 24 | 25 | input_features = in_channels 26 | layers = cfg.MODEL.ROI_KEYPOINT_HEAD.CONV_LAYERS 27 | next_feature = input_features 28 | self.blocks = [] 29 | for layer_idx, layer_features in enumerate(layers, 1): 30 | layer_name = "conv_fcn{}".format(layer_idx) 31 | module = Conv2d(next_feature, layer_features, 3, stride=1, padding=1) 32 | nn.init.kaiming_normal_(module.weight, mode="fan_out", nonlinearity="relu") 33 | nn.init.constant_(module.bias, 0) 34 | self.add_module(layer_name, module) 35 | next_feature = layer_features 36 | self.blocks.append(layer_name) 37 | self.out_channels = layer_features 38 | 39 | def forward(self, x, proposals): 40 | x = self.pooler(x, proposals) 41 | for layer_name in self.blocks: 42 | x = F.relu(getattr(self, layer_name)(x)) 43 | return x 44 | 45 | 46 | def make_roi_keypoint_feature_extractor(cfg, in_channels): 47 | func = registry.ROI_KEYPOINT_FEATURE_EXTRACTORS[ 48 | cfg.MODEL.ROI_KEYPOINT_HEAD.FEATURE_EXTRACTOR 49 | ] 50 | return func(cfg, in_channels) 51 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/roi_heads/keypoint_head/roi_keypoint_predictors.py: -------------------------------------------------------------------------------- 1 | from torch import nn 2 | 3 | from maskrcnn_benchmark import layers 4 | from maskrcnn_benchmark.modeling import registry 5 | 6 | 7 | @registry.ROI_KEYPOINT_PREDICTOR.register("KeypointRCNNPredictor") 8 | class KeypointRCNNPredictor(nn.Module): 9 | def __init__(self, cfg, in_channels): 10 | super(KeypointRCNNPredictor, self).__init__() 11 | input_features = in_channels 12 | num_keypoints = cfg.MODEL.ROI_KEYPOINT_HEAD.NUM_CLASSES 13 | deconv_kernel = 4 14 | self.kps_score_lowres = layers.ConvTranspose2d( 15 | input_features, 16 | num_keypoints, 17 | deconv_kernel, 18 | stride=2, 19 | padding=deconv_kernel // 2 - 1, 20 | ) 21 | nn.init.kaiming_normal_( 22 | self.kps_score_lowres.weight, mode="fan_out", nonlinearity="relu" 23 | ) 24 | nn.init.constant_(self.kps_score_lowres.bias, 0) 25 | self.up_scale = 2 26 | self.out_channels = num_keypoints 27 | 28 | def forward(self, x): 29 | x = self.kps_score_lowres(x) 30 | x = layers.interpolate( 31 | x, scale_factor=self.up_scale, mode="bilinear", align_corners=False 32 | ) 33 | return x 34 | 35 | 36 | def make_roi_keypoint_predictor(cfg, in_channels): 37 | func = registry.ROI_KEYPOINT_PREDICTOR[cfg.MODEL.ROI_KEYPOINT_HEAD.PREDICTOR] 38 | return func(cfg, in_channels) 39 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/roi_heads/mask_head/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jkli1998/DRM/1dd943bd911f505ef5838c7b4d138ab3301e3fc0/maskrcnn_benchmark/modeling/roi_heads/mask_head/__init__.py -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/roi_heads/mask_head/roi_mask_feature_extractors.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | from torch import nn 3 | from torch.nn import functional as F 4 | 5 | from ..box_head.roi_box_feature_extractors import ResNet50Conv5ROIFeatureExtractor 6 | from maskrcnn_benchmark.modeling import registry 7 | from maskrcnn_benchmark.modeling.poolers import Pooler 8 | from maskrcnn_benchmark.modeling.make_layers import make_conv3x3 9 | 10 | 11 | registry.ROI_MASK_FEATURE_EXTRACTORS.register( 12 | "ResNet50Conv5ROIFeatureExtractor", ResNet50Conv5ROIFeatureExtractor 13 | ) 14 | 15 | 16 | @registry.ROI_MASK_FEATURE_EXTRACTORS.register("MaskRCNNFPNFeatureExtractor") 17 | class MaskRCNNFPNFeatureExtractor(nn.Module): 18 | """ 19 | Heads for FPN for classification 20 | """ 21 | 22 | def __init__(self, cfg, in_channels): 23 | """ 24 | Arguments: 25 | num_classes (int): number of output classes 26 | input_size (int): number of channels of the input once it's flattened 27 | representation_size (int): size of the intermediate representation 28 | """ 29 | super(MaskRCNNFPNFeatureExtractor, self).__init__() 30 | 31 | resolution = cfg.MODEL.ROI_MASK_HEAD.POOLER_RESOLUTION 32 | scales = cfg.MODEL.ROI_MASK_HEAD.POOLER_SCALES 33 | sampling_ratio = cfg.MODEL.ROI_MASK_HEAD.POOLER_SAMPLING_RATIO 34 | pooler = Pooler( 35 | output_size=(resolution, resolution), 36 | scales=scales, 37 | sampling_ratio=sampling_ratio, 38 | ) 39 | input_size = in_channels 40 | self.pooler = pooler 41 | 42 | use_gn = cfg.MODEL.ROI_MASK_HEAD.USE_GN 43 | layers = cfg.MODEL.ROI_MASK_HEAD.CONV_LAYERS 44 | dilation = cfg.MODEL.ROI_MASK_HEAD.DILATION 45 | 46 | next_feature = input_size 47 | self.blocks = [] 48 | for layer_idx, layer_features in enumerate(layers, 1): 49 | layer_name = "mask_fcn{}".format(layer_idx) 50 | module = make_conv3x3( 51 | next_feature, layer_features, 52 | dilation=dilation, stride=1, use_gn=use_gn 53 | ) 54 | self.add_module(layer_name, module) 55 | next_feature = layer_features 56 | self.blocks.append(layer_name) 57 | self.out_channels = layer_features 58 | 59 | def forward(self, x, proposals): 60 | x = self.pooler(x, proposals) 61 | 62 | for layer_name in self.blocks: 63 | x = F.relu(getattr(self, layer_name)(x)) 64 | 65 | return x 66 | 67 | 68 | def make_roi_mask_feature_extractor(cfg, in_channels): 69 | func = registry.ROI_MASK_FEATURE_EXTRACTORS[ 70 | cfg.MODEL.ROI_MASK_HEAD.FEATURE_EXTRACTOR 71 | ] 72 | return func(cfg, in_channels) 73 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/roi_heads/mask_head/roi_mask_predictors.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | from torch import nn 3 | from torch.nn import functional as F 4 | 5 | from maskrcnn_benchmark.layers import Conv2d 6 | from maskrcnn_benchmark.layers import ConvTranspose2d 7 | from maskrcnn_benchmark.modeling import registry 8 | 9 | 10 | @registry.ROI_MASK_PREDICTOR.register("MaskRCNNC4Predictor") 11 | class MaskRCNNC4Predictor(nn.Module): 12 | def __init__(self, cfg, in_channels): 13 | super(MaskRCNNC4Predictor, self).__init__() 14 | num_classes = cfg.MODEL.ROI_BOX_HEAD.NUM_CLASSES 15 | dim_reduced = cfg.MODEL.ROI_MASK_HEAD.CONV_LAYERS[-1] 16 | num_inputs = in_channels 17 | 18 | self.conv5_mask = ConvTranspose2d(num_inputs, dim_reduced, 2, 2, 0) 19 | self.mask_fcn_logits = Conv2d(dim_reduced, num_classes, 1, 1, 0) 20 | 21 | for name, param in self.named_parameters(): 22 | if "bias" in name: 23 | nn.init.constant_(param, 0) 24 | elif "weight" in name: 25 | # Caffe2 implementation uses MSRAFill, which in fact 26 | # corresponds to kaiming_normal_ in PyTorch 27 | nn.init.kaiming_normal_(param, mode="fan_out", nonlinearity="relu") 28 | 29 | def forward(self, x): 30 | x = F.relu(self.conv5_mask(x)) 31 | return self.mask_fcn_logits(x) 32 | 33 | 34 | @registry.ROI_MASK_PREDICTOR.register("MaskRCNNConv1x1Predictor") 35 | class MaskRCNNConv1x1Predictor(nn.Module): 36 | def __init__(self, cfg, in_channels): 37 | super(MaskRCNNConv1x1Predictor, self).__init__() 38 | num_classes = cfg.MODEL.ROI_BOX_HEAD.NUM_CLASSES 39 | num_inputs = in_channels 40 | 41 | self.mask_fcn_logits = Conv2d(num_inputs, num_classes, 1, 1, 0) 42 | 43 | for name, param in self.named_parameters(): 44 | if "bias" in name: 45 | nn.init.constant_(param, 0) 46 | elif "weight" in name: 47 | # Caffe2 implementation uses MSRAFill, which in fact 48 | # corresponds to kaiming_normal_ in PyTorch 49 | nn.init.kaiming_normal_(param, mode="fan_out", nonlinearity="relu") 50 | 51 | def forward(self, x): 52 | return self.mask_fcn_logits(x) 53 | 54 | 55 | def make_roi_mask_predictor(cfg, in_channels): 56 | func = registry.ROI_MASK_PREDICTOR[cfg.MODEL.ROI_MASK_HEAD.PREDICTOR] 57 | return func(cfg, in_channels) 58 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/roi_heads/relation_head/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jkli1998/DRM/1dd943bd911f505ef5838c7b4d138ab3301e3fc0/maskrcnn_benchmark/modeling/roi_heads/relation_head/__init__.py -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/roi_heads/relation_head/utils_sample.py: -------------------------------------------------------------------------------- 1 | import torch 2 | import random 3 | import numpy as np 4 | 5 | """ 6 | class BalanceTripletSample(object): 7 | def __init__(self, statistics): 8 | self.sample_rate_list = self.generate_sample(statistics) 9 | 10 | @staticmethod 11 | def generate_sample(statistics): 12 | predicate_order_count = statistics['pred_matrix'] 13 | assert len(predicate_order_count) == 51 14 | median = np.median(predicate_order_count) 15 | out = [0 for _ in range(len(predicate_order_count))] 16 | for i in range(len(predicate_order_count)): 17 | if i == 0: 18 | out[i] = 0.0 19 | continue 20 | if predicate_order_count[i] > median: 21 | num = 1.0 * median / predicate_order_count[i] 22 | if num < 0.01: 23 | num = 0.01 24 | out[i] = num 25 | else: 26 | out[i] = 1.0 27 | return out 28 | 29 | def generate_cur_chosen_matrix(self, rel_labels): 30 | cur_chosen_matrix = torch.zeros_like(rel_labels, dtype=torch.bool) 31 | for i in range(len(rel_labels)): 32 | rel_tar = rel_labels[i].item() 33 | if rel_tar == 0: 34 | cur_chosen_matrix[i] = False 35 | else: 36 | if random.random() <= self.sample_rate_list[rel_tar]: 37 | cur_chosen_matrix[i] = True 38 | return cur_chosen_matrix 39 | """ 40 | 41 | 42 | class BalanceTripletSample(object): 43 | def __init__(self, cfg, statistics): 44 | self.cfg = cfg 45 | self.sample_rate_list = self.generate_sample(statistics) 46 | 47 | def generate_sample(self, statistics): 48 | down_rate = statistics['down_rate'].tolist() 49 | for i in range(len(down_rate)): 50 | if down_rate[i] < 0.01: 51 | down_rate[i] = 0.01 52 | down_rate[0] = 0.0 53 | return down_rate 54 | 55 | def generate_cur_chosen_matrix(self, rel_labels): 56 | cur_chosen_matrix = [] 57 | for i in range(len(rel_labels)): 58 | rel_tar = rel_labels[i].item() 59 | if rel_tar != 0: 60 | if random.random() <= self.sample_rate_list[rel_tar]: 61 | cur_chosen_matrix.append(i) 62 | else: 63 | cur_chosen_matrix.append(i) 64 | return cur_chosen_matrix 65 | 66 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/rpn/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | # from .rpn import build_rpn 3 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/rpn/retinanet/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jkli1998/DRM/1dd943bd911f505ef5838c7b4d138ab3301e3fc0/maskrcnn_benchmark/modeling/rpn/retinanet/__init__.py -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/rpn/utils.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | """ 3 | Utility functions minipulating the prediction layers 4 | """ 5 | 6 | from ..utils import cat 7 | 8 | import torch 9 | 10 | def permute_and_flatten(layer, N, A, C, H, W): 11 | layer = layer.view(N, -1, C, H, W) 12 | layer = layer.permute(0, 3, 4, 1, 2) 13 | layer = layer.reshape(N, -1, C) 14 | return layer 15 | 16 | 17 | def concat_box_prediction_layers(box_cls, box_regression): 18 | box_cls_flattened = [] 19 | box_regression_flattened = [] 20 | # for each feature level, permute the outputs to make them be in the 21 | # same format as the labels. Note that the labels are computed for 22 | # all feature levels concatenated, so we keep the same representation 23 | # for the objectness and the box_regression 24 | for box_cls_per_level, box_regression_per_level in zip( 25 | box_cls, box_regression 26 | ): 27 | N, AxC, H, W = box_cls_per_level.shape 28 | Ax4 = box_regression_per_level.shape[1] 29 | A = Ax4 // 4 30 | C = AxC // A 31 | box_cls_per_level = permute_and_flatten( 32 | box_cls_per_level, N, A, C, H, W 33 | ) 34 | box_cls_flattened.append(box_cls_per_level) 35 | 36 | box_regression_per_level = permute_and_flatten( 37 | box_regression_per_level, N, A, 4, H, W 38 | ) 39 | box_regression_flattened.append(box_regression_per_level) 40 | # concatenate on the first dimension (representing the feature levels), to 41 | # take into account the way the labels were generated (with all feature maps 42 | # being concatenated as well) 43 | box_cls = cat(box_cls_flattened, dim=1).reshape(-1, C) 44 | box_regression = cat(box_regression_flattened, dim=1).reshape(-1, 4) 45 | return box_cls, box_regression 46 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/utils.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | """ 3 | Miscellaneous utility functions 4 | """ 5 | 6 | import torch 7 | 8 | 9 | def cat(tensors, dim=0): 10 | """ 11 | Efficient version of torch.cat that avoids a copy if there is only a single element in a list 12 | """ 13 | assert isinstance(tensors, (list, tuple)) 14 | if len(tensors) == 1: 15 | return tensors[0] 16 | return torch.cat(tensors, dim) 17 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/solver/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | from .build import make_optimizer 3 | from .build import make_lr_scheduler 4 | from .lr_scheduler import WarmupMultiStepLR, WarmupReduceLROnPlateau 5 | 6 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/solver/build.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | import torch 3 | 4 | from .lr_scheduler import WarmupMultiStepLR, WarmupReduceLROnPlateau, WarmupCosStepLR 5 | 6 | 7 | def make_optimizer(cfg, model, logger, slow_heads=None, slow_ratio=5.0, rl_factor=1.0, fast_heads=None, fast_ratio=10.0): 8 | params = [] 9 | for key, value in model.named_parameters(): 10 | if not value.requires_grad: 11 | continue 12 | lr = cfg.SOLVER.BASE_LR 13 | weight_decay = cfg.SOLVER.WEIGHT_DECAY 14 | if "bias" in key: 15 | lr = cfg.SOLVER.BASE_LR * cfg.SOLVER.BIAS_LR_FACTOR 16 | weight_decay = cfg.SOLVER.WEIGHT_DECAY_BIAS 17 | if slow_heads is not None: 18 | for item in slow_heads: 19 | if item in key: 20 | logger.info("SLOW HEADS: {} is slow down by ratio of {}.".format(key, str(slow_ratio))) 21 | lr = lr / slow_ratio 22 | break 23 | params += [{"params": [value], "lr": lr * rl_factor, "weight_decay": weight_decay}] 24 | 25 | optimizer = torch.optim.SGD(params, lr=cfg.SOLVER.BASE_LR, momentum=cfg.SOLVER.MOMENTUM) 26 | return optimizer 27 | 28 | 29 | def make_lr_scheduler(cfg, optimizer, logger=None): 30 | if cfg.SOLVER.SCHEDULE.TYPE == "WarmupMultiStepLR": 31 | return WarmupMultiStepLR( 32 | optimizer, 33 | cfg.SOLVER.STEPS, 34 | cfg.SOLVER.GAMMA, 35 | warmup_factor=cfg.SOLVER.WARMUP_FACTOR, 36 | warmup_iters=cfg.SOLVER.WARMUP_ITERS, 37 | warmup_method=cfg.SOLVER.WARMUP_METHOD, 38 | ) 39 | 40 | elif cfg.SOLVER.SCHEDULE.TYPE == "WarmupReduceLROnPlateau": 41 | return WarmupReduceLROnPlateau( 42 | optimizer, 43 | cfg.SOLVER.SCHEDULE.FACTOR, 44 | warmup_factor=cfg.SOLVER.WARMUP_FACTOR, 45 | warmup_iters=cfg.SOLVER.WARMUP_ITERS, 46 | warmup_method=cfg.SOLVER.WARMUP_METHOD, 47 | patience=cfg.SOLVER.SCHEDULE.PATIENCE, 48 | threshold=cfg.SOLVER.SCHEDULE.THRESHOLD, 49 | cooldown=cfg.SOLVER.SCHEDULE.COOLDOWN, 50 | logger=logger, 51 | ) 52 | if cfg.SOLVER.SCHEDULE.TYPE == "WarmupCosStepLR": 53 | return WarmupCosStepLR( 54 | optimizer, 55 | warmup_factor=cfg.SOLVER.WARMUP_FACTOR, 56 | warmup_iters=cfg.SOLVER.WARMUP_ITERS, 57 | cosine_factor=cfg.SOLVER.COSINE_FACTOR, 58 | max_iteration=cfg.SOLVER.MAX_ITER, 59 | ) 60 | else: 61 | raise ValueError("Invalid Schedule Type") 62 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/structures/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jkli1998/DRM/1dd943bd911f505ef5838c7b4d138ab3301e3fc0/maskrcnn_benchmark/structures/__init__.py -------------------------------------------------------------------------------- /maskrcnn_benchmark/structures/image_list.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | from __future__ import division 3 | 4 | import torch 5 | 6 | 7 | class ImageList(object): 8 | """ 9 | Structure that holds a list of images (of possibly 10 | varying sizes) as a single tensor. 11 | This works by padding the images to the same size, 12 | and storing in a field the original sizes of each image 13 | """ 14 | 15 | def __init__(self, tensors, image_sizes): 16 | """ 17 | Arguments: 18 | tensors (tensor) 19 | image_sizes (list[tuple[int, int]]) 20 | """ 21 | self.tensors = tensors 22 | self.image_sizes = image_sizes 23 | 24 | def to(self, *args, **kwargs): 25 | cast_tensor = self.tensors.to(*args, **kwargs) 26 | return ImageList(cast_tensor, self.image_sizes) 27 | 28 | 29 | def to_image_list(tensors, size_divisible=0): 30 | """ 31 | tensors can be an ImageList, a torch.Tensor or 32 | an iterable of Tensors. It can't be a numpy array. 33 | When tensors is an iterable of Tensors, it pads 34 | the Tensors with zeros so that they have the same 35 | shape 36 | """ 37 | if isinstance(tensors, torch.Tensor) and size_divisible > 0: 38 | tensors = [tensors] 39 | 40 | if isinstance(tensors, ImageList): 41 | return tensors 42 | elif isinstance(tensors, torch.Tensor): 43 | # single tensor shape can be inferred 44 | if tensors.dim() == 3: 45 | tensors = tensors[None] 46 | assert tensors.dim() == 4 47 | image_sizes = [tensor.shape[-2:] for tensor in tensors] 48 | return ImageList(tensors, image_sizes) 49 | elif isinstance(tensors, (tuple, list)): 50 | max_size = tuple(max(s) for s in zip(*[img.shape for img in tensors])) 51 | 52 | # TODO Ideally, just remove this and let me model handle arbitrary 53 | # input sizs 54 | if size_divisible > 0: 55 | import math 56 | 57 | stride = size_divisible 58 | max_size = list(max_size) 59 | max_size[1] = int(math.ceil(max_size[1] / stride) * stride) 60 | max_size[2] = int(math.ceil(max_size[2] / stride) * stride) 61 | max_size = tuple(max_size) 62 | 63 | batch_shape = (len(tensors),) + max_size 64 | batched_imgs = tensors[0].new(*batch_shape).zero_() 65 | for img, pad_img in zip(tensors, batched_imgs): 66 | pad_img[: img.shape[0], : img.shape[1], : img.shape[2]].copy_(img) 67 | 68 | image_sizes = [im.shape[-2:] for im in tensors] 69 | 70 | return ImageList(batched_imgs, image_sizes) 71 | else: 72 | raise TypeError("Unsupported type for to_image_list: {}".format(type(tensors))) 73 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/utils/README.md: -------------------------------------------------------------------------------- 1 | # Utility functions 2 | 3 | This folder contain utility functions that are not used in the 4 | core library, but are useful for building models or training 5 | code using the config system. 6 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jkli1998/DRM/1dd943bd911f505ef5838c7b4d138ab3301e3fc0/maskrcnn_benchmark/utils/__init__.py -------------------------------------------------------------------------------- /maskrcnn_benchmark/utils/collect_env.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | import PIL 3 | 4 | from torch.utils.collect_env import get_pretty_env_info 5 | 6 | 7 | def get_pil_version(): 8 | return "\n Pillow ({})".format(PIL.__version__) 9 | 10 | 11 | def collect_env_info(): 12 | env_str = get_pretty_env_info() 13 | env_str += get_pil_version() 14 | return env_str 15 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/utils/cv2_util.py: -------------------------------------------------------------------------------- 1 | """ 2 | Module for cv2 utility functions and maintaining version compatibility 3 | between 3.x and 4.x 4 | """ 5 | import cv2 6 | 7 | 8 | def findContours(*args, **kwargs): 9 | """ 10 | Wraps cv2.findContours to maintain compatiblity between versions 11 | 3 and 4 12 | 13 | Returns: 14 | contours, hierarchy 15 | """ 16 | if cv2.__version__.startswith('4'): 17 | contours, hierarchy = cv2.findContours(*args, **kwargs) 18 | elif cv2.__version__.startswith('3'): 19 | _, contours, hierarchy = cv2.findContours(*args, **kwargs) 20 | else: 21 | raise AssertionError( 22 | 'cv2 must be either version 3 or 4 to call this method') 23 | 24 | return contours, hierarchy 25 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/utils/env.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | import os 3 | 4 | from maskrcnn_benchmark.utils.imports import import_file 5 | 6 | 7 | def setup_environment(): 8 | """Perform environment setup work. The default setup is a no-op, but this 9 | function allows the user to specify a Python source file that performs 10 | custom setup work that may be necessary to their computing environment. 11 | """ 12 | custom_module_path = os.environ.get("TORCH_DETECTRON_ENV_MODULE") 13 | if custom_module_path: 14 | setup_custom_environment(custom_module_path) 15 | else: 16 | # The default setup is a no-op 17 | pass 18 | 19 | 20 | def setup_custom_environment(custom_module_path): 21 | """Load custom environment setup from a Python source file and run the setup 22 | function. 23 | """ 24 | module = import_file("maskrcnn_benchmark.utils.env.custom_module", custom_module_path) 25 | assert hasattr(module, "setup_environment") and callable( 26 | module.setup_environment 27 | ), ( 28 | "Custom environment module defined in {} does not have the " 29 | "required callable attribute 'setup_environment'." 30 | ).format( 31 | custom_module_path 32 | ) 33 | module.setup_environment() 34 | 35 | 36 | # Force environment setup when this module is imported 37 | setup_environment() 38 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/utils/imports.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | import torch 3 | 4 | if torch._six.PY37: 5 | import importlib 6 | import importlib.util 7 | import sys 8 | 9 | 10 | # from https://stackoverflow.com/questions/67631/how-to-import-a-module-given-the-full-path?utm_medium=organic&utm_source=google_rich_qa&utm_campaign=google_rich_qa 11 | def import_file(module_name, file_path, make_importable=False): 12 | spec = importlib.util.spec_from_file_location(module_name, file_path) 13 | module = importlib.util.module_from_spec(spec) 14 | spec.loader.exec_module(module) 15 | if make_importable: 16 | sys.modules[module_name] = module 17 | return module 18 | else: 19 | import imp 20 | 21 | def import_file(module_name, file_path, make_importable=None): 22 | module = imp.load_source(module_name, file_path) 23 | return module 24 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/utils/logger.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | import logging 3 | import os 4 | import sys 5 | 6 | DEBUG_PRINT_ON = True 7 | 8 | def debug_print(logger, info): 9 | if DEBUG_PRINT_ON: 10 | logger.info('#'*20+' '+info+' '+'#'*20) 11 | 12 | def setup_logger(name, save_dir, distributed_rank, filename="log.txt"): 13 | logger = logging.getLogger(name) 14 | logger.setLevel(logging.DEBUG) 15 | # don't log results for the non-master process 16 | if distributed_rank > 0: 17 | return logger 18 | ch = logging.StreamHandler(stream=sys.stdout) 19 | ch.setLevel(logging.DEBUG) 20 | formatter = logging.Formatter("%(asctime)s %(name)s %(levelname)s: %(message)s") 21 | ch.setFormatter(formatter) 22 | logger.addHandler(ch) 23 | 24 | if save_dir: 25 | fh = logging.FileHandler(os.path.join(save_dir, filename)) 26 | fh.setLevel(logging.DEBUG) 27 | fh.setFormatter(formatter) 28 | logger.addHandler(fh) 29 | 30 | return logger 31 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/utils/metric_logger.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | from collections import defaultdict 3 | from collections import deque 4 | 5 | import torch 6 | 7 | 8 | class SmoothedValue(object): 9 | """Track a series of values and provide access to smoothed values over a 10 | window or the global series average. 11 | """ 12 | 13 | def __init__(self, window_size=20): 14 | self.deque = deque(maxlen=window_size) 15 | self.series = [] 16 | self.total = 0.0 17 | self.count = 0 18 | 19 | def update(self, value): 20 | self.deque.append(value) 21 | self.series.append(value) 22 | self.count += 1 23 | self.total += value 24 | 25 | @property 26 | def median(self): 27 | d = torch.tensor(list(self.deque)) 28 | return d.median().item() 29 | 30 | @property 31 | def avg(self): 32 | d = torch.tensor(list(self.deque)) 33 | return d.mean().item() 34 | 35 | @property 36 | def global_avg(self): 37 | return self.total / self.count 38 | 39 | 40 | class MetricLogger(object): 41 | def __init__(self, delimiter="\t"): 42 | self.meters = defaultdict(SmoothedValue) 43 | self.delimiter = delimiter 44 | 45 | def update(self, **kwargs): 46 | for k, v in kwargs.items(): 47 | if isinstance(v, torch.Tensor): 48 | v = v.item() 49 | assert isinstance(v, (float, int)) 50 | self.meters[k].update(v) 51 | 52 | def __getattr__(self, attr): 53 | if attr in self.meters: 54 | return self.meters[attr] 55 | if attr in self.__dict__: 56 | return self.__dict__[attr] 57 | raise AttributeError("'{}' object has no attribute '{}'".format( 58 | type(self).__name__, attr)) 59 | 60 | def __str__(self): 61 | loss_str = [] 62 | for name, meter in self.meters.items(): 63 | loss_str.append( 64 | "{}: {:.4f} ({:.4f})".format(name, meter.median, meter.global_avg) 65 | ) 66 | return self.delimiter.join(loss_str) 67 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/utils/miscellaneous.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | import errno 3 | import json 4 | import logging 5 | import os 6 | from .comm import is_main_process 7 | import numpy as np 8 | 9 | from maskrcnn_benchmark.structures.bounding_box import BoxList 10 | from maskrcnn_benchmark.structures.boxlist_ops import boxlist_iou 11 | 12 | def mkdir(path): 13 | try: 14 | os.makedirs(path) 15 | except OSError as e: 16 | if e.errno != errno.EEXIST: 17 | raise 18 | 19 | 20 | def save_labels(dataset_list, output_dir): 21 | if is_main_process(): 22 | logger = logging.getLogger(__name__) 23 | 24 | ids_to_labels = {} 25 | for dataset in dataset_list: 26 | if hasattr(dataset, 'categories'): 27 | ids_to_labels.update(dataset.categories) 28 | else: 29 | logger.warning("Dataset [{}] has no categories attribute, labels.json file won't be created".format( 30 | dataset.__class__.__name__)) 31 | 32 | if ids_to_labels: 33 | labels_file = os.path.join(output_dir, 'labels.json') 34 | logger.info("Saving labels mapping into {}".format(labels_file)) 35 | with open(labels_file, 'w') as f: 36 | json.dump(ids_to_labels, f, indent=2) 37 | 38 | 39 | def save_config(cfg, path): 40 | if is_main_process(): 41 | with open(path, 'w') as f: 42 | f.write(cfg.dump()) 43 | 44 | 45 | def intersect_2d(x1, x2): 46 | """ 47 | Given two arrays [m1, n], [m2,n], returns a [m1, m2] array where each entry is True if those 48 | rows match. 49 | :param x1: [m1, n] numpy array 50 | :param x2: [m2, n] numpy array 51 | :return: [m1, m2] bool array of the intersections 52 | """ 53 | if x1.shape[1] != x2.shape[1]: 54 | raise ValueError("Input arrays must have same #columns") 55 | 56 | # This performs a matrix multiplication-esque thing between the two arrays 57 | # Instead of summing, we want the equality, so we reduce in that way 58 | res = (x1[..., None] == x2.T[None, ...]).all(1) 59 | return res 60 | 61 | def argsort_desc(scores): 62 | """ 63 | Returns the indices that sort scores descending in a smart way 64 | :param scores: Numpy array of arbitrary size 65 | :return: an array of size [numel(scores), dim(scores)] where each row is the index you'd 66 | need to get the score. 67 | """ 68 | return np.column_stack(np.unravel_index(np.argsort(-scores.ravel()), scores.shape)) 69 | 70 | def bbox_overlaps(boxes1, boxes2): 71 | """ 72 | Parameters: 73 | boxes1 (m, 4) [List or np.array] : bounding boxes of (x1,y1,x2,y2) 74 | boxes2 (n, 4) [List or np.array] : bounding boxes of (x1,y1,x2,y2) 75 | Return: 76 | iou (m, n) [np.array] 77 | """ 78 | boxes1 = BoxList(boxes1, (0, 0), 'xyxy') 79 | boxes2 = BoxList(boxes2, (0, 0), 'xyxy') 80 | iou = boxlist_iou(boxes1, boxes2).cpu().numpy() 81 | return iou 82 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/utils/registry.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | 3 | 4 | def _register_generic(module_dict, module_name, module): 5 | assert module_name not in module_dict 6 | module_dict[module_name] = module 7 | 8 | 9 | class Registry(dict): 10 | ''' 11 | A helper class for managing registering modules, it extends a dictionary 12 | and provides a register functions. 13 | 14 | Eg. creeting a registry: 15 | some_registry = Registry({"default": default_module}) 16 | 17 | There're two ways of registering new modules: 18 | 1): normal way is just calling register function: 19 | def foo(): 20 | ... 21 | some_registry.register("foo_module", foo) 22 | 2): used as decorator when declaring the module: 23 | @some_registry.register("foo_module") 24 | @some_registry.register("foo_modeul_nickname") 25 | def foo(): 26 | ... 27 | 28 | Access of module is just like using a dictionary, eg: 29 | f = some_registry["foo_modeul"] 30 | ''' 31 | def __init__(self, *args, **kwargs): 32 | super(Registry, self).__init__(*args, **kwargs) 33 | 34 | def register(self, module_name, module=None): 35 | # used as function call 36 | if module is not None: 37 | _register_generic(self, module_name, module) 38 | return 39 | 40 | # used as decorator 41 | def register_fn(fn): 42 | _register_generic(self, module_name, fn) 43 | return fn 44 | 45 | return register_fn 46 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/utils/timer.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | 3 | 4 | import time 5 | import datetime 6 | 7 | 8 | class Timer(object): 9 | def __init__(self): 10 | self.reset() 11 | 12 | @property 13 | def average_time(self): 14 | return self.total_time / self.calls if self.calls > 0 else 0.0 15 | 16 | def tic(self): 17 | # using time.time instead of time.clock because time time.clock 18 | # does not normalize for multithreading 19 | self.start_time = time.time() 20 | 21 | def toc(self, average=True): 22 | self.add(time.time() - self.start_time) 23 | if average: 24 | return self.average_time 25 | else: 26 | return self.diff 27 | 28 | def add(self, time_diff): 29 | self.diff = time_diff 30 | self.total_time += self.diff 31 | self.calls += 1 32 | 33 | def reset(self): 34 | self.total_time = 0.0 35 | self.calls = 0 36 | self.start_time = 0.0 37 | self.diff = 0.0 38 | 39 | def avg_time_str(self): 40 | time_str = str(datetime.timedelta(seconds=self.average_time)) 41 | return time_str 42 | 43 | 44 | def get_time_str(time_diff): 45 | time_str = str(datetime.timedelta(seconds=time_diff)) 46 | return time_str 47 | -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | #!/usr/bin/env python 3 | 4 | import glob 5 | import os 6 | 7 | import torch 8 | from setuptools import find_packages 9 | from setuptools import setup 10 | from torch.utils.cpp_extension import CUDA_HOME 11 | from torch.utils.cpp_extension import CppExtension 12 | from torch.utils.cpp_extension import CUDAExtension 13 | 14 | requirements = ["torch", "torchvision"] 15 | 16 | 17 | def get_extensions(): 18 | this_dir = os.path.dirname(os.path.abspath(__file__)) 19 | extensions_dir = os.path.join(this_dir, "maskrcnn_benchmark", "csrc") 20 | 21 | main_file = glob.glob(os.path.join(extensions_dir, "*.cpp")) 22 | source_cpu = glob.glob(os.path.join(extensions_dir, "cpu", "*.cpp")) 23 | source_cuda = glob.glob(os.path.join(extensions_dir, "cuda", "*.cu")) 24 | 25 | sources = main_file + source_cpu 26 | extension = CppExtension 27 | 28 | extra_compile_args = {"cxx": []} 29 | define_macros = [] 30 | 31 | if (torch.cuda.is_available() and CUDA_HOME is not None) or os.getenv("FORCE_CUDA", "0") == "1": 32 | extension = CUDAExtension 33 | sources += source_cuda 34 | define_macros += [("WITH_CUDA", None)] 35 | extra_compile_args["nvcc"] = [ 36 | "-DCUDA_HAS_FP16=1", 37 | "-D__CUDA_NO_HALF_OPERATORS__", 38 | "-D__CUDA_NO_HALF_CONVERSIONS__", 39 | "-D__CUDA_NO_HALF2_OPERATORS__", 40 | ] 41 | 42 | sources = [os.path.join(extensions_dir, s) for s in sources] 43 | 44 | include_dirs = [extensions_dir] 45 | 46 | ext_modules = [ 47 | extension( 48 | "maskrcnn_benchmark._C", 49 | sources, 50 | include_dirs=include_dirs, 51 | define_macros=define_macros, 52 | extra_compile_args=extra_compile_args, 53 | ) 54 | ] 55 | 56 | return ext_modules 57 | 58 | 59 | setup( 60 | name="maskrcnn_benchmark", 61 | version="0.1", 62 | author="fmassa", 63 | url="https://github.com/facebookresearch/maskrcnn-benchmark", 64 | description="object detection in pytorch", 65 | packages=find_packages(exclude=("configs", "tests",)), 66 | # install_requires=requirements, 67 | ext_modules=get_extensions(), 68 | cmdclass={"build_ext": torch.utils.cpp_extension.BuildExtension}, 69 | ) 70 | -------------------------------------------------------------------------------- /tests/env_tests/env.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | 3 | import os 4 | 5 | 6 | def get_config_root_path(): 7 | ''' Path to configs for unit tests ''' 8 | # cur_file_dir is root/tests/env_tests 9 | cur_file_dir = os.path.dirname(os.path.abspath(os.path.realpath(__file__))) 10 | ret = os.path.dirname(os.path.dirname(cur_file_dir)) 11 | ret = os.path.join(ret, "configs") 12 | return ret 13 | -------------------------------------------------------------------------------- /tests/test_backbones.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | 3 | import unittest 4 | import copy 5 | import torch 6 | # import modules to to register backbones 7 | from maskrcnn_benchmark.modeling.backbone import build_backbone # NoQA 8 | from maskrcnn_benchmark.modeling import registry 9 | from maskrcnn_benchmark.config import cfg as g_cfg 10 | from utils import load_config 11 | 12 | 13 | # overwrite configs if specified, otherwise default config is used 14 | BACKBONE_CFGS = { 15 | "R-50-FPN": "e2e_faster_rcnn_R_50_FPN_1x.yaml", 16 | "R-101-FPN": "e2e_faster_rcnn_R_101_FPN_1x.yaml", 17 | "R-152-FPN": "e2e_faster_rcnn_R_101_FPN_1x.yaml", 18 | "R-50-FPN-RETINANET": "retinanet/retinanet_R-50-FPN_1x.yaml", 19 | "R-101-FPN-RETINANET": "retinanet/retinanet_R-101-FPN_1x.yaml", 20 | } 21 | 22 | 23 | class TestBackbones(unittest.TestCase): 24 | def test_build_backbones(self): 25 | ''' Make sure backbones run ''' 26 | 27 | self.assertGreater(len(registry.BACKBONES), 0) 28 | 29 | for name, backbone_builder in registry.BACKBONES.items(): 30 | print('Testing {}...'.format(name)) 31 | if name in BACKBONE_CFGS: 32 | cfg = load_config(BACKBONE_CFGS[name]) 33 | else: 34 | # Use default config if config file is not specified 35 | cfg = copy.deepcopy(g_cfg) 36 | backbone = backbone_builder(cfg) 37 | 38 | # make sures the backbone has `out_channels` 39 | self.assertIsNotNone( 40 | getattr(backbone, 'out_channels', None), 41 | 'Need to provide out_channels for backbone {}'.format(name) 42 | ) 43 | 44 | N, C_in, H, W = 2, 3, 224, 256 45 | input = torch.rand([N, C_in, H, W], dtype=torch.float32) 46 | out = backbone(input) 47 | for cur_out in out: 48 | self.assertEqual( 49 | cur_out.shape[:2], 50 | torch.Size([N, backbone.out_channels]) 51 | ) 52 | 53 | 54 | if __name__ == "__main__": 55 | unittest.main() 56 | -------------------------------------------------------------------------------- /tests/test_configs.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | 3 | import unittest 4 | import glob 5 | import os 6 | import utils 7 | 8 | 9 | class TestConfigs(unittest.TestCase): 10 | def test_configs_load(self): 11 | ''' Make sure configs are loadable ''' 12 | 13 | cfg_root_path = utils.get_config_root_path() 14 | files = glob.glob( 15 | os.path.join(cfg_root_path, "./**/*.yaml"), recursive=True) 16 | self.assertGreater(len(files), 0) 17 | 18 | for fn in files: 19 | print('Loading {}...'.format(fn)) 20 | utils.load_config_from_file(fn) 21 | 22 | 23 | if __name__ == "__main__": 24 | unittest.main() 25 | -------------------------------------------------------------------------------- /tests/test_metric_logger.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | import unittest 3 | 4 | from maskrcnn_benchmark.utils.metric_logger import MetricLogger 5 | 6 | 7 | class TestMetricLogger(unittest.TestCase): 8 | def test_update(self): 9 | meter = MetricLogger() 10 | for i in range(10): 11 | meter.update(metric=float(i)) 12 | 13 | m = meter.meters["metric"] 14 | self.assertEqual(m.count, 10) 15 | self.assertEqual(m.total, 45) 16 | self.assertEqual(m.median, 4) 17 | self.assertEqual(m.avg, 4.5) 18 | 19 | def test_no_attr(self): 20 | meter = MetricLogger() 21 | _ = meter.meters 22 | _ = meter.delimiter 23 | def broken(): 24 | _ = meter.not_existent 25 | self.assertRaises(AttributeError, broken) 26 | 27 | if __name__ == "__main__": 28 | unittest.main() 29 | -------------------------------------------------------------------------------- /tests/test_rpn_heads.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | 3 | import unittest 4 | import copy 5 | import torch 6 | # import modules to to register rpn heads 7 | from maskrcnn_benchmark.modeling.backbone import build_backbone # NoQA 8 | from maskrcnn_benchmark.modeling.rpn.rpn import build_rpn # NoQA 9 | from maskrcnn_benchmark.modeling import registry 10 | from maskrcnn_benchmark.config import cfg as g_cfg 11 | from utils import load_config 12 | 13 | 14 | # overwrite configs if specified, otherwise default config is used 15 | RPN_CFGS = { 16 | } 17 | 18 | 19 | class TestRPNHeads(unittest.TestCase): 20 | def test_build_rpn_heads(self): 21 | ''' Make sure rpn heads run ''' 22 | 23 | self.assertGreater(len(registry.RPN_HEADS), 0) 24 | 25 | in_channels = 64 26 | num_anchors = 10 27 | 28 | for name, builder in registry.RPN_HEADS.items(): 29 | print('Testing {}...'.format(name)) 30 | if name in RPN_CFGS: 31 | cfg = load_config(RPN_CFGS[name]) 32 | else: 33 | # Use default config if config file is not specified 34 | cfg = copy.deepcopy(g_cfg) 35 | 36 | rpn = builder(cfg, in_channels, num_anchors) 37 | 38 | N, C_in, H, W = 2, in_channels, 24, 32 39 | input = torch.rand([N, C_in, H, W], dtype=torch.float32) 40 | LAYERS = 3 41 | out = rpn([input] * LAYERS) 42 | self.assertEqual(len(out), 2) 43 | logits, bbox_reg = out 44 | for idx in range(LAYERS): 45 | self.assertEqual( 46 | logits[idx].shape, 47 | torch.Size([ 48 | input.shape[0], num_anchors, 49 | input.shape[2], input.shape[3], 50 | ]) 51 | ) 52 | self.assertEqual( 53 | bbox_reg[idx].shape, 54 | torch.Size([ 55 | logits[idx].shape[0], num_anchors * 4, 56 | logits[idx].shape[2], logits[idx].shape[3], 57 | ]), 58 | ) 59 | 60 | 61 | if __name__ == "__main__": 62 | unittest.main() 63 | -------------------------------------------------------------------------------- /tests/test_segmentation_mask.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | import unittest 3 | import torch 4 | from maskrcnn_benchmark.structures.segmentation_mask import SegmentationMask 5 | 6 | 7 | class TestSegmentationMask(unittest.TestCase): 8 | def __init__(self, method_name='runTest'): 9 | super(TestSegmentationMask, self).__init__(method_name) 10 | poly = [[[423.0, 306.5, 406.5, 277.0, 400.0, 271.5, 389.5, 277.0, 11 | 387.5, 292.0, 384.5, 295.0, 374.5, 220.0, 378.5, 210.0, 12 | 391.0, 200.5, 404.0, 199.5, 414.0, 203.5, 425.5, 221.0, 13 | 438.5, 297.0, 423.0, 306.5], 14 | [100, 100, 200, 100, 200, 200, 100, 200], 15 | ]] 16 | width = 640 17 | height = 480 18 | size = width, height 19 | 20 | self.P = SegmentationMask(poly, size, 'poly') 21 | self.M = SegmentationMask(poly, size, 'poly').convert('mask') 22 | 23 | def L1(self, A, B): 24 | diff = A.get_mask_tensor() - B.get_mask_tensor() 25 | diff = torch.sum(torch.abs(diff.float())).item() 26 | return diff 27 | 28 | def test_convert(self): 29 | M_hat = self.M.convert('poly').convert('mask') 30 | P_hat = self.P.convert('mask').convert('poly') 31 | 32 | diff_mask = self.L1(self.M, M_hat) 33 | diff_poly = self.L1(self.P, P_hat) 34 | self.assertTrue(diff_mask == diff_poly) 35 | self.assertTrue(diff_mask <= 8169.) 36 | self.assertTrue(diff_poly <= 8169.) 37 | 38 | def test_crop(self): 39 | box = [400, 250, 500, 300] # xyxy 40 | diff = self.L1(self.M.crop(box), self.P.crop(box)) 41 | self.assertTrue(diff <= 1.) 42 | 43 | def test_resize(self): 44 | new_size = 50, 25 45 | M_hat = self.M.resize(new_size) 46 | P_hat = self.P.resize(new_size) 47 | diff = self.L1(M_hat, P_hat) 48 | 49 | self.assertTrue(self.M.size == self.P.size) 50 | self.assertTrue(M_hat.size == P_hat.size) 51 | self.assertTrue(self.M.size != M_hat.size) 52 | self.assertTrue(diff <= 255.) 53 | 54 | def test_transpose(self): 55 | FLIP_LEFT_RIGHT = 0 56 | FLIP_TOP_BOTTOM = 1 57 | diff_hor = self.L1(self.M.transpose(FLIP_LEFT_RIGHT), 58 | self.P.transpose(FLIP_LEFT_RIGHT)) 59 | 60 | diff_ver = self.L1(self.M.transpose(FLIP_TOP_BOTTOM), 61 | self.P.transpose(FLIP_TOP_BOTTOM)) 62 | 63 | self.assertTrue(diff_hor <= 53250.) 64 | self.assertTrue(diff_ver <= 42494.) 65 | 66 | 67 | if __name__ == "__main__": 68 | 69 | unittest.main() 70 | -------------------------------------------------------------------------------- /tests/utils.py: -------------------------------------------------------------------------------- 1 | from __future__ import absolute_import, division, print_function, unicode_literals 2 | 3 | # Set up custom environment before nearly anything else is imported 4 | # NOTE: this should be the first import (no not reorder) 5 | from maskrcnn_benchmark.utils.env import setup_environment # noqa F401 isort:skip 6 | import env_tests.env as env_tests 7 | 8 | import os 9 | import copy 10 | 11 | from maskrcnn_benchmark.config import cfg as g_cfg 12 | 13 | 14 | def get_config_root_path(): 15 | return env_tests.get_config_root_path() 16 | 17 | 18 | def load_config(rel_path): 19 | ''' Load config from file path specified as path relative to config_root ''' 20 | cfg_path = os.path.join(env_tests.get_config_root_path(), rel_path) 21 | return load_config_from_file(cfg_path) 22 | 23 | 24 | def load_config_from_file(file_path): 25 | ''' Load config from file path specified as absolute path ''' 26 | ret = copy.deepcopy(g_cfg) 27 | ret.merge_from_file(file_path) 28 | return ret 29 | -------------------------------------------------------------------------------- /tools/cityscapes/instances2dict_with_polygons.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/python 2 | # 3 | # Convert instances from png files to a dictionary 4 | # This files is created according to https://github.com/facebookresearch/Detectron/issues/111 5 | 6 | from __future__ import print_function, absolute_import, division 7 | import os, sys 8 | 9 | sys.path.append( os.path.normpath( os.path.join( os.path.dirname( __file__ ) , '..' , 'helpers' ) ) ) 10 | from csHelpers import * 11 | 12 | # Cityscapes imports 13 | from cityscapesscripts.evaluation.instance import * 14 | from cityscapesscripts.helpers.csHelpers import * 15 | import cv2 16 | from maskrcnn_benchmark.utils import cv2_util 17 | 18 | 19 | def instances2dict_with_polygons(imageFileList, verbose=False): 20 | imgCount = 0 21 | instanceDict = {} 22 | 23 | if not isinstance(imageFileList, list): 24 | imageFileList = [imageFileList] 25 | 26 | if verbose: 27 | print("Processing {} images...".format(len(imageFileList))) 28 | 29 | for imageFileName in imageFileList: 30 | # Load image 31 | img = Image.open(imageFileName) 32 | 33 | # Image as numpy array 34 | imgNp = np.array(img) 35 | 36 | # Initialize label categories 37 | instances = {} 38 | for label in labels: 39 | instances[label.name] = [] 40 | 41 | # Loop through all instance ids in instance image 42 | for instanceId in np.unique(imgNp): 43 | if instanceId < 1000: 44 | continue 45 | instanceObj = Instance(imgNp, instanceId) 46 | instanceObj_dict = instanceObj.toDict() 47 | 48 | #instances[id2label[instanceObj.labelID].name].append(instanceObj.toDict()) 49 | if id2label[instanceObj.labelID].hasInstances: 50 | mask = (imgNp == instanceId).astype(np.uint8) 51 | contour, hier = cv2_util.findContours( 52 | mask.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE) 53 | 54 | polygons = [c.reshape(-1).tolist() for c in contour] 55 | instanceObj_dict['contours'] = polygons 56 | 57 | instances[id2label[instanceObj.labelID].name].append(instanceObj_dict) 58 | 59 | imgKey = os.path.abspath(imageFileName) 60 | instanceDict[imgKey] = instances 61 | imgCount += 1 62 | 63 | if verbose: 64 | print("\rImages Processed: {}".format(imgCount), end=' ') 65 | sys.stdout.flush() 66 | 67 | if verbose: 68 | print("") 69 | 70 | return instanceDict 71 | 72 | def main(argv): 73 | fileList = [] 74 | if (len(argv) > 2): 75 | for arg in argv: 76 | if ("png" in arg): 77 | fileList.append(arg) 78 | instances2dict_with_polygons(fileList, True) 79 | 80 | if __name__ == "__main__": 81 | main(sys.argv[1:]) 82 | -------------------------------------------------------------------------------- /tools/test_directly.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | # Set up custom environment before nearly anything else is imported 3 | # NOTE: this should be the first import (no not reorder) 4 | from maskrcnn_benchmark.utils.env import setup_environment # noqa F401 isort:skip 5 | 6 | import argparse 7 | import os 8 | 9 | import torch 10 | from maskrcnn_benchmark.config import cfg 11 | from maskrcnn_benchmark.data import make_data_loader 12 | from maskrcnn_benchmark.utils.comm import synchronize 13 | from maskrcnn_benchmark.utils.miscellaneous import mkdir 14 | 15 | from maskrcnn_benchmark.data.datasets.evaluation.vg.vg_eval import do_vg_evaluation_directly 16 | 17 | # Check if we can enable mixed-precision via apex.amp 18 | try: 19 | from apex import amp 20 | except ImportError: 21 | raise ImportError('Use APEX for mixed precision via apex.amp') 22 | 23 | 24 | def main(output_folder): 25 | parser = argparse.ArgumentParser(description="PyTorch Object Detection Inference") 26 | parser.add_argument( 27 | "--config-file", 28 | default="configs/SHA_GCL_e2e_relation_X_101_32_8_FPN_1x", 29 | metavar="FILE", 30 | help="path to config file", 31 | ) 32 | parser.add_argument("--local_rank", type=int, default=0) 33 | parser.add_argument( 34 | "opts", 35 | help="Modify config options using the command-line", 36 | default=None, 37 | nargs=argparse.REMAINDER, 38 | ) 39 | 40 | args = parser.parse_args() 41 | 42 | num_gpus = int(os.environ["WORLD_SIZE"]) if "WORLD_SIZE" in os.environ else 1 43 | distributed = num_gpus > 1 44 | 45 | cfg.merge_from_file(args.config_file) 46 | cfg.merge_from_list(args.opts) 47 | cfg.freeze() 48 | 49 | iou_types = ("bbox",) 50 | if cfg.MODEL.RELATION_ON: 51 | iou_types = iou_types + ("relations", ) 52 | 53 | data_loaders_val = make_data_loader(cfg, mode="test", is_distributed=distributed) 54 | 55 | for data_loader_val in data_loaders_val: 56 | print('\n\nwarning!\nwarning!\nwarning!\nwe generate results without testing!\n\n') 57 | # convert to a torch.device for efficiency 58 | 59 | dataset = data_loader_val.dataset 60 | 61 | predictions = torch.load(os.path.join(output_folder, "eval_results.pytorch"), map_location=torch.device("cpu"))['predictions'] 62 | synchronize() 63 | 64 | return do_vg_evaluation_directly(cfg=cfg, 65 | dataset=dataset, 66 | predictions=predictions, 67 | iou_types=iou_types) 68 | 69 | 70 | if __name__ == "__main__": 71 | output_folder = 'G:/myprogram/winscp_save/sggtest/0824_drn_trans_Topdown' 72 | main(output_folder) 73 | --------------------------------------------------------------------------------