├── .gitignore ├── .idea ├── .gitignore ├── VisualGroundingR50.iml ├── deployment.xml ├── dictionaries │ └── liuyf.xml ├── emacs.xml ├── inspectionProfiles │ └── profiles_settings.xml ├── misc.xml ├── modules.xml ├── sshConfigs.xml ├── vcs.xml └── webServers.xml ├── INSTALL.md ├── README.md ├── caffe_extract └── extract.py ├── configs ├── 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 │ ├── e2e_faster_rcnn_R_50_FPN_1x_cocostyle.yaml │ └── e2e_mask_rcnn_R_50_FPN_1x_cocostyle.yaml ├── e2e_flickr_bottom_up_faster_rcnn_R_101_FPN_1x.yaml ├── e2e_flickr_det_faster_rcnn_R_101_FPN_1x.yaml ├── e2e_flickr_faster_rcnn_R_101_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 ├── 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 └── yaml_hist_MaskRCNN │ ├── e2e_VRD_faster_rcnn_R_101_FPN_1x.yaml │ ├── e2e_VRD_faster_rcnn_R_50_C4_1x.yaml │ ├── e2e_VRD_faster_rcnn_VGG16.yaml │ ├── 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 ├── data_analysis ├── VisDetectionBbox.ipynb ├── bert.ipynb ├── data_analysis.ipynb ├── fast_rcnn │ ├── __init__.py │ ├── bbox_transform.py │ ├── bbox_transform_pytorch.py │ ├── config.py │ ├── config2.py │ └── nms_wrapper.py ├── flicker_recall_check.ipynb ├── flicker_recall_check.py ├── flickr_recall_check_v1.py ├── model_size.py ├── nms │ ├── .gitignore │ ├── __init__.py │ ├── cpu_nms.pyx │ ├── gpu_nms.hpp │ ├── gpu_nms.pyx │ ├── nms_kernel.cu │ └── py_cpu_nms.py ├── pretrain_weight │ ├── embed_ba_0.npy │ ├── embed_ba_1.npy │ ├── lstm1_0.npy │ ├── lstm1_1.npy │ ├── lstm1_2.npy │ ├── query_bbox_pred_0.npy │ ├── query_bbox_pred_1.npy │ ├── query_score_fc_0.npy │ ├── query_score_fc_1.npy │ ├── qv_fc1_0.npy │ └── qv_fc1_1.npy ├── sng_parser │ ├── __init__.py │ ├── _data │ │ ├── phrasal-preps.txt │ │ ├── phrasal-verbs.txt │ │ └── scene-nouns.txt │ ├── backends │ │ ├── __init__.py │ │ ├── backend.py │ │ └── spacy_parser.py │ ├── database.py │ ├── parser.py │ └── utils.py ├── tools │ ├── .gitignore │ ├── get-phrasal-verbs.sh │ ├── get-scene-nouns.sh │ ├── parse-eos.py │ └── process-scene-nouns.py ├── untitled.txt ├── upper_bound.ipynb └── utils │ ├── __init__.py │ ├── blob.py │ ├── boxes-Copy1.py │ ├── boxes.py │ ├── cbam.py │ ├── collections.py │ ├── colormap.py │ ├── cython_bbox.c │ ├── cython_bbox.pyx │ ├── cython_nms.c │ ├── cython_nms.pyx │ ├── detectron_weight_helper.py │ ├── env.py │ ├── fpn.py │ ├── image.py │ ├── io.py │ ├── keypoints.py │ ├── logging.py │ ├── misc.py │ ├── net.py │ ├── resnet_weights_helper.py │ ├── segms.py │ ├── subprocess.py │ ├── timer.py │ ├── training_stats.py │ └── vis.py ├── demo ├── README.md ├── demo_e2e_mask_rcnn_R_50_FPN_1x.png ├── demo_e2e_mask_rcnn_X_101_32x8d_FPN_1x.png ├── predictor.py └── webcam.py ├── killpy.sh ├── 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 │ │ ├── nms.cu │ │ └── vision.h │ ├── nms.h │ └── vision.cpp ├── data │ ├── README.md │ ├── __init__.py │ ├── build.py │ ├── collate_batch.py │ ├── datasets │ │ ├── __init__.py │ │ ├── coco.py │ │ ├── concat_dataset.py │ │ ├── evaluation │ │ │ ├── VG │ │ │ │ ├── __init__.py │ │ │ │ └── vg_eval.py │ │ │ ├── __init__.py │ │ │ ├── coco │ │ │ │ ├── __init__.py │ │ │ │ └── coco_eval.py │ │ │ ├── flickr │ │ │ │ ├── __init__.py │ │ │ │ └── flickr_eval.py │ │ │ └── voc │ │ │ │ ├── __init__.py │ │ │ │ └── voc_eval.py │ │ ├── flickr.py │ │ ├── list_dataset.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 │ │ ├── transforms_vg.py │ │ └── transforms_vg_bp.py ├── engine │ ├── __init__.py │ ├── inference.py │ ├── trainer.py │ └── trainer_bak.py ├── layers │ ├── __init__.py │ ├── _utils.py │ ├── batch_norm.py │ ├── generate_dense_relation.py │ ├── generate_sample_relation.py │ ├── generate_union_region.py │ ├── misc.py │ ├── nms.py │ ├── numerical_stability_softmax.py │ ├── roi_align.py │ ├── roi_pool.py │ ├── sigmoid_focal_loss.py │ ├── smooth_l1_loss.py │ └── spatial_coordinate.py ├── modeling │ ├── __init__.py │ ├── backbone │ │ ├── __init__.py │ │ ├── backbone.py │ │ ├── bottom_up_resnet.py │ │ ├── fbnet.py │ │ ├── fbnet_builder.py │ │ ├── fbnet_modeldef.py │ │ ├── fpn.py │ │ ├── resnet.py │ │ └── vgg16.py │ ├── balanced_positive_negative_sampler.py │ ├── box_coder.py │ ├── detector │ │ ├── __init__.py │ │ ├── detectors.py │ │ ├── generalized_rcnn.py │ │ └── generalized_rcnn_det.py │ ├── make_layers.py │ ├── matcher.py │ ├── poolers.py │ ├── registry.py │ ├── relation │ │ ├── __init__.py │ │ ├── feature_refine.py │ │ ├── loss.py │ │ └── relation_detection.py │ ├── roi_heads │ │ ├── __init__.py │ │ ├── box_head │ │ │ ├── __init__.py │ │ │ ├── box_head.py │ │ │ ├── inference.py │ │ │ ├── loss.py │ │ │ ├── roi_box_feature_extractors.py │ │ │ └── roi_box_predictors.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 │ │ └── 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 │ └── vg │ │ ├── FeatureRefinement.py │ │ ├── VisualGraph.py │ │ ├── VisualGraphUpdate.py │ │ ├── __init__.py │ │ ├── loss.py │ │ ├── phrase_embedding.py │ │ ├── vg_detection.py │ │ └── vg_detection_2stage_sep_rel_const.py ├── solver │ ├── __init__.py │ ├── build.py │ └── lr_scheduler.py ├── structures │ ├── __init__.py │ ├── bounding_box.py │ ├── boxlist_ops.py │ ├── image_list.py │ ├── keypoint.py │ ├── relation_triplet.py │ └── segmentation_mask.py └── utils │ ├── README.md │ ├── __init__.py │ ├── c2_model_loading.py │ ├── checkpoint.py │ ├── collect_env.py │ ├── comm.py │ ├── cv2_util.py │ ├── debugger.py │ ├── direction_word_dict.py │ ├── env.py │ ├── imports.py │ ├── logger.py │ ├── metric_logger.py │ ├── miscellaneous.py │ ├── model_serialization.py │ ├── model_zoo.py │ ├── ops.py │ ├── registry.py │ └── timer.py ├── requirements.txt ├── scripts └── train.sh ├── setup.py ├── skipthoughts ├── __init__.py ├── dropout.py ├── gru.py ├── skipthoughts.py └── version.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 └── utils.py └── tools ├── cityscapes ├── convert_cityscapes_to_coco.py └── instances2dict_with_polygons.py ├── test_flickr.py ├── test_net.py └── train_net.py /.gitignore: -------------------------------------------------------------------------------- 1 | maskrcnn_benchmark/modeling/vg_bak 2 | maskrcnn_benchmark/structure_prediction -------------------------------------------------------------------------------- /.idea/.gitignore: -------------------------------------------------------------------------------- 1 | # Default ignored files 2 | /shelf/ 3 | /workspace.xml 4 | # Datasource local storage ignored files 5 | /dataSources/ 6 | /dataSources.local.xml 7 | # Editor-based HTTP Client requests 8 | /httpRequests/ 9 | -------------------------------------------------------------------------------- /.idea/VisualGroundingR50.iml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 11 | -------------------------------------------------------------------------------- /.idea/deployment.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | 13 | 14 | 15 | 16 | 17 | 18 | 19 | 20 | 22 | -------------------------------------------------------------------------------- /.idea/dictionaries/liuyf.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | anno 5 | atte 6 | atten 7 | avgpool 8 | baidu 9 | bphr 10 | bvis 11 | conv 12 | datasets 13 | downsample 14 | flickr 15 | inds 16 | intra 17 | keypoint 18 | keypoints 19 | logits 20 | mscoco 21 | msra 22 | noent 23 | phrsbj 24 | phrtnobj 25 | phrtnsbj 26 | pooler 27 | precomp 28 | precompute 29 | pretrained 30 | rcnn 31 | relu 32 | resnet 33 | segm 34 | softmax 35 | topk 36 | xyxy 37 | 38 | 39 | -------------------------------------------------------------------------------- /.idea/emacs.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 6 | -------------------------------------------------------------------------------- /.idea/inspectionProfiles/profiles_settings.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 6 | -------------------------------------------------------------------------------- /.idea/misc.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 6 | 7 | -------------------------------------------------------------------------------- /.idea/modules.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | -------------------------------------------------------------------------------- /.idea/sshConfigs.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | -------------------------------------------------------------------------------- /.idea/vcs.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | -------------------------------------------------------------------------------- /.idea/webServers.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 22 | 23 | -------------------------------------------------------------------------------- /INSTALL.md: -------------------------------------------------------------------------------- 1 | ## Installation 2 | 3 | ### Requirements: 4 | - PyTorch 1.0 from a nightly release. It **will not** work with 1.0 nor 1.0.1. Installation instructions can be found in https://pytorch.org/get-started/locally/ 5 | - torchvision from master 6 | - cocoapi 7 | - yacs 8 | - matplotlib 9 | - GCC >= 4.9 10 | - (optional) OpenCV for the webcam demo 11 | 12 | 13 | ### Option 1: Step-by-step installation 14 | 15 | ```bash 16 | 17 | # install pycocotools 18 | cd $INSTALL_DIR 19 | git clone https://github.com/cocodataset/cocoapi.git 20 | cd cocoapi/PythonAPI 21 | python setup.py build_ext install 22 | 23 | 24 | # install allennlp 25 | pip install allennlp 26 | 27 | # install PyTorch Detection 28 | cd $INSTALL_DIR 29 | git clone https://github.com/facebookresearch/maskrcnn-benchmark.git 30 | cd maskrcnn-benchmark 31 | 32 | 33 | # the following will install the lib with 34 | # symbolic links, so that you can modify 35 | # the files if you want and won't need to 36 | # re-build it 37 | python setup.py build develop 38 | 39 | install allennlp 40 | 41 | 42 | ``` -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # LCMCG.Pytorch 2 | 3 | This repo is the official implementation of ["Learning Cross-Modal Context Graph for Visual Grounding"](https://arxiv.org/pdf/1911.09042.pdf) (AAAI2020) 4 | ## Installation 5 | Check [INSTALL.md](INSTALL.md) for installation instructions. 6 | 7 | ## pre-requirements 8 | 1. Download the flickr30k dataset in this [link](http://bryanplummer.com/Flickr30kEntities/) 9 | 2. Pre-computed bounding boxes are extracted by using [FasterRCNN](https://github.com/facebookresearch/maskrcnn-benchmark) \ 10 | We use the config "e2e_faster_rcnn_R_50_C4_1x.yaml" to train the object detector on MSCOCO dataset and extract the feature map at C4 layer. 11 | 3. Language graph extraction by using [SceneGraphParser](https://github.com/vacancy/SceneGraphParser). I have uploaded the sg_anno.json into Google drive. You can download it now. 12 | 4. Some pre-processing data, like sentence annotations, box annotations. 13 | 5. You need to create the './flickr_datasets' folder and put all annotation in it. I would highly recommend you to figure all 14 | the data path out in this project. You can refer this two file "maskrcnn_benchmark/config/paths_catalog.py" and "maskrcnn_benchmark/data/flickr.py" for details. 15 | 16 | The pretrained object detector weights and annotations can be found here at baidu-disk (link:https://pan.baidu.com/s/1bYbGUsHcZJQHele87MzcMg password:5ie6) or [google drive](https://drive.google.com/drive/folders/1dRp61muWDNuFG-V9KMKcZ26zR8f2ujci?usp=sharing) 17 | 18 | 19 | ## training 20 | 21 | 1. You can train our model by running the scripts 22 | ```bash 23 | sh scripts/train.sh 24 | ``` 25 | 26 | "" 27 | 28 | ## citation 29 | If you are interested in our paper, please cite it. 30 | ```bash 31 | @inproceedings{liu2019learning, 32 | title={Learning Cross-modal Context Graph for Visual Grounding}, 33 | author={Liu, Yongfei and Wan, Bo and Zhu, Xiaodan and He, Xuming}, 34 | booktitle={Proceedings of the AAAI Conference on Artificial Intelligenc} 35 | year={2020} 36 | } 37 | ``` 38 | -------------------------------------------------------------------------------- /caffe_extract/extract.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/python3.6 2 | # -*- coding: utf-8 -*- 3 | # @Time : 2019-06-03 16:46 4 | # @Author : Yongfei Liu 5 | # @Email : liuyf3@shanghaitech.edu.cn 6 | 7 | import caffe 8 | import numpy as np 9 | import argparse 10 | import os 11 | 12 | def extract_caffe_model(model, weights, output_path): 13 | """extract caffe model's parameters to numpy array, and write them to files 14 | Args: 15 | model: path of '.prototxt' 16 | weights: path of '.caffemodel' 17 | output_path: output path of numpy params 18 | Returns: 19 | None 20 | """ 21 | net = caffe.Net(model, caffe.TEST) 22 | net.copy_from(weights) 23 | 24 | if not os.path.exists(output_path): 25 | os.makedirs(output_path) 26 | 27 | for item in net.params.items(): 28 | name, layer = item 29 | print('convert layer: ' + name) 30 | 31 | num = 0 32 | for p in net.params[name]: 33 | np.save(output_path + '/' + str(name) + '_' + str(num), p.data) 34 | num += 1 35 | 36 | if __name__ == '__main__': 37 | parser = argparse.ArgumentParser() 38 | parser.add_argument("--model", help="model prototxt path .prototxt") 39 | parser.add_argument("--weights", help="caffe model weights path .caffemodel") 40 | parser.add_argument("--output", help="output path") 41 | args = parser.parse_args() 42 | extract_caffe_model(args.model, args.weights, args.output) 43 | 44 | 45 | -------------------------------------------------------------------------------- /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/e2e_flickr_det_faster_rcnn_R_101_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNNDet" 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 | NMS: 0.4 18 | DETECTIONS_PER_IMG: 100 19 | 20 | VG_ON: True 21 | RELATION_ON: False 22 | 23 | VG: 24 | FIXED_BACKBONE: True 25 | FIXED_RPN: True 26 | FIXED_ROI_HEAD: True 27 | FG_IOU_THRESHOLD: 0.5 28 | BG_IOU_THRESHOLD: 0.2 29 | VOCAB_FILE: "datasets/skip-thoughts/vocab.json" 30 | SKIP_THROUGH_DATA_DIR: "datasets/skip-thoughts" 31 | 32 | ROI_BOX_HEAD: 33 | POOLER_RESOLUTION: 7 34 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 35 | POOLER_SAMPLING_RATIO: 2 36 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 37 | PREDICTOR: "FPNPredictor" 38 | NUM_CLASSES: 151 39 | 40 | 41 | DATASETS: 42 | TRAIN: ("flickr_train" ,) 43 | TEST: ("flickr_val" ,) 44 | DATALOADER: 45 | SIZE_DIVISIBILITY: 32 46 | NUM_WORKERS: 2 47 | SOLVER: 48 | BASE_LR: 0.05 49 | WEIGHT_DECAY: 0.0001 50 | STEPS: (40000, ) 51 | CHECKPOINT_PERIOD: 4000 52 | START_SAVE_CHECKPOINT: 4000 53 | MAX_ITER: 80000 54 | -------------------------------------------------------------------------------- /configs/e2e_flickr_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 | NMS: 0.4 18 | DETECTIONS_PER_IMG: 100 19 | 20 | VG_ON: True 21 | RELATION_ON: False 22 | 23 | VG: 24 | FIXED_BACKBONE: True 25 | FIXED_RESNET: True 26 | FIXED_RPN: True 27 | FIXED_ROI_HEAD: True 28 | FG_IOU_THRESHOLD: 0.5 29 | BG_IOU_THRESHOLD: 0.2 30 | VOCAB_FILE: "datasets/skip-thoughts/vocab.json" 31 | SKIP_THROUGH_DATA_DIR: "datasets/skip-thoughts" 32 | RESNET_PARAMS_FILE: './outputs/bottom-up-pretrained/bottomup_pretrained_10_100.pth' 33 | FIXED_EMBEDDING: False 34 | 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 42 | 43 | 44 | DATASETS: 45 | TRAIN: ("flickr_train" ,) 46 | TEST: ("flickr_val" ,) 47 | DATALOADER: 48 | SIZE_DIVISIBILITY: 32 49 | NUM_WORKERS: 2 50 | SOLVER: 51 | BASE_LR: 0.05 52 | WEIGHT_DECAY: 0.0001 53 | STEPS: (60000, 100000, ) 54 | CHECKPOINT_PERIOD: 5000 55 | START_SAVE_CHECKPOINT: 5000 56 | MAX_ITER: 120001 57 | -------------------------------------------------------------------------------- /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/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/yaml_hist_MaskRCNN/e2e_VRD_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 | NMS: 0.5 18 | DETECTIONS_PER_IMG: 128 19 | 20 | 21 | RELATION_ON: True 22 | 23 | RELATION: 24 | MAKE_PAIR_PROPOSAL_CNT: 128 25 | MAX_PROPOSAL_PAIR: 2048 26 | PHRASE_POOLED_SIZE: 8 27 | PHRASE_CLUSTER: True 28 | APPLY_REGRESSION: True 29 | USE_DETECTION_RESULT_FOR_RELATION: True 30 | FIXED_ROI_HEAD: True 31 | FIXED_RPN: True 32 | RELATION_CLASS: 51 33 | NEG_POS_PHRASE_PROP_RATE: 4 34 | SEPARATED_BACKBONE: True 35 | TOPK_TRIPLETS: (50, 100, ) 36 | SAMPLE_DETECTION_BOX: False 37 | 38 | FEATURE_REFINE: 39 | MASSAGE_PASSING: 0 40 | MP_UNIT_OUTPUT_DIM: 128 41 | 42 | ROI_BOX_HEAD: 43 | POOLER_RESOLUTION: 7 44 | POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) 45 | POOLER_SAMPLING_RATIO: 2 46 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" 47 | PREDICTOR: "FPNPredictor" 48 | NUM_CLASSES: 151 49 | 50 | 51 | DATASETS: 52 | # TRAIN: ("vg_150_50_train_fat" ,) 53 | TRAIN: ("vg_150_50_train_small" ,) 54 | # TRAIN: ("vg_150_50_train" ,) 55 | TEST: ("vg_150_50_test_small" ,) 56 | DATALOADER: 57 | SIZE_DIVISIBILITY: 32 58 | NUM_WORKERS: 2 59 | SOLVER: 60 | BASE_LR: 0.001 61 | WEIGHT_DECAY: 0.0001 62 | STEPS: (100000, ) 63 | CHECKPOINT_PERIOD: 5000 64 | START_SAVE_CHECKPOINT: 5000 65 | MAX_ITER: 200000 66 | -------------------------------------------------------------------------------- /configs/yaml_hist_MaskRCNN/e2e_VRD_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 | 8 | RELATION_ON: True 9 | 10 | RELATION: 11 | MAKE_PAIR_PROPOSAL_CNT: 128 12 | MAX_PROPOSAL_PAIR: 2048 13 | PHRASE_POOLED_SIZE: 8 14 | PHRASE_CLUSTER: True 15 | APPLY_REGRESSION: True 16 | USE_DETECTION_RESULT_FOR_RELATION: True 17 | FIXED_ROI_HEAD: True 18 | FIXED_RPN: True 19 | RELATION_CLASS: 51 20 | NEG_POS_PHRASE_PROP_RATE: 4 21 | SEPARATED_BACKBONE: True 22 | TOPK_TRIPLETS: (50, 100, ) 23 | SAMPLE_DETECTION_BOX: False 24 | 25 | ROI_BOX_HEAD: 26 | NUM_CLASSES: 151 27 | FEATURE_EXTRACTOR: "ResNet50Conv5ROIFeatureExtractorFlatten" 28 | PREDICTOR: "FastRCNNPredictorFlatten" 29 | 30 | 31 | DATASETS: 32 | TRAIN: ("vg_150_50_train" ,) 33 | TEST: ("vg_150_50_test_small" ,) 34 | 35 | 36 | SOLVER: 37 | BASE_LR: 0.001 38 | WEIGHT_DECAY: 0.0001 39 | STEPS: (21000, ) 40 | CHECKPOINT_PERIOD: 3000 41 | START_SAVE_CHECKPOINT: 3000 42 | MAX_ITER: 50400 43 | IMS_PER_BATCH: 8 44 | -------------------------------------------------------------------------------- /configs/yaml_hist_MaskRCNN/e2e_VRD_faster_rcnn_VGG16.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | WEIGHT: "VGG16" 4 | RPN: 5 | PRE_NMS_TOP_N_TEST: 6000 6 | POST_NMS_TOP_N_TEST: 1000 7 | 8 | BACKBONE: 9 | CONV_BODY: "VGG16" 10 | FREEZE_CONV_BODY_AT: 5 11 | 12 | RELATION_ON: False 13 | 14 | RELATION: 15 | MAKE_PAIR_PROPOSAL_CNT: 128 16 | MAX_PROPOSAL_PAIR: 2048 17 | PHRASE_POOLED_SIZE: 8 18 | PHRASE_CLUSTER: True 19 | APPLY_REGRESSION: True 20 | USE_DETECTION_RESULT_FOR_RELATION: True 21 | FIXED_ROI_HEAD: True 22 | FIXED_RPN: True 23 | RELATION_CLASS: 51 24 | NEG_POS_PHRASE_PROP_RATE: 4 25 | SEPARATED_BACKBONE: True 26 | TOPK_TRIPLETS: (50, 100, ) 27 | SAMPLE_DETECTION_BOX: False 28 | 29 | ROI_BOX_HEAD: 30 | NUM_CLASSES: 151 31 | FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" # work like a single feature layer FPN 32 | PREDICTOR: "FPNPredictor" 33 | 34 | 35 | DATASETS: 36 | TRAIN: ("vg_150_50_train_fat" ,) 37 | TEST: ("vg_150_50_test_small" ,) 38 | 39 | 40 | SOLVER: 41 | BASE_LR: 0.001 42 | WEIGHT_DECAY: 0.0001 43 | STEPS: (90000, ) 44 | CHECKPOINT_PERIOD: 3000 45 | START_SAVE_CHECKPOINT: 3000 46 | MAX_ITER: 200000 47 | IMS_PER_BATCH: 8 48 | -------------------------------------------------------------------------------- /configs/yaml_hist_MaskRCNN/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_val",) 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/yaml_hist_MaskRCNN/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/yaml_hist_MaskRCNN/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/yaml_hist_MaskRCNN/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/yaml_hist_MaskRCNN/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/yaml_hist_MaskRCNN/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/yaml_hist_MaskRCNN/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/yaml_hist_MaskRCNN/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/yaml_hist_MaskRCNN/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/yaml_hist_MaskRCNN/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/yaml_hist_MaskRCNN/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/yaml_hist_MaskRCNN/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/yaml_hist_MaskRCNN/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/yaml_hist_MaskRCNN/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/yaml_hist_MaskRCNN/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/yaml_hist_MaskRCNN/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/yaml_hist_MaskRCNN/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/yaml_hist_MaskRCNN/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/yaml_hist_MaskRCNN/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/yaml_hist_MaskRCNN/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 | -------------------------------------------------------------------------------- /data_analysis/fast_rcnn/__init__.py: -------------------------------------------------------------------------------- 1 | # -------------------------------------------------------- 2 | # Fast R-CNN 3 | # Copyright (c) 2015 Microsoft 4 | # Licensed under The MIT License [see LICENSE for details] 5 | # Written by Ross Girshick 6 | # -------------------------------------------------------- 7 | 8 | 9 | from data_analysis.fast_rcnn import nms_wrapper -------------------------------------------------------------------------------- /data_analysis/fast_rcnn/bbox_transform_pytorch.py: -------------------------------------------------------------------------------- 1 | import torch 2 | 3 | 4 | def bbox_transform_inv(boxes, deltas): 5 | widths = boxes[:, 2] - boxes[:, 0] + 1.0 6 | heights = boxes[:, 3] - boxes[:, 1] + 1.0 7 | ctr_x = boxes[:, 0] + 0.5 * widths 8 | ctr_y = boxes[:, 1] + 0.5 * heights 9 | 10 | dx = deltas[:, 0] 11 | dy = deltas[:, 1] 12 | dw = deltas[:, 2] 13 | dh = deltas[:, 3] 14 | 15 | pred_ctr_x = dx * widths + ctr_x 16 | pred_ctr_y = dy * heights + ctr_y 17 | pred_w = torch.exp(dw) * widths 18 | pred_h = torch.exp(dh) * heights 19 | 20 | pred_boxes = deltas.clone() 21 | # x1 22 | pred_boxes[:, 0::4] = pred_ctr_x - 0.5 * pred_w 23 | # y1 24 | pred_boxes[:, 1::4] = pred_ctr_y - 0.5 * pred_h 25 | # x2 26 | pred_boxes[:, 2::4] = pred_ctr_x + 0.5 * pred_w 27 | # y2 28 | pred_boxes[:, 3::4] = pred_ctr_y + 0.5 * pred_h 29 | 30 | return pred_boxes 31 | 32 | 33 | def clip_boxes(boxes, im_shape): 34 | ret = boxes.clone() 35 | # x1 36 | ret[:, 0::4] = boxes[:, 0::4].clamp(0, im_shape[1] - 1) 37 | ret[:, 1::4] = boxes[:, 1::4].clamp(0, im_shape[0] - 1) 38 | ret[:, 2::4] = boxes[:, 2::4].clamp(0, im_shape[1] - 1) 39 | ret[:, 3::4] = boxes[:, 3::4].clamp(0, im_shape[0] - 1) 40 | return ret 41 | 42 | def clip_rois(boxes, im_shape): 43 | ret = boxes.clone() 44 | # x1 45 | ret[:, 1::5] = boxes[:, 1::5].clamp(0, im_shape[1] - 1) 46 | ret[:, 2::5] = boxes[:, 2::5].clamp(0, im_shape[0] - 1) 47 | ret[:, 3::5] = boxes[:, 3::5].clamp(0, im_shape[1] - 1) 48 | ret[:, 4::5] = boxes[:, 4::5].clamp(0, im_shape[0] - 1) 49 | return ret -------------------------------------------------------------------------------- /data_analysis/fast_rcnn/nms_wrapper.py: -------------------------------------------------------------------------------- 1 | # -------------------------------------------------------- 2 | # Fast R-CNN 3 | # Copyright (c) 2015 Microsoft 4 | # Licensed under The MIT License [see LICENSE for details] 5 | # Written by Ross Girshick 6 | # -------------------------------------------------------- 7 | 8 | from data_analysis.nms.cpu_nms import cpu_nms 9 | from data_analysis.nms.gpu_nms import gpu_nms 10 | 11 | from .config import cfg 12 | 13 | 14 | def nms(dets, thresh, force_cpu=False): 15 | """Dispatch to either CPU or GPU NMS implementations.""" 16 | 17 | if dets.shape[0] == 0: 18 | return [] 19 | if cfg.USE_GPU_NMS and not force_cpu: 20 | return gpu_nms(dets, thresh, device_id=cfg.GPU_ID) 21 | else: 22 | return cpu_nms(dets, thresh) 23 | -------------------------------------------------------------------------------- /data_analysis/nms/.gitignore: -------------------------------------------------------------------------------- 1 | *.c 2 | *.cpp 3 | *.so 4 | -------------------------------------------------------------------------------- /data_analysis/nms/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/data_analysis/nms/__init__.py -------------------------------------------------------------------------------- /data_analysis/nms/cpu_nms.pyx: -------------------------------------------------------------------------------- 1 | # -------------------------------------------------------- 2 | # Fast R-CNN 3 | # Copyright (c) 2015 Microsoft 4 | # Licensed under The MIT License [see LICENSE for details] 5 | # Written by Ross Girshick 6 | # -------------------------------------------------------- 7 | 8 | import numpy as np 9 | cimport numpy as np 10 | 11 | cdef inline np.float32_t max(np.float32_t a, np.float32_t b): 12 | return a if a >= b else b 13 | 14 | cdef inline np.float32_t min(np.float32_t a, np.float32_t b): 15 | return a if a <= b else b 16 | 17 | def cpu_nms(np.ndarray[np.float32_t, ndim=2] dets, np.float thresh): 18 | cdef np.ndarray[np.float32_t, ndim=1] x1 = dets[:, 0] 19 | cdef np.ndarray[np.float32_t, ndim=1] y1 = dets[:, 1] 20 | cdef np.ndarray[np.float32_t, ndim=1] x2 = dets[:, 2] 21 | cdef np.ndarray[np.float32_t, ndim=1] y2 = dets[:, 3] 22 | cdef np.ndarray[np.float32_t, ndim=1] scores = dets[:, 4] 23 | 24 | cdef np.ndarray[np.float32_t, ndim=1] areas = (x2 - x1 + 1) * (y2 - y1 + 1) 25 | cdef np.ndarray[np.int_t, ndim=1] order = scores.argsort()[::-1] 26 | 27 | cdef int ndets = dets.shape[0] 28 | cdef np.ndarray[np.int_t, ndim=1] suppressed = \ 29 | np.zeros((ndets), dtype=np.int) 30 | 31 | # nominal indices 32 | cdef int _i, _j 33 | # sorted indices 34 | cdef int i, j 35 | # temp variables for box i's (the box currently under consideration) 36 | cdef np.float32_t ix1, iy1, ix2, iy2, iarea 37 | # variables for computing overlap with box j (lower scoring box) 38 | cdef np.float32_t xx1, yy1, xx2, yy2 39 | cdef np.float32_t w, h 40 | cdef np.float32_t inter, ovr 41 | 42 | keep = [] 43 | for _i in range(ndets): 44 | i = order[_i] 45 | if suppressed[i] == 1: 46 | continue 47 | keep.append(i) 48 | ix1 = x1[i] 49 | iy1 = y1[i] 50 | ix2 = x2[i] 51 | iy2 = y2[i] 52 | iarea = areas[i] 53 | for _j in range(_i + 1, ndets): 54 | j = order[_j] 55 | if suppressed[j] == 1: 56 | continue 57 | xx1 = max(ix1, x1[j]) 58 | yy1 = max(iy1, y1[j]) 59 | xx2 = min(ix2, x2[j]) 60 | yy2 = min(iy2, y2[j]) 61 | w = max(0.0, xx2 - xx1 + 1) 62 | h = max(0.0, yy2 - yy1 + 1) 63 | inter = w * h 64 | ovr = inter / (iarea + areas[j] - inter) 65 | if ovr >= thresh: 66 | suppressed[j] = 1 67 | 68 | return keep 69 | -------------------------------------------------------------------------------- /data_analysis/nms/gpu_nms.hpp: -------------------------------------------------------------------------------- 1 | void _nms(int* keep_out, int* num_out, const float* boxes_host, int boxes_num, 2 | int boxes_dim, float nms_overlap_thresh, int device_id); 3 | -------------------------------------------------------------------------------- /data_analysis/nms/gpu_nms.pyx: -------------------------------------------------------------------------------- 1 | # -------------------------------------------------------- 2 | # Faster R-CNN 3 | # Copyright (c) 2015 Microsoft 4 | # Licensed under The MIT License [see LICENSE for details] 5 | # Written by Ross Girshick 6 | # -------------------------------------------------------- 7 | 8 | import numpy as np 9 | cimport numpy as np 10 | 11 | assert sizeof(int) == sizeof(np.int32_t) 12 | 13 | cdef extern from "gpu_nms.hpp": 14 | void _nms(np.int32_t*, int*, np.float32_t*, int, int, float, int) 15 | 16 | def gpu_nms(np.ndarray[np.float32_t, ndim=2] dets, np.float thresh, 17 | np.int32_t device_id=0): 18 | cdef int boxes_num = dets.shape[0] 19 | cdef int boxes_dim = dets.shape[1] 20 | cdef int num_out 21 | cdef np.ndarray[np.int32_t, ndim=1] \ 22 | keep = np.zeros(boxes_num, dtype=np.int32) 23 | cdef np.ndarray[np.float32_t, ndim=1] \ 24 | scores = dets[:, 4] 25 | cdef np.ndarray[np.int_t, ndim=1] \ 26 | order = scores.argsort()[::-1] 27 | cdef np.ndarray[np.float32_t, ndim=2] \ 28 | sorted_dets = dets[order, :] 29 | _nms(&keep[0], &num_out, &sorted_dets[0, 0], boxes_num, boxes_dim, thresh, device_id) 30 | keep = keep[:num_out] 31 | return list(order[keep]) 32 | -------------------------------------------------------------------------------- /data_analysis/nms/py_cpu_nms.py: -------------------------------------------------------------------------------- 1 | # -------------------------------------------------------- 2 | # Fast R-CNN 3 | # Copyright (c) 2015 Microsoft 4 | # Licensed under The MIT License [see LICENSE for details] 5 | # Written by Ross Girshick 6 | # -------------------------------------------------------- 7 | 8 | import numpy as np 9 | 10 | def py_cpu_nms(dets, thresh): 11 | """Pure Python NMS baseline.""" 12 | x1 = dets[:, 0] 13 | y1 = dets[:, 1] 14 | x2 = dets[:, 2] 15 | y2 = dets[:, 3] 16 | scores = dets[:, 4] 17 | 18 | areas = (x2 - x1 + 1) * (y2 - y1 + 1) 19 | order = scores.argsort()[::-1] 20 | 21 | keep = [] 22 | while order.size > 0: 23 | i = order[0] 24 | keep.append(i) 25 | xx1 = np.maximum(x1[i], x1[order[1:]]) 26 | yy1 = np.maximum(y1[i], y1[order[1:]]) 27 | xx2 = np.minimum(x2[i], x2[order[1:]]) 28 | yy2 = np.minimum(y2[i], y2[order[1:]]) 29 | 30 | w = np.maximum(0.0, xx2 - xx1 + 1) 31 | h = np.maximum(0.0, yy2 - yy1 + 1) 32 | inter = w * h 33 | ovr = inter / (areas[i] + areas[order[1:]] - inter) 34 | 35 | inds = np.where(ovr <= thresh)[0] 36 | order = order[inds + 1] 37 | 38 | return keep 39 | -------------------------------------------------------------------------------- /data_analysis/pretrain_weight/embed_ba_0.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/data_analysis/pretrain_weight/embed_ba_0.npy -------------------------------------------------------------------------------- /data_analysis/pretrain_weight/embed_ba_1.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/data_analysis/pretrain_weight/embed_ba_1.npy -------------------------------------------------------------------------------- /data_analysis/pretrain_weight/lstm1_0.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/data_analysis/pretrain_weight/lstm1_0.npy -------------------------------------------------------------------------------- /data_analysis/pretrain_weight/lstm1_1.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/data_analysis/pretrain_weight/lstm1_1.npy -------------------------------------------------------------------------------- /data_analysis/pretrain_weight/lstm1_2.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/data_analysis/pretrain_weight/lstm1_2.npy -------------------------------------------------------------------------------- /data_analysis/pretrain_weight/query_bbox_pred_0.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/data_analysis/pretrain_weight/query_bbox_pred_0.npy -------------------------------------------------------------------------------- /data_analysis/pretrain_weight/query_bbox_pred_1.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/data_analysis/pretrain_weight/query_bbox_pred_1.npy -------------------------------------------------------------------------------- /data_analysis/pretrain_weight/query_score_fc_0.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/data_analysis/pretrain_weight/query_score_fc_0.npy -------------------------------------------------------------------------------- /data_analysis/pretrain_weight/query_score_fc_1.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/data_analysis/pretrain_weight/query_score_fc_1.npy -------------------------------------------------------------------------------- /data_analysis/pretrain_weight/qv_fc1_0.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/data_analysis/pretrain_weight/qv_fc1_0.npy -------------------------------------------------------------------------------- /data_analysis/pretrain_weight/qv_fc1_1.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/data_analysis/pretrain_weight/qv_fc1_1.npy -------------------------------------------------------------------------------- /data_analysis/sng_parser/__init__.py: -------------------------------------------------------------------------------- 1 | #! /usr/bin/env python3 2 | # -*- coding: utf-8 -*- 3 | # File : __init__.py 4 | # Author : Jiayuan Mao 5 | # Email : maojiayuan@gmail.com 6 | # Date : 08/21/2018 7 | # 8 | # This file is part of SceneGraphParser. 9 | # Distributed under terms of the MIT license. 10 | # https://github.com/vacancy/SceneGraphParser 11 | 12 | from .parser import * 13 | from .backends import * 14 | from .utils import * 15 | 16 | __version__ = (0, 1, 0) 17 | __author__ = 'Jiayuan Mao' 18 | __email__ = 'maojiayuan@gmail.com' 19 | 20 | -------------------------------------------------------------------------------- /data_analysis/sng_parser/_data/phrasal-preps.txt: -------------------------------------------------------------------------------- 1 | in addition to 2 | in front of 3 | in reference to 4 | in regard to 5 | in spite of 6 | on account of 7 | on top of 8 | on side of 9 | on the side of 10 | with regard to 11 | 12 | -------------------------------------------------------------------------------- /data_analysis/sng_parser/backends/__init__.py: -------------------------------------------------------------------------------- 1 | #! /usr/bin/env python3 2 | # -*- coding: utf-8 -*- 3 | # File : __init__.py 4 | # Author : Jiayuan Mao 5 | # Email : maojiayuan@gmail.com 6 | # Date : 08/21/2018 7 | # 8 | # This file is part of SceneGraphParser. 9 | # Distributed under terms of the MIT license. 10 | # https://github.com/vacancy/SceneGraphParser 11 | 12 | from .spacy_parser import * 13 | 14 | -------------------------------------------------------------------------------- /data_analysis/sng_parser/backends/backend.py: -------------------------------------------------------------------------------- 1 | #! /usr/bin/env python3 2 | # -*- coding: utf-8 -*- 3 | # File : backend.py 4 | # Author : Jiayuan Mao 5 | # Email : maojiayuan@gmail.com 6 | # Date : 08/21/2018 7 | # 8 | # This file is part of SceneGraphParser. 9 | # Distributed under terms of the MIT license. 10 | # https://github.com/vacancy/SceneGraphParser 11 | 12 | 13 | class ParserBackend(object): 14 | """ 15 | Based class for all parser backends. This class 16 | specifies the methods that should be override by subclasses. 17 | """ 18 | 19 | def parse(self, sentence): 20 | raise NotImplementedError() 21 | 22 | -------------------------------------------------------------------------------- /data_analysis/sng_parser/database.py: -------------------------------------------------------------------------------- 1 | #! /usr/bin/env python3 2 | # -*- coding: utf-8 -*- 3 | # File : database.py 4 | # Author : Jiayuan Mao 5 | # Email : maojiayuan@gmail.com 6 | # Date : 08/23/2018 7 | # 8 | # This file is part of SceneGraphParser. 9 | # Distributed under terms of the MIT license. 10 | # https://github.com/vacancy/SceneGraphParser 11 | 12 | import os.path as osp 13 | 14 | 15 | _caches = dict() 16 | 17 | 18 | def load_list(filename): 19 | if filename not in _caches: 20 | out = set() 21 | for x in open(osp.join(osp.dirname(__file__), '_data', filename)): 22 | x = x.strip() 23 | if len(x) > 0: 24 | out.add(x) 25 | _caches[filename] = out 26 | return _caches[filename] 27 | 28 | 29 | def is_phrasal_verb(verb): 30 | return verb in load_list('phrasal-verbs.txt') 31 | 32 | 33 | def is_phrasal_prep(prep): 34 | return prep in load_list('phrasal-preps.txt') 35 | 36 | 37 | def is_scene_noun(noun): 38 | head = noun.split(' ')[-1] 39 | s = load_list('scene-nouns.txt') 40 | return noun in s or head in s 41 | 42 | -------------------------------------------------------------------------------- /data_analysis/sng_parser/utils.py: -------------------------------------------------------------------------------- 1 | #! /usr/bin/env python3 2 | # -*- coding: utf-8 -*- 3 | # File : utils.py 4 | # Author : Jiayuan Mao 5 | # Email : maojiayuan@gmail.com 6 | # Date : 08/21/2018 7 | # 8 | # This file is part of SceneGraphParser. 9 | # Distributed under terms of the MIT license. 10 | # https://github.com/vacancy/SceneGraphParser 11 | 12 | import functools 13 | import tabulate 14 | 15 | 16 | __all__ = ['tprint'] 17 | 18 | 19 | def tprint(graph, file=None, show_entities=True, show_relations=True): 20 | """ 21 | Print a scene graph as a table. 22 | The printed strings contains only essential information about the parsed scene graph. 23 | """ 24 | 25 | _print = functools.partial(print, file=file) 26 | 27 | if show_entities: 28 | _print('Entities:') 29 | 30 | entities_data = [ 31 | [e['head'].lower(), e['span'].lower(), ','.join([ x['span'].lower() for x in e['modifiers'] ])] 32 | for e in graph['entities'] 33 | ] 34 | _print(tabulate.tabulate(entities_data, headers=['Head', 'Span', 'Modifiers'], tablefmt=_tabulate_format)) 35 | 36 | if show_relations: 37 | _print('Relations:') 38 | 39 | entities = graph['entities'] 40 | relations_data = [ 41 | [ 42 | entities[rel['subject']]['head'].lower(), 43 | rel['relation'].lower(), 44 | entities[rel['object']]['head'].lower() 45 | ] 46 | for rel in graph['relations'] 47 | ] 48 | _print(tabulate.tabulate(relations_data, headers=['Subject', 'Relation', 'Object'], tablefmt=_tabulate_format)) 49 | 50 | 51 | _tabulate_format = tabulate.TableFormat( 52 | lineabove=tabulate.Line("+", "-", "+", "+"), 53 | linebelowheader=tabulate.Line("|", "-", "+", "|"), 54 | linebetweenrows=None, 55 | linebelow=tabulate.Line("+", "-", "+", "+"), 56 | headerrow=tabulate.DataRow("|", "|", "|"), 57 | datarow=tabulate.DataRow("|", "|", "|"), 58 | padding=1, with_header_hide=None 59 | ) 60 | -------------------------------------------------------------------------------- /data_analysis/tools/.gitignore: -------------------------------------------------------------------------------- 1 | /*.txt 2 | 3 | -------------------------------------------------------------------------------- /data_analysis/tools/get-phrasal-verbs.sh: -------------------------------------------------------------------------------- 1 | #! /bin/sh 2 | # 3 | # get-phrasal-verbs.sh 4 | # Copyright (C) 2018 Jiayuan Mao 5 | # 6 | # Distributed under terms of the MIT license. 7 | 8 | set -x 9 | 10 | rm -f ../sng_parser/_data/phrasal-verbs.txt 11 | 12 | for alpha in {A..Z} 13 | do 14 | echo curling $alpha 15 | curl \ 16 | -H "User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.89 Safari/537.36" \ 17 | http://www.english-for-students.com/Phrasal-Verbs-$alpha.html | python3 parse-eos.py >> ../sng_parser/_data/phrasal-verbs.txt 18 | sleep 3 19 | done 20 | 21 | -------------------------------------------------------------------------------- /data_analysis/tools/get-scene-nouns.sh: -------------------------------------------------------------------------------- 1 | #! /bin/sh 2 | # 3 | # get-scene-nouns.sh 4 | # Copyright (C) 2018 Jiayuan Mao 5 | # 6 | # Distributed under terms of the MIT license. 7 | # 8 | 9 | set -x 10 | 11 | curl https://raw.githubusercontent.com/CSAILVision/places365/master/IO_places365.txt | \ 12 | python3 process-scene-nouns.py > \ 13 | ../sng_parser/_data/scene-nouns.txt 14 | -------------------------------------------------------------------------------- /data_analysis/tools/parse-eos.py: -------------------------------------------------------------------------------- 1 | #! /usr/bin/env python3 2 | # -*- coding: utf-8 -*- 3 | # File : parse-eos.py 4 | # Author : Jiayuan Mao 5 | # Email : maojiayuan@gmail.com 6 | # Date : 08/23/2018 7 | # 8 | # This file is part of SceneGraphParser. 9 | # Distributed under terms of the MIT license. 10 | # https://github.com/vacancy/SceneGraphParser 11 | 12 | import re 13 | 14 | 15 | def main(): 16 | import sys 17 | 18 | text = '\n'.join(sys.stdin.readlines()) 19 | groups = re.findall("(.*?)<\/b>", text, re.MULTILINE) 20 | 21 | if len(groups) == 0: 22 | print('Error to get the page.') 23 | 24 | current = groups[len(groups) // 3 * 2][0].lower() 25 | print('Current', current, file=sys.stderr) 26 | 27 | for g in groups: 28 | g = g.lower() 29 | if not g.startswith(current): 30 | print('Filter: ', g, file=sys.stderr) 31 | else: 32 | print(g) 33 | 34 | 35 | if __name__ == '__main__': 36 | main() 37 | 38 | -------------------------------------------------------------------------------- /data_analysis/tools/process-scene-nouns.py: -------------------------------------------------------------------------------- 1 | #! /usr/bin/env python3 2 | # -*- coding: utf-8 -*- 3 | # File : process-scene-nouns.py 4 | # Author : Jiayuan Mao 5 | # Email : maojiayuan@gmail.com 6 | # Date : 08/23/2018 7 | # 8 | # This file is part of SceneGraphParser. 9 | # Distributed under terms of the MIT license. 10 | # https://github.com/vacancy/SceneGraphParser 11 | 12 | import sys 13 | import spacy 14 | 15 | nlp = spacy.load('en') 16 | 17 | extra_nouns = ['cabin', 'airport', 'terminal', 'arcade', 'park', 'apartment', 'gallery', 'school', 'studio', 'loft', 'field', 'factory', 'showroom', 'bank', 'banquet', 'court', 'salon', 'laboratory', 'station', 'store', 'lab', 'room', 'conference', 'dorm', 'lobby', 'entrance', 'restaurant', 'market', 'office', 'theater', 'skating', 'jail', 'kindergarden', 'dock', 'gym', 'cubicles', 'residential', 'mall', 'resort', 'hole', 'hostel'] 18 | 19 | 20 | def main(): 21 | nouns = set() 22 | for line in sys.stdin: 23 | line, _ = line.split(' ') 24 | line = line.split('/')[2:] 25 | for x in line: 26 | parts = x.split('_') 27 | nouns.add(' '.join(parts)) 28 | 29 | nouns.update(set(extra_nouns)) 30 | 31 | for n in sorted(nouns): 32 | print(n) 33 | 34 | 35 | if __name__ == '__main__': 36 | main() 37 | 38 | -------------------------------------------------------------------------------- /data_analysis/untitled.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/data_analysis/untitled.txt -------------------------------------------------------------------------------- /data_analysis/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/data_analysis/utils/__init__.py -------------------------------------------------------------------------------- /data_analysis/utils/collections.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) 2017-present, Facebook, Inc. 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | ############################################################################## 15 | 16 | """A simple attribute dictionary used for representing configuration options.""" 17 | 18 | from __future__ import absolute_import 19 | from __future__ import division 20 | from __future__ import print_function 21 | from __future__ import unicode_literals 22 | 23 | 24 | class AttrDict(dict): 25 | 26 | IMMUTABLE = '__immutable__' 27 | 28 | def __init__(self, *args, **kwargs): 29 | super(AttrDict, self).__init__(*args, **kwargs) 30 | self.__dict__[AttrDict.IMMUTABLE] = False 31 | 32 | def __getattr__(self, name): 33 | if name in self.__dict__: 34 | return self.__dict__[name] 35 | elif name in self: 36 | return self[name] 37 | else: 38 | raise AttributeError(name) 39 | 40 | def __setattr__(self, name, value): 41 | if not self.__dict__[AttrDict.IMMUTABLE]: 42 | if name in self.__dict__: 43 | self.__dict__[name] = value 44 | else: 45 | self[name] = value 46 | else: 47 | raise AttributeError( 48 | 'Attempted to set "{}" to "{}", but AttrDict is immutable'. 49 | format(name, value) 50 | ) 51 | 52 | def immutable(self, is_immutable): 53 | """Set immutability to is_immutable and recursively apply the setting 54 | to all nested AttrDicts. 55 | """ 56 | self.__dict__[AttrDict.IMMUTABLE] = is_immutable 57 | # Recursively set immutable state 58 | for v in self.__dict__.values(): 59 | if isinstance(v, AttrDict): 60 | v.immutable(is_immutable) 61 | for v in self.values(): 62 | if isinstance(v, AttrDict): 63 | v.immutable(is_immutable) 64 | 65 | def is_immutable(self): 66 | return self.__dict__[AttrDict.IMMUTABLE] 67 | -------------------------------------------------------------------------------- /data_analysis/utils/detectron_weight_helper.py: -------------------------------------------------------------------------------- 1 | """Helper functions for loading pretrained weights from Detectron pickle files 2 | """ 3 | 4 | import pickle 5 | import re 6 | import torch 7 | 8 | 9 | def load_detectron_weight(net, detectron_weight_file): 10 | name_mapping, orphan_in_detectron = net.detectron_weight_mapping 11 | 12 | with open(detectron_weight_file, 'rb') as fp: 13 | src_blobs = pickle.load(fp, encoding='latin1') 14 | if 'blobs' in src_blobs: 15 | src_blobs = src_blobs['blobs'] 16 | 17 | params = net.state_dict() 18 | for p_name, p_tensor in params.items(): 19 | d_name = name_mapping[p_name] 20 | if isinstance(d_name, str): # maybe str, None or True 21 | v = src_blobs.get(d_name) 22 | if v is not None: 23 | p_tensor.copy_(torch.Tensor(v)) 24 | 25 | def resnet_weights_name_pattern(): 26 | pattern = re.compile(r"conv1_w|conv1_gn_[sb]|res_conv1_.+|res\d+_\d+_.+") 27 | return pattern 28 | 29 | 30 | if __name__ == '__main__': 31 | """Testing""" 32 | from pprint import pprint 33 | import sys 34 | sys.path.insert(0, '..') 35 | from modeling.model_builder import Generalized_RCNN 36 | from core.config import cfg, cfg_from_file 37 | 38 | cfg.MODEL.NUM_CLASSES = 81 39 | cfg_from_file('../../cfgs/res50_mask.yml') 40 | net = Generalized_RCNN() 41 | 42 | # pprint(list(net.state_dict().keys()), width=1) 43 | 44 | mapping, orphans = net.detectron_weight_mapping 45 | state_dict = net.state_dict() 46 | 47 | for k in mapping.keys(): 48 | assert k in state_dict, '%s' % k 49 | 50 | rest = set(state_dict.keys()) - set(mapping.keys()) 51 | assert len(rest) == 0 52 | -------------------------------------------------------------------------------- /data_analysis/utils/env.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) 2017-present, Facebook, Inc. 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | ############################################################################## 15 | 16 | """Environment helper functions.""" 17 | 18 | from __future__ import absolute_import 19 | from __future__ import division 20 | from __future__ import print_function 21 | from __future__ import unicode_literals 22 | 23 | import os 24 | import sys 25 | 26 | # Default value of the CMake install prefix 27 | _CMAKE_INSTALL_PREFIX = '/usr/local' 28 | 29 | 30 | def get_runtime_dir(): 31 | """Retrieve the path to the runtime directory.""" 32 | return os.getcwd() 33 | 34 | 35 | def get_py_bin_ext(): 36 | """Retrieve python binary extension.""" 37 | return '.py' 38 | 39 | 40 | def set_up_matplotlib(): 41 | """Set matplotlib up.""" 42 | import matplotlib 43 | # Use a non-interactive backend 44 | matplotlib.use('Agg') 45 | 46 | 47 | def exit_on_error(): 48 | """Exit from a detectron tool when there's an error.""" 49 | sys.exit(1) 50 | -------------------------------------------------------------------------------- /data_analysis/utils/image.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) 2017-present, Facebook, Inc. 2 | # 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | ############################################################################## 15 | 16 | """Image helper functions.""" 17 | 18 | from __future__ import absolute_import 19 | from __future__ import division 20 | from __future__ import print_function 21 | from __future__ import unicode_literals 22 | 23 | import cv2 24 | import numpy as np 25 | 26 | 27 | def aspect_ratio_rel(im, aspect_ratio): 28 | """Performs width-relative aspect ratio transformation.""" 29 | im_h, im_w = im.shape[:2] 30 | im_ar_w = int(round(aspect_ratio * im_w)) 31 | im_ar = cv2.resize(im, dsize=(im_ar_w, im_h)) 32 | return im_ar 33 | 34 | 35 | def aspect_ratio_abs(im, aspect_ratio): 36 | """Performs absolute aspect ratio transformation.""" 37 | im_h, im_w = im.shape[:2] 38 | im_area = im_h * im_w 39 | 40 | im_ar_w = np.sqrt(im_area * aspect_ratio) 41 | im_ar_h = np.sqrt(im_area / aspect_ratio) 42 | assert np.isclose(im_ar_w / im_ar_h, aspect_ratio) 43 | 44 | im_ar = cv2.resize(im, dsize=(int(im_ar_w), int(im_ar_h))) 45 | return im_ar 46 | -------------------------------------------------------------------------------- /data_analysis/utils/timer.py: -------------------------------------------------------------------------------- 1 | from __future__ import absolute_import 2 | from __future__ import division 3 | from __future__ import print_function 4 | from __future__ import unicode_literals 5 | 6 | import time 7 | 8 | 9 | class Timer(object): 10 | """A simple timer.""" 11 | 12 | def __init__(self): 13 | self.reset() 14 | 15 | def tic(self): 16 | # using time.time instead of time.clock because time time.clock 17 | # does not normalize for multithreading 18 | self.start_time = time.time() 19 | 20 | def toc(self, average=True): 21 | self.diff = time.time() - self.start_time 22 | self.total_time += self.diff 23 | self.calls += 1 24 | self.average_time = self.total_time / self.calls 25 | if average: 26 | return self.average_time 27 | else: 28 | return self.diff 29 | 30 | def reset(self): 31 | self.total_time = 0. 32 | self.calls = 0 33 | self.start_time = 0. 34 | self.diff = 0. 35 | self.average_time = 0. 36 | -------------------------------------------------------------------------------- /demo/README.md: -------------------------------------------------------------------------------- 1 | ## Webcam and Jupyter notebook demo 2 | 3 | This folder contains a simple webcam demo that illustrates how you can use `maskrcnn_benchmark` for inference. 4 | 5 | 6 | ### With your preferred environment 7 | 8 | You can start it by running it from this folder, using one of the following commands: 9 | ```bash 10 | # by default, it runs on the GPU 11 | # for best results, use min-image-size 800 12 | python webcam.py --min-image-size 800 13 | # can also run it on the CPU 14 | python webcam.py --min-image-size 300 MODEL.DEVICE cpu 15 | # or change the model that you want to use 16 | python webcam.py --config-file ../configs/caffe2/e2e_mask_rcnn_R_101_FPN_1x_caffe2.yaml --min-image-size 300 MODEL.DEVICE cpu 17 | # in order to see the probability heatmaps, pass --show-mask-heatmaps 18 | python webcam.py --min-image-size 300 --show-mask-heatmaps MODEL.DEVICE cpu 19 | ``` 20 | 21 | ### With Docker 22 | 23 | Build the image with the tag `maskrcnn-benchmark` (check [INSTALL.md](../INSTALL.md) for instructions) 24 | 25 | Adjust permissions of the X server host (be careful with this step, refer to 26 | [here](http://wiki.ros.org/docker/Tutorials/GUI) for alternatives) 27 | 28 | ```bash 29 | xhost + 30 | ``` 31 | 32 | Then run a container with the demo: 33 | 34 | ``` 35 | docker run --rm -it \ 36 | -e DISPLAY=${DISPLAY} \ 37 | --privileged \ 38 | -v /tmp/.X11-unix:/tmp/.X11-unix \ 39 | --device=/dev/video0:/dev/video0 \ 40 | --ipc=host maskrcnn-benchmark \ 41 | python demo/webcam.py --min-image-size 300 42 | ``` 43 | 44 | **DISCLAIMER:** *This was tested for an Ubuntu 16.04 machine, 45 | the volume mapping may vary depending on your platform* 46 | -------------------------------------------------------------------------------- /demo/demo_e2e_mask_rcnn_R_50_FPN_1x.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/demo/demo_e2e_mask_rcnn_R_50_FPN_1x.png -------------------------------------------------------------------------------- /demo/demo_e2e_mask_rcnn_X_101_32x8d_FPN_1x.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/demo/demo_e2e_mask_rcnn_X_101_32x8d_FPN_1x.png -------------------------------------------------------------------------------- /demo/webcam.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | import argparse 3 | import cv2 4 | 5 | from maskrcnn_benchmark.config import cfg 6 | from predictor import COCODemo 7 | 8 | import time 9 | 10 | 11 | def main(): 12 | parser = argparse.ArgumentParser(description="PyTorch Object Detection Webcam Demo") 13 | parser.add_argument( 14 | "--config-file", 15 | default="../configs/caffe2/e2e_mask_rcnn_R_50_FPN_1x_caffe2.yaml", 16 | metavar="FILE", 17 | help="path to config file", 18 | ) 19 | parser.add_argument( 20 | "--confidence-threshold", 21 | type=float, 22 | default=0.7, 23 | help="Minimum score for the prediction to be shown", 24 | ) 25 | parser.add_argument( 26 | "--min-image-size", 27 | type=int, 28 | default=224, 29 | help="Smallest size of the image to feed to the model. " 30 | "Model was trained with 800, which gives best results", 31 | ) 32 | parser.add_argument( 33 | "--show-mask-heatmaps", 34 | dest="show_mask_heatmaps", 35 | help="Show a heatmap probability for the top masks-per-dim masks", 36 | action="store_true", 37 | ) 38 | parser.add_argument( 39 | "--masks-per-dim", 40 | type=int, 41 | default=2, 42 | help="Number of heatmaps per dimension to show", 43 | ) 44 | parser.add_argument( 45 | "opts", 46 | help="Modify model config options using the command-line", 47 | default=None, 48 | nargs=argparse.REMAINDER, 49 | ) 50 | 51 | args = parser.parse_args() 52 | 53 | # load config from file and command-line arguments 54 | cfg.merge_from_file(args.config_file) 55 | cfg.merge_from_list(args.opts) 56 | cfg.freeze() 57 | 58 | # prepare object that handles inference plus adds predictions on top of image 59 | coco_demo = COCODemo( 60 | cfg, 61 | confidence_threshold=args.confidence_threshold, 62 | show_mask_heatmaps=args.show_mask_heatmaps, 63 | masks_per_dim=args.masks_per_dim, 64 | min_image_size=args.min_image_size, 65 | ) 66 | 67 | cam = cv2.VideoCapture(0) 68 | while True: 69 | start_time = time.time() 70 | ret_val, img = cam.read() 71 | composite = coco_demo.run_on_opencv_image(img) 72 | print("Time: {:.2f} s / img".format(time.time() - start_time)) 73 | cv2.imshow("COCO detections", composite) 74 | if cv2.waitKey(1) == 27: 75 | break # esc to quit 76 | cv2.destroyAllWindows() 77 | 78 | 79 | if __name__ == "__main__": 80 | main() 81 | -------------------------------------------------------------------------------- /killpy.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | ps -ef|grep python|grep -v grep|cut -c 9-15|xargs kill -9 3 | 4 | -------------------------------------------------------------------------------- /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 | 4 | 5 | def adjustment_for_relation(cfg): 6 | if cfg.MODEL.RELATION_ON: 7 | cfg.MODEL.ROI_HEADS.BATCH_SIZE_PER_IMAGE = \ 8 | cfg.MODEL.RELATION.MAKE_PAIR_PROPOSAL_CNT * 2 9 | if cfg.MODEL.RELATION.USE_DETECTION_RESULT_FOR_RELATION: 10 | cfg.MODEL.ROI_HEADS.DETECTIONS_PER_IMG = \ 11 | cfg.MODEL.RELATION.MAKE_PAIR_PROPOSAL_CNT 12 | return cfg -------------------------------------------------------------------------------- /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/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 | 7 | PYBIND11_MODULE(TORCH_EXTENSION_NAME, m) { 8 | m.def("nms", &nms, "non-maximum suppression"); 9 | m.def("roi_align_forward", &ROIAlign_forward, "ROIAlign_forward"); 10 | m.def("roi_align_backward", &ROIAlign_backward, "ROIAlign_backward"); 11 | m.def("roi_pool_forward", &ROIPool_forward, "ROIPool_forward"); 12 | m.def("roi_pool_backward", &ROIPool_backward, "ROIPool_backward"); 13 | m.def("sigmoid_focalloss_forward", &SigmoidFocalLoss_forward, "SigmoidFocalLoss_forward"); 14 | m.def("sigmoid_focalloss_backward", &SigmoidFocalLoss_backward, "SigmoidFocalLoss_backward"); 15 | } 16 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/data/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | from .build import make_data_loader 3 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/data/collate_batch.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | from maskrcnn_benchmark.modeling import registry 3 | from maskrcnn_benchmark.structures.image_list import to_image_list 4 | 5 | 6 | @registry.BATCH_COLLATOR.register("DetectionOnlyCollator") 7 | class BatchCollator(object): 8 | """ 9 | From a list of samples from the dataset, 10 | returns the batched images and targets. 11 | This should be passed to the DataLoader 12 | """ 13 | 14 | def __init__(self, size_divisible=0): 15 | self.size_divisible = size_divisible 16 | 17 | def __call__(self, batch): 18 | transposed_batch = list(zip(*batch)) 19 | images = to_image_list(transposed_batch[0], self.size_divisible) 20 | targets = transposed_batch[1] 21 | img_ids = transposed_batch[2] 22 | return images, targets, img_ids 23 | 24 | 25 | @registry.BATCH_COLLATOR.register("RelationCollator") 26 | class RelationBatchCollator: 27 | def __init__(self, size_divisible=0): 28 | self.size_divisible = size_divisible 29 | 30 | def __call__(self, batch): 31 | transposed_batch = list(zip(*batch)) 32 | images = to_image_list(transposed_batch[0], self.size_divisible) 33 | det_targets = transposed_batch[1] 34 | rel_targets = transposed_batch[2] 35 | img_ids = transposed_batch[3] 36 | 37 | return images, (det_targets, rel_targets), img_ids 38 | 39 | 40 | @registry.BATCH_COLLATOR.register("VGCollator") 41 | class VGBatchCollator: 42 | def __init__(self, size_divisible=0): 43 | self.size_divisible = size_divisible 44 | 45 | def __call__(self, batch): 46 | transposed_batch = list(zip(*batch)) 47 | 48 | # images = to_image_list(transposed_batch[0], self.size_divisible) 49 | images = transposed_batch[0] 50 | targets = transposed_batch[1] 51 | img_id = transposed_batch[2] 52 | phrase_ids = transposed_batch[3] 53 | sent_id = transposed_batch[4] 54 | sentence = transposed_batch[5] 55 | precompute_bbox = transposed_batch[6] 56 | precompute_score = transposed_batch[7] 57 | feature_map = transposed_batch[8] 58 | vocab_label_elmo = transposed_batch[9] 59 | sent_sg = transposed_batch[10] 60 | topN_box = transposed_batch[11] 61 | 62 | return images, targets, img_id, phrase_ids, sent_id, sentence, precompute_bbox, precompute_score, feature_map, vocab_label_elmo, sent_sg, topN_box 63 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/data/datasets/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | # from .coco import COCODataset 3 | # from .concat_dataset import ConcatDataset 4 | # from .visual_genome import VGDataset 5 | # from .voc import PascalVOCDataset 6 | from .flickr import Flickr 7 | 8 | # __all__ = ["COCODataset", "ConcatDataset", "PascalVOCDataset", "VGDataset", "Flickr"] 9 | __all__ = ["Flickr"] 10 | -------------------------------------------------------------------------------- /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/VG/__init__.py: -------------------------------------------------------------------------------- 1 | import logging 2 | 3 | from maskrcnn_benchmark.config import cfg 4 | from .vg_eval import eval_detection, eval_relation 5 | 6 | 7 | def vg_evaluation( 8 | dataset, 9 | predictions, 10 | output_folder, 11 | box_only, 12 | iou_types, 13 | expected_results, 14 | expected_results_sigma_tol, ): 15 | logger = logging.getLogger(__name__) 16 | # split prediction 17 | det_predictions = [] 18 | rel_predictions = [] 19 | for prop, res in predictions: 20 | if cfg.MODEL.RELATION_ON: 21 | det_predictions.append((prop, res[0])) 22 | rel_predictions.append(res[1]) 23 | else: 24 | det_predictions.append((prop, res)) 25 | proposal_eval_res = None 26 | det_eval_results = None 27 | coco_results = None 28 | rel_eval_results = None 29 | proposal_eval_res, det_eval_results, \ 30 | coco_results = eval_detection(dataset=dataset, 31 | predictions=det_predictions, 32 | box_only=box_only, 33 | output_folder=output_folder, 34 | iou_types=iou_types, 35 | expected_results=expected_results, 36 | expected_results_sigma_tol=expected_results_sigma_tol, ) 37 | if cfg.MODEL.RELATION_ON: 38 | # relation evaluations 39 | rel_eval_results = eval_relation(dataset=dataset, 40 | predictions=rel_predictions, 41 | output_folder=output_folder) 42 | 43 | logger.info("vg evaluation done") 44 | return proposal_eval_res, det_eval_results, rel_eval_results, coco_results 45 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/data/datasets/evaluation/__init__.py: -------------------------------------------------------------------------------- 1 | from maskrcnn_benchmark.data import datasets 2 | # from .VG import vg_evaluation 3 | # from .coco import coco_evaluation 4 | # from .voc import voc_evaluation 5 | from .flickr import flick_evaluation 6 | 7 | 8 | def evaluate(dataset, predictions, image_ids, curr_iter, output_folder, **kwargs): 9 | """evaluate dataset using different methods based on dataset type. 10 | Args: 11 | dataset: Dataset object 12 | predictions(list[BoxList]): each item in the list represents the 13 | prediction results for one image. 14 | output_folder: output folder, to save evaluation files or results. 15 | **kwargs: other args. 16 | Returns: 17 | evaluation result 18 | """ 19 | args = dict( 20 | dataset=dataset, predictions=predictions,image_ids=image_ids, curr_iter=curr_iter, output_folder=output_folder 21 | ) 22 | # if isinstance(dataset, datasets.COCODataset): 23 | # return coco_evaluation(**args) 24 | # 25 | # elif isinstance(dataset, datasets.VGDataset): 26 | # return vg_evaluation(**args) 27 | # 28 | # elif isinstance(dataset, datasets.PascalVOCDataset): 29 | # return voc_evaluation(**args) 30 | if isinstance(dataset, datasets.Flickr): 31 | return flick_evaluation(**args) 32 | 33 | else: 34 | dataset_name = dataset.__class__.__name__ 35 | raise NotImplementedError("Unsupported dataset type {}.".format(dataset_name)) 36 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/data/datasets/evaluation/coco/__init__.py: -------------------------------------------------------------------------------- 1 | from .coco_eval import do_coco_evaluation 2 | 3 | 4 | def coco_evaluation( 5 | dataset, 6 | predictions, 7 | output_folder, 8 | box_only, 9 | iou_types, 10 | expected_results, 11 | expected_results_sigma_tol, 12 | ): 13 | return do_coco_evaluation( 14 | dataset=dataset, 15 | predictions=predictions, 16 | box_only=box_only, 17 | output_folder=output_folder, 18 | iou_types=iou_types, 19 | expected_results=expected_results, 20 | expected_results_sigma_tol=expected_results_sigma_tol, 21 | ) 22 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/data/datasets/evaluation/flickr/__init__.py: -------------------------------------------------------------------------------- 1 | from .flickr_eval import eval_recall 2 | 3 | 4 | def flick_evaluation(dataset, predictions, image_ids,curr_iter, output_folder): 5 | return eval_recall(dataset, predictions, image_ids, curr_iter, output_folder) -------------------------------------------------------------------------------- /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(dataset, predictions, output_folder, box_only, **_): 7 | logger = logging.getLogger("maskrcnn_benchmark.inference") 8 | if box_only: 9 | logger.warning("voc evaluation doesn't support box_only, ignored.") 10 | logger.info("performing voc evaluation, ignored iou_types.") 11 | return do_voc_evaluation( 12 | dataset=dataset, 13 | predictions=predictions, 14 | output_folder=output_folder, 15 | logger=logger, 16 | ) 17 | -------------------------------------------------------------------------------- /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/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 .build import build_transforms 3 | from .transforms import Compose 4 | from .transforms import Normalize 5 | from .transforms import RandomHorizontalFlip 6 | from .transforms import Resize 7 | from .transforms import ToTensor 8 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/data/transforms/build.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | from . import transforms_vg_bp as TBP 3 | 4 | 5 | def build_transforms(cfg, is_train=True): 6 | if is_train: 7 | min_size = cfg.INPUT.MIN_SIZE_TRAIN 8 | max_size = cfg.INPUT.MAX_SIZE_TRAIN 9 | # flip_prob = 0.5 # cfg.INPUT.FLIP_PROB_TRAIN 10 | flip_prob = 0 11 | else: 12 | min_size = cfg.INPUT.MIN_SIZE_TEST 13 | max_size = cfg.INPUT.MAX_SIZE_TEST 14 | flip_prob = 0 15 | 16 | to_bgr255 = cfg.INPUT.TO_BGR255 17 | normalize_transform = TBP.Normalize( 18 | mean=cfg.INPUT.PIXEL_MEAN, std=cfg.INPUT.PIXEL_STD, to_bgr255=to_bgr255 19 | ) 20 | 21 | To255 = TBP.To255(mean=cfg.INPUT.PIXEL_MEAN, std=cfg.INPUT.PIXEL_STD, to_bgr255=to_bgr255) 22 | 23 | transform = TBP.Compose( 24 | [ 25 | TBP.ResizeAndNormalize(min_size, max_size, cfg.INPUT.PIXEL_MEAN, cfg.INPUT.PIXEL_STD), 26 | TBP.ToTensor(), 27 | ] 28 | ) 29 | return transform 30 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/engine/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/layers/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | import torch 3 | 4 | from .batch_norm import FrozenBatchNorm2d 5 | from .misc import Conv2d 6 | from .misc import ConvTranspose2d 7 | from .misc import BatchNorm2d 8 | from .misc import interpolate 9 | from .nms import nms 10 | from .roi_align import ROIAlign 11 | from .roi_align import roi_align 12 | from .roi_pool import ROIPool 13 | from .roi_pool import roi_pool 14 | from .smooth_l1_loss import smooth_l1_loss 15 | from .sigmoid_focal_loss import SigmoidFocalLoss 16 | 17 | __all__ = ["nms", "roi_align", "ROIAlign", "roi_pool", "ROIPool", 18 | "smooth_l1_loss", "Conv2d", "ConvTranspose2d", "interpolate", 19 | "BatchNorm2d", "FrozenBatchNorm2d", "SigmoidFocalLoss" 20 | ] 21 | 22 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/layers/_utils.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | import glob 3 | import os.path 4 | 5 | import torch 6 | 7 | try: 8 | from torch.utils.cpp_extension import load as load_ext 9 | from torch.utils.cpp_extension import CUDA_HOME 10 | except ImportError: 11 | raise ImportError("The cpp layer extensions requires PyTorch 0.4 or higher") 12 | 13 | 14 | def _load_C_extensions(): 15 | this_dir = os.path.dirname(os.path.abspath(__file__)) 16 | this_dir = os.path.dirname(this_dir) 17 | this_dir = os.path.join(this_dir, "csrc") 18 | 19 | main_file = glob.glob(os.path.join(this_dir, "*.cpp")) 20 | source_cpu = glob.glob(os.path.join(this_dir, "cpu", "*.cpp")) 21 | source_cuda = glob.glob(os.path.join(this_dir, "cuda", "*.cu")) 22 | 23 | source = main_file + source_cpu 24 | 25 | extra_cflags = [] 26 | if torch.cuda.is_available() and CUDA_HOME is not None: 27 | source.extend(source_cuda) 28 | extra_cflags = ["-DWITH_CUDA"] 29 | source = [os.path.join(this_dir, s) for s in source] 30 | extra_include_paths = [this_dir] 31 | return load_ext( 32 | "torchvision", 33 | source, 34 | extra_cflags=extra_cflags, 35 | extra_include_paths=extra_include_paths, 36 | ) 37 | 38 | 39 | _C = _load_C_extensions() 40 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/layers/batch_norm.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | import torch 3 | from torch import nn 4 | 5 | 6 | class FrozenBatchNorm2d(nn.Module): 7 | """ 8 | BatchNorm2d where the batch statistics and the affine parameters 9 | are fixed 10 | """ 11 | 12 | def __init__(self, n): 13 | super(FrozenBatchNorm2d, self).__init__() 14 | self.register_buffer("weight", torch.ones(n)) 15 | self.register_buffer("bias", torch.zeros(n)) 16 | self.register_buffer("running_mean", torch.zeros(n)) 17 | self.register_buffer("running_var", torch.ones(n)) 18 | 19 | def forward(self, x): 20 | scale = self.weight * self.running_var.rsqrt() 21 | bias = self.bias - self.running_mean * scale 22 | scale = scale.reshape(1, -1, 1, 1) 23 | bias = bias.reshape(1, -1, 1, 1) 24 | return x * scale + bias 25 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/layers/nms.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | # from ._utils import _C 3 | from maskrcnn_benchmark import _C 4 | 5 | nms = _C.nms 6 | # nms.__doc__ = """ 7 | # This function performs Non-maximum suppresion""" 8 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/layers/roi_align.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | import torch 3 | from torch import nn 4 | from torch.autograd import Function 5 | from torch.autograd.function import once_differentiable 6 | from torch.nn.modules.utils import _pair 7 | 8 | from maskrcnn_benchmark import _C 9 | 10 | 11 | class _ROIAlign(Function): 12 | @staticmethod 13 | def forward(ctx, input, roi, output_size, spatial_scale, sampling_ratio): 14 | ctx.save_for_backward(roi) 15 | ctx.output_size = _pair(output_size) 16 | ctx.spatial_scale = spatial_scale 17 | ctx.sampling_ratio = sampling_ratio 18 | ctx.input_shape = input.size() 19 | output = _C.roi_align_forward( 20 | input, roi, spatial_scale, output_size[0], output_size[1], sampling_ratio 21 | ) 22 | return output 23 | 24 | @staticmethod 25 | @once_differentiable 26 | def backward(ctx, grad_output): 27 | rois, = ctx.saved_tensors 28 | output_size = ctx.output_size 29 | spatial_scale = ctx.spatial_scale 30 | sampling_ratio = ctx.sampling_ratio 31 | bs, ch, h, w = ctx.input_shape 32 | grad_input = _C.roi_align_backward( 33 | grad_output, 34 | rois, 35 | spatial_scale, 36 | output_size[0], 37 | output_size[1], 38 | bs, 39 | ch, 40 | h, 41 | w, 42 | sampling_ratio, 43 | ) 44 | return grad_input, None, None, None, None 45 | 46 | 47 | roi_align = _ROIAlign.apply 48 | 49 | 50 | class ROIAlign(nn.Module): 51 | def __init__(self, output_size, spatial_scale, sampling_ratio): 52 | super(ROIAlign, self).__init__() 53 | self.output_size = output_size 54 | self.spatial_scale = spatial_scale 55 | self.sampling_ratio = sampling_ratio 56 | 57 | def forward(self, input, rois): 58 | return roi_align( 59 | input, rois, self.output_size, self.spatial_scale, self.sampling_ratio 60 | ) 61 | 62 | def __repr__(self): 63 | tmpstr = self.__class__.__name__ + "(" 64 | tmpstr += "output_size=" + str(self.output_size) 65 | tmpstr += ", spatial_scale=" + str(self.spatial_scale) 66 | tmpstr += ", sampling_ratio=" + str(self.sampling_ratio) 67 | tmpstr += ")" 68 | return tmpstr 69 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/layers/roi_pool.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | import torch 3 | from torch import nn 4 | from torch.autograd import Function 5 | from torch.autograd.function import once_differentiable 6 | from torch.nn.modules.utils import _pair 7 | 8 | from maskrcnn_benchmark import _C 9 | 10 | 11 | class _ROIPool(Function): 12 | @staticmethod 13 | def forward(ctx, input, roi, output_size, spatial_scale): 14 | ctx.output_size = _pair(output_size) 15 | ctx.spatial_scale = spatial_scale 16 | ctx.input_shape = input.size() 17 | output, argmax = _C.roi_pool_forward( 18 | input, roi, spatial_scale, output_size[0], output_size[1] 19 | ) 20 | ctx.save_for_backward(input, roi, argmax) 21 | return output 22 | 23 | @staticmethod 24 | @once_differentiable 25 | def backward(ctx, grad_output): 26 | input, rois, argmax = ctx.saved_tensors 27 | output_size = ctx.output_size 28 | spatial_scale = ctx.spatial_scale 29 | bs, ch, h, w = ctx.input_shape 30 | grad_input = _C.roi_pool_backward( 31 | grad_output, 32 | input, 33 | rois, 34 | argmax, 35 | spatial_scale, 36 | output_size[0], 37 | output_size[1], 38 | bs, 39 | ch, 40 | h, 41 | w, 42 | ) 43 | return grad_input, None, None, None 44 | 45 | 46 | roi_pool = _ROIPool.apply 47 | 48 | 49 | class ROIPool(nn.Module): 50 | def __init__(self, output_size, spatial_scale): 51 | super(ROIPool, self).__init__() 52 | self.output_size = output_size 53 | self.spatial_scale = spatial_scale 54 | 55 | def forward(self, input, rois): 56 | return roi_pool(input, rois, self.output_size, self.spatial_scale) 57 | 58 | def __repr__(self): 59 | tmpstr = self.__class__.__name__ + "(" 60 | tmpstr += "output_size=" + str(self.output_size) 61 | tmpstr += ", spatial_scale=" + str(self.spatial_scale) 62 | tmpstr += ")" 63 | return tmpstr 64 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/layers/sigmoid_focal_loss.py: -------------------------------------------------------------------------------- 1 | import torch 2 | from torch import nn 3 | from torch.autograd import Function 4 | from torch.autograd.function import once_differentiable 5 | 6 | from maskrcnn_benchmark import _C 7 | 8 | # TODO: Use JIT to replace CUDA implementation in the future. 9 | class _SigmoidFocalLoss(Function): 10 | @staticmethod 11 | def forward(ctx, logits, targets, gamma, alpha): 12 | ctx.save_for_backward(logits, targets) 13 | num_classes = logits.shape[1] 14 | ctx.num_classes = num_classes 15 | ctx.gamma = gamma 16 | ctx.alpha = alpha 17 | 18 | losses = _C.sigmoid_focalloss_forward( 19 | logits, targets, num_classes, gamma, alpha 20 | ) 21 | return losses 22 | 23 | @staticmethod 24 | @once_differentiable 25 | def backward(ctx, d_loss): 26 | logits, targets = ctx.saved_tensors 27 | num_classes = ctx.num_classes 28 | gamma = ctx.gamma 29 | alpha = ctx.alpha 30 | d_loss = d_loss.contiguous() 31 | d_logits = _C.sigmoid_focalloss_backward( 32 | logits, targets, d_loss, num_classes, gamma, alpha 33 | ) 34 | return d_logits, None, None, None, None 35 | 36 | 37 | sigmoid_focal_loss_cuda = _SigmoidFocalLoss.apply 38 | 39 | 40 | def sigmoid_focal_loss_cpu(logits, targets, gamma, alpha): 41 | num_classes = logits.shape[1] 42 | gamma = gamma[0] 43 | alpha = alpha[0] 44 | dtype = targets.dtype 45 | device = targets.device 46 | class_range = torch.arange(1, num_classes+1, dtype=dtype, device=device).unsqueeze(0) 47 | 48 | t = targets.unsqueeze(1) 49 | p = torch.sigmoid(logits) 50 | term1 = (1 - p) ** gamma * torch.log(p) 51 | term2 = p ** gamma * torch.log(1 - p) 52 | return -(t == class_range).float() * term1 * alpha - ((t != class_range) * (t >= 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 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/layers/spatial_coordinate.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/python3.6 2 | # -*- coding: utf-8 -*- 3 | # @Time : 2019-07-09 13:40 4 | # @Author : Yongfei Liu 5 | # @Email : liuyf3@shanghaitech.edu.cn 6 | 7 | import numpy as np 8 | import torch 9 | 10 | 11 | 12 | def meshgrid_generation(feat): 13 | 14 | b, c, h, w = feat.shape 15 | 16 | device = feat.get_device() 17 | half_h = h/2 18 | half_w = w/2 19 | 20 | grid_h, grid_w = torch.meshgrid(torch.arange(h), torch.arange(w)) 21 | grid_h = grid_h.float() 22 | grid_w = grid_w.float() 23 | grid_h = grid_h/half_h - 1 24 | grid_w = grid_w/half_w - 1 25 | spatial_coord = torch.cat((grid_h[None,None, :,:], grid_w[None, None, :, :]), 1) 26 | spatial_coord = spatial_coord.to(device) 27 | 28 | return spatial_coord 29 | 30 | 31 | def get_spatial_feat(precomp_boxes): 32 | 33 | bbox = precomp_boxes.bbox 34 | bbox_size = [precomp_boxes.size[0], precomp_boxes.size[1]] ## width, height 35 | bbox_area = (bbox[:, 2] - bbox[:, 0]) * (bbox[:, 3] - bbox[:, 1]) 36 | bbox_area_ratio = bbox_area / (bbox_size[0] * bbox_area[1]) 37 | bbox_area_ratio = bbox_area_ratio.unsqueeze(1) # 100 * 1 38 | device_id = precomp_boxes.bbox.get_device() 39 | bbox_size.extend(bbox_size) 40 | bbox_size = torch.FloatTensor(np.array(bbox_size).astype(np.float32)).to(device_id) 41 | bbox = bbox / bbox_size 42 | vis_spatial = torch.cat((bbox, bbox_area_ratio), 1) 43 | return vis_spatial 44 | 45 | if __name__ == '__main__': 46 | 47 | feat = torch.ones(3,1,50,50) 48 | meshgrid_generation(feat=feat) 49 | 50 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/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/vgg16.py: -------------------------------------------------------------------------------- 1 | import torch.nn as nn 2 | import torchvision.models as models 3 | 4 | 5 | class VGG16(nn.Module): 6 | def __init__(self, cfg): 7 | super(VGG16, self).__init__() 8 | self.features = models.vgg16_bn(pretrained=True).features 9 | self.out_channels = 512 10 | cnt = 0 11 | for each in self.features: 12 | if cnt >= cfg.MODEL.BACKBONE.FREEZE_CONV_BODY_AT: 13 | break 14 | cnt += 1 15 | set_trainable(each, requires_grad=False) 16 | 17 | def forward(self, im_data): 18 | x = self.features(im_data) 19 | return [x] # for the following process 20 | 21 | 22 | def set_trainable(model, requires_grad): 23 | set_trainable_param(model.parameters(), requires_grad) 24 | 25 | 26 | def set_trainable_param(parameters, requires_grad): 27 | for param in parameters: 28 | param.requires_grad = requires_grad 29 | -------------------------------------------------------------------------------- /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 | from .generalized_rcnn_det import GeneralizedRCNNDet 4 | 5 | 6 | _DETECTION_META_ARCHITECTURES = {"GeneralizedRCNN": GeneralizedRCNN, "GeneralizedRCNNDet": GeneralizedRCNNDet} 7 | 8 | 9 | def build_detection_model(cfg): 10 | meta_arch = _DETECTION_META_ARCHITECTURES[cfg.MODEL.META_ARCHITECTURE] 11 | return meta_arch(cfg) 12 | -------------------------------------------------------------------------------- /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_KEYPOINT_FEATURE_EXTRACTORS = Registry() 10 | ROI_KEYPOINT_PREDICTOR = Registry() 11 | ROI_MASK_FEATURE_EXTRACTORS = Registry() 12 | ROI_MASK_PREDICTOR = Registry() 13 | 14 | BATCH_COLLATOR = Registry() -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/relation/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/maskrcnn_benchmark/modeling/relation/__init__.py -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/roi_heads/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/maskrcnn_benchmark/modeling/roi_heads/__init__.py -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/roi_heads/box_head/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/maskrcnn_benchmark/modeling/roi_heads/box_head/__init__.py -------------------------------------------------------------------------------- /maskrcnn_benchmark/modeling/roi_heads/keypoint_head/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/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 .inference import make_roi_keypoint_post_processor 4 | from .loss import make_roi_keypoint_loss_evaluator 5 | from .roi_keypoint_feature_extractors import make_roi_keypoint_feature_extractor 6 | from .roi_keypoint_predictors import make_roi_keypoint_predictor 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.layers import Conv2d 5 | from maskrcnn_benchmark.modeling import registry 6 | from maskrcnn_benchmark.modeling.poolers import Pooler 7 | 8 | 9 | @registry.ROI_KEYPOINT_FEATURE_EXTRACTORS.register("KeypointRCNNFeatureExtractor") 10 | class KeypointRCNNFeatureExtractor(nn.Module): 11 | def __init__(self, cfg, in_channels): 12 | super(KeypointRCNNFeatureExtractor, self).__init__() 13 | 14 | resolution = cfg.MODEL.ROI_KEYPOINT_HEAD.POOLER_RESOLUTION 15 | scales = cfg.MODEL.ROI_KEYPOINT_HEAD.POOLER_SCALES 16 | sampling_ratio = cfg.MODEL.ROI_KEYPOINT_HEAD.POOLER_SAMPLING_RATIO 17 | pooler = Pooler( 18 | output_size=(resolution, resolution), 19 | scales=scales, 20 | sampling_ratio=sampling_ratio, 21 | ) 22 | self.pooler = pooler 23 | 24 | input_features = in_channels 25 | layers = cfg.MODEL.ROI_KEYPOINT_HEAD.CONV_LAYERS 26 | next_feature = input_features 27 | self.blocks = [] 28 | for layer_idx, layer_features in enumerate(layers, 1): 29 | layer_name = "conv_fcn{}".format(layer_idx) 30 | module = Conv2d(next_feature, layer_features, 3, stride=1, padding=1) 31 | nn.init.kaiming_normal_(module.weight, mode="fan_out", nonlinearity="relu") 32 | nn.init.constant_(module.bias, 0) 33 | self.add_module(layer_name, module) 34 | next_feature = layer_features 35 | self.blocks.append(layer_name) 36 | self.out_channels = layer_features 37 | 38 | def forward(self, x, proposals): 39 | x = self.pooler(x, proposals) 40 | for layer_name in self.blocks: 41 | x = F.relu(getattr(self, layer_name)(x)) 42 | return x 43 | 44 | 45 | def make_roi_keypoint_feature_extractor(cfg, in_channels): 46 | func = registry.ROI_KEYPOINT_FEATURE_EXTRACTORS[ 47 | cfg.MODEL.ROI_KEYPOINT_HEAD.FEATURE_EXTRACTOR 48 | ] 49 | return func(cfg, in_channels) 50 | -------------------------------------------------------------------------------- /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/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/maskrcnn_benchmark/modeling/roi_heads/mask_head/__init__.py -------------------------------------------------------------------------------- /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/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/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/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/modeling/vg/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/maskrcnn_benchmark/modeling/vg/__init__.py -------------------------------------------------------------------------------- /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 5 | -------------------------------------------------------------------------------- /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 5 | 6 | def make_optimizer(cfg, model): 7 | 8 | params = [] 9 | for key, value in model.named_parameters(): 10 | 11 | if not value.requires_grad: 12 | continue 13 | print('gradient', key) 14 | lr = cfg.SOLVER.BASE_LR 15 | if "body" in key or "head" in key: 16 | lr = cfg.SOLVER.BASE_LR * cfg.SOLVER.RESNET_LR_FACTOR 17 | elif "fpn" in key: 18 | lr = cfg.SOLVER.BASE_LR * cfg.SOLVER.FPN_LR_FACTOR 19 | elif 'phrase_embed' in key: 20 | lr = cfg.SOLVER.BASE_LR * cfg.SOLVER.PHRASE_EMBEDDING_LR_FACTOR 21 | 22 | # print(key) 23 | weight_decay = cfg.SOLVER.WEIGHT_DECAY 24 | # if "bias" in key: 25 | # lr = cfg.SOLVER.BASE_LR * cfg.SOLVER.BIAS_LR_FACTOR 26 | # weight_decay = cfg.SOLVER.WEIGHT_DECAY_BIAS 27 | if "bias" in key: 28 | lr = lr * cfg.SOLVER.BIAS_LR_FACTOR 29 | weight_decay = cfg.SOLVER.WEIGHT_DECAY_BIAS 30 | params += [{"params": [value], "lr": lr, "weight_decay": weight_decay}] 31 | 32 | if cfg.SOLVER.TYPE == "SGD": 33 | optimizer = torch.optim.SGD(params, lr, momentum=cfg.SOLVER.MOMENTUM) 34 | elif cfg.SOLVER.TYPE == 'Adam': 35 | optimizer = torch.optim.Adam(params, lr) 36 | else: 37 | raise NotImplementedError 38 | 39 | return optimizer 40 | 41 | 42 | def make_lr_scheduler(cfg, optimizer): 43 | return WarmupMultiStepLR( 44 | optimizer, 45 | cfg.SOLVER.STEPS, 46 | cfg.SOLVER.GAMMA, 47 | warmup_factor=cfg.SOLVER.WARMUP_FACTOR, 48 | warmup_iters=cfg.SOLVER.WARMUP_ITERS, 49 | warmup_method=cfg.SOLVER.WARMUP_METHOD, 50 | ) 51 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/solver/lr_scheduler.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | from bisect import bisect_right 3 | 4 | import torch 5 | 6 | 7 | # FIXME ideally this would be achieved with a CombinedLRScheduler, 8 | # separating MultiStepLR with WarmupLR 9 | # but the current LRScheduler design doesn't allow it 10 | class WarmupMultiStepLR(torch.optim.lr_scheduler._LRScheduler): 11 | def __init__( 12 | self, 13 | optimizer, 14 | milestones, 15 | gamma=0.1, 16 | warmup_factor=1.0 / 3, 17 | warmup_iters=500, 18 | warmup_method="linear", 19 | last_epoch=-1, 20 | ): 21 | if not list(milestones) == sorted(milestones): 22 | raise ValueError( 23 | "Milestones should be a list of" " increasing integers. Got {}", 24 | milestones, 25 | ) 26 | 27 | if warmup_method not in ("constant", "linear"): 28 | raise ValueError( 29 | "Only 'constant' or 'linear' warmup_method accepted" 30 | "got {}".format(warmup_method) 31 | ) 32 | self.milestones = milestones 33 | self.gamma = gamma 34 | self.warmup_factor = warmup_factor 35 | self.warmup_iters = warmup_iters 36 | self.warmup_method = warmup_method 37 | super(WarmupMultiStepLR, self).__init__(optimizer, last_epoch) 38 | 39 | def get_lr(self): 40 | warmup_factor = 1 41 | if self.last_epoch < self.warmup_iters: 42 | if self.warmup_method == "constant": 43 | warmup_factor = self.warmup_factor 44 | elif self.warmup_method == "linear": 45 | alpha = float(self.last_epoch) / self.warmup_iters 46 | warmup_factor = self.warmup_factor * (1 - alpha) + alpha 47 | return [ 48 | base_lr 49 | * warmup_factor 50 | * self.gamma ** bisect_right(self.milestones, self.last_epoch) 51 | for base_lr in self.base_lrs 52 | ] 53 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/structures/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/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 | if isinstance(tensors, ImageList): 40 | return tensors 41 | elif isinstance(tensors, torch.Tensor): 42 | # single tensor shape can be inferred 43 | if tensors.dim() == 3: 44 | tensors = tensors[None] 45 | assert tensors.dim() == 4 46 | image_sizes = [tensor.shape[-2:] for tensor in tensors] 47 | return ImageList(tensors, image_sizes) 48 | elif isinstance(tensors, (tuple, list)): 49 | max_size = tuple(max(s) for s in zip(*[img.shape for img in tensors])) 50 | 51 | # TODO Ideally, just remove this and let me model handle arbitrary 52 | # input sizs 53 | if size_divisible > 0: 54 | import math 55 | 56 | stride = size_divisible 57 | max_size = list(max_size) 58 | max_size[1] = int(math.ceil(max_size[1] / stride) * stride) 59 | max_size[2] = int(math.ceil(max_size[2] / stride) * stride) 60 | max_size = tuple(max_size) 61 | 62 | batch_shape = (len(tensors),) + max_size 63 | batched_imgs = tensors[0].new(*batch_shape).zero_() 64 | for img, pad_img in zip(tensors, batched_imgs): 65 | pad_img[: img.shape[0], : img.shape[1], : img.shape[2]].copy_(img) 66 | 67 | image_sizes = [im.shape[-2:] for im in tensors] 68 | 69 | return ImageList(batched_imgs, image_sizes) 70 | else: 71 | raise TypeError("Unsupported type for to_image_list: {}".format(type(tensors))) 72 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/structures/relation_triplet.py: -------------------------------------------------------------------------------- 1 | import torch 2 | 3 | from .bounding_box import BoxList 4 | 5 | class RelationTriplet: 6 | def __init__(self, instance:BoxList, 7 | pair_mat:torch.Tensor, phrase_label:torch.Tensor, phrase_score:torch.Tensor): 8 | """ 9 | 10 | :param sub: boxlist 11 | :param obj: boxlist 12 | :param pair_mat: shape (connection_num, 2) [sub, obj] 13 | :param phrase_label: phrase label_id 14 | :param phrase_score: phrase label_id 15 | """ 16 | 17 | self.instance = instance 18 | 19 | assert len(pair_mat) == len(phrase_label) 20 | assert len(phrase_label) == len(phrase_score) 21 | self.pair_mat = pair_mat 22 | self.phrase_l = phrase_label 23 | self.phrase_s = phrase_score 24 | 25 | self.extra_fields = {} 26 | 27 | def to(self, device): 28 | triplet = RelationTriplet(self.instance.to(device), 29 | self.pair_mat.to(device), 30 | self.phrase_l.to(device), 31 | self.phrase_s.to(device)) 32 | 33 | for k, v in self.extra_fields.items(): 34 | if hasattr(v, "to"): 35 | v = v.to(device) 36 | triplet.add_field(k, v) 37 | return triplet 38 | 39 | 40 | def get_instance_list(self, side): 41 | assert side in ['sub', 'obj'] 42 | if side == 'sub': 43 | return self.instance[self.pair_mat[: ,0]] 44 | else: 45 | return self.instance[self.pair_mat[:, 1]] 46 | 47 | 48 | 49 | """ 50 | add extra information to Box 51 | """ 52 | def add_field(self, field, field_data): 53 | assert len(field_data) == len(self.pair_mat) 54 | self.extra_fields[field] = field_data 55 | 56 | def get_field(self, field): 57 | return self.extra_fields[field] 58 | 59 | def has_field(self, field): 60 | return field in self.extra_fields 61 | 62 | def fields(self): 63 | return list(self.extra_fields.keys()) 64 | 65 | 66 | def __getitem__(self, item): 67 | triplet = RelationTriplet(self.instance, 68 | self.pair_mat[item], 69 | self.phrase_l[item], 70 | self.phrase_s[item]) 71 | for k, v in self.extra_fields.items(): 72 | triplet.add_field(k, v[item]) 73 | return triplet 74 | 75 | 76 | def __repr__(self): 77 | s = self.__class__.__name__ + "(" 78 | s += "num_relation={}, ".format(len(self.pair_mat)) 79 | s += "instance_num={}, ".format(len(self.instance)) 80 | s += ")" 81 | return s -------------------------------------------------------------------------------- /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/youngfly11/LCMCG-PyTorch/e95299b9a9f1b13e21750ef0dcde0941d703d009/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/debugger.py: -------------------------------------------------------------------------------- 1 | import ipdb 2 | 3 | from maskrcnn_benchmark.config import cfg 4 | 5 | def set_trace(): 6 | if cfg.DEBUG: 7 | ipdb.set_trace(context=10) -------------------------------------------------------------------------------- /maskrcnn_benchmark/utils/direction_word_dict.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/python3.6 2 | # -*- coding: utf-8 -*- 3 | # @Time : 2019-06-16 21:21 4 | # @Author : Yongfei Liu 5 | # @Email : liuyf3@shanghaitech.edu.cn 6 | """ 7 | Flickr: 8 | sent level, left:575, right:645 9 | phrase level, left:535, right 572 10 | """ 11 | 12 | left_word_dict = ['left-hand', 'left', 'left-turning', 'camera-left'] 13 | right_word_dict = ['right', 'upright', 'right-handed'] -------------------------------------------------------------------------------- /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.PY3: 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/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=100): 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})\n".format(name, meter.median, meter.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 os 4 | 5 | 6 | def mkdir(path): 7 | try: 8 | os.makedirs(path) 9 | except OSError as e: 10 | if e.errno != errno.EEXIST: 11 | raise 12 | -------------------------------------------------------------------------------- /maskrcnn_benchmark/utils/ops.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/python3.6 2 | # -*- coding: utf-8 -*- 3 | # @Time : 2019/8/11 15:31 4 | # @Author : Yongfei Liu 5 | # @Email : liuyf3@shanghaitech.edu.cn 6 | 7 | import numpy as np 8 | import torch 9 | import torch.nn as nn 10 | 11 | class Linear(nn.Linear): 12 | def __init__(self, *args, **kwargs): 13 | super().__init__(*args, **kwargs) 14 | 15 | # compatible with xavier_initializer in TensorFlow 16 | fan_avg = (self.in_features + self.out_features) / 2. 17 | bound = np.sqrt(3. / fan_avg) 18 | nn.init.uniform_(self.weight, -bound, bound) 19 | if self.bias is not None: 20 | nn.init.constant_(self.bias, 0.) 21 | 22 | 23 | def apply_mask1d(attention, image_locs): 24 | batch_size, num_loc = attention.size() 25 | tmp1 = attention.new_zeros(num_loc) 26 | tmp1[:num_loc] = torch.arange( 27 | 0, num_loc, dtype=attention.dtype).unsqueeze(0) 28 | 29 | tmp1 = tmp1.expand(batch_size, num_loc) 30 | tmp2 = image_locs.type(tmp1.type()) 31 | tmp2 = tmp2.unsqueeze(dim=1).expand(batch_size, num_loc) 32 | mask = torch.ge(tmp1, tmp2) 33 | attention = attention.masked_fill(mask, -1e30) 34 | return attention 35 | 36 | def apply_mask2d(attention, image_locs): 37 | batch_size, num_loc, _ = attention.size() 38 | tmp1 = attention.new_zeros(num_loc) 39 | tmp1[:num_loc] = torch.arange( 40 | 0, num_loc, dtype=attention.dtype).unsqueeze(0) 41 | 42 | tmp1 = tmp1.expand(batch_size, num_loc) 43 | tmp2 = image_locs.type(tmp1.type()) 44 | tmp2 = tmp2.unsqueeze(dim=1).expand(batch_size, num_loc) 45 | mask1d = torch.ge(tmp1, tmp2) 46 | mask2d = mask1d[:, None, :] | mask1d[:, :, None] 47 | attention = attention.masked_fill(mask2d, -1e30) 48 | return attention -------------------------------------------------------------------------------- /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 datetime 5 | import time 6 | 7 | import torch 8 | 9 | 10 | class Timer(object): 11 | def __init__(self): 12 | self.reset() 13 | 14 | @property 15 | def average_time(self): 16 | return self.total_time / self.calls if self.calls > 0 else 0.0 17 | 18 | def tic(self): 19 | # using time.time instead of time.clock because time time.clock 20 | # does not normalize for multithreading 21 | self.start_time = time.time() 22 | 23 | def toc(self, average=True): 24 | self.add(time.time() - self.start_time) 25 | if average: 26 | return self.average_time 27 | else: 28 | return self.diff 29 | 30 | def add(self, time_diff): 31 | self.diff = time_diff 32 | self.total_time += self.diff 33 | self.calls += 1 34 | 35 | def reset(self): 36 | self.total_time = 0.0 37 | self.calls = 0 38 | self.start_time = 0.0 39 | self.diff = 0.0 40 | 41 | def avg_time_str(self): 42 | time_str = str(datetime.timedelta(seconds=self.average_time)) 43 | return time_str 44 | 45 | 46 | def get_time_str(time_diff): 47 | time_str = str(datetime.timedelta(seconds=time_diff)) 48 | return time_str 49 | 50 | 51 | class SimpleTimer(object): 52 | """A simple timer.""" 53 | 54 | def __init__(self): 55 | self.total_time = 0. 56 | self.calls = 0 57 | self.start_time = 0. 58 | self.diff = 0. 59 | self.average_time = 0. 60 | 61 | def tic(self): 62 | # using time.time instead of time.clock because time time.clock 63 | # does not normalize for multithreading 64 | self.start_time = time.time() 65 | 66 | def toc(self, event="", average=False): 67 | torch.cuda.synchronize() 68 | self.diff = time.time() - self.start_time 69 | self.total_time += self.diff 70 | self.calls += 1 71 | self.average_time = self.total_time / self.calls 72 | if average: 73 | return self.average_time 74 | else: 75 | print("%-28s %f" % (event + "cost time:", self.diff)) 76 | return self.diff 77 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | ninja 2 | yacs 3 | cython 4 | matplotlib 5 | tqdm 6 | -------------------------------------------------------------------------------- /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: 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 | -------------------------------------------------------------------------------- /skipthoughts/__init__.py: -------------------------------------------------------------------------------- 1 | from .version import __version__ 2 | 3 | from .skipthoughts import AbstractSkipThoughts 4 | 5 | from .skipthoughts import AbstractUniSkip 6 | from .skipthoughts import UniSkip 7 | from .skipthoughts import DropUniSkip 8 | from .skipthoughts import BayesianUniSkip 9 | 10 | from .skipthoughts import AbstractBiSkip 11 | from .skipthoughts import BiSkip 12 | 13 | from .gru import AbstractGRUCell 14 | from .gru import GRUCell 15 | from .gru import BayesianGRUCell 16 | 17 | from .gru import AbstractGRU 18 | from .gru import GRU 19 | from .gru import BayesianGRU 20 | 21 | from .dropout import EmbeddingDropout 22 | from .dropout import SequentialDropout -------------------------------------------------------------------------------- /skipthoughts/version.py: -------------------------------------------------------------------------------- 1 | __version__ = '0.0.0' -------------------------------------------------------------------------------- /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/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 | --------------------------------------------------------------------------------