maskrcnn-benchmark
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
File Explorer
Download Latest Version (.zip)- bug-report.md
- feature-request.md
- questions-help-support.md
- 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
- e2e_faster_rcnn_R_50_FPN_1x_cocostyle.yaml
- e2e_mask_rcnn_R_50_FPN_1x_binarymask.yaml
- e2e_mask_rcnn_R_50_FPN_1x_cocostyle.yaml
- e2e_mask_rcnn_R_50_FPN_1x_poly.yaml
- README.md
- e2e_faster_rcnn_dconv_R_50_FPN_1x.yaml
- e2e_faster_rcnn_mdconv_R_50_FPN_1x.yaml
- e2e_mask_rcnn_dconv_R_50_FPN_1x.yaml
- e2e_mask_rcnn_mdconv_R_50_FPN_1x.yaml
- 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
- README.md
- 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
- 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
- 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_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
- e2e_mask_rcnn_R_50_FPN_1x.yaml
- e2e_faster_rcnn_fbnet.yaml
- e2e_faster_rcnn_fbnet_600.yaml
- e2e_faster_rcnn_fbnet_chamv1a_600.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_keypoint_rcnn_R_50_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
- 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_R_50_FPN_1x_periodically_testing.yaml
- e2e_mask_rcnn_X_101_32x8d_FPN_1x.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
- demo_e2e_mask_rcnn_R_50_FPN_1x.png
- demo_e2e_mask_rcnn_X_101_32x8d_FPN_1x.png
- Mask_R-CNN_demo.ipynb
- panoptic_segmentation_shapes_dataset_demo.ipynb
- predictor.py
- README.md
- shapes_dataset_demo.ipynb
- shapes_pruning.ipynb
- webcam.py
- Dockerfile
- jupyter_notebook_config.py
- Dockerfile
- __init__.py
- defaults.py
- paths_catalog.py
- nms_cpu.cpp
- ROIAlign_cpu.cpp
- vision.h
- deform_conv_cuda.cu
- deform_conv_kernel_cuda.cu
- deform_pool_cuda.cu
- deform_pool_kernel_cuda.cu
- nms.cu
- ROIAlign_cuda.cu
- ROIPool_cuda.cu
- SigmoidFocalLoss_cuda.cu
- vision.h
- deform_conv.h
- deform_pool.h
- nms.h
- ROIAlign.h
- ROIPool.h
- SigmoidFocalLoss.h
- vision.cpp
- __init__.py
- cityscapes_eval.py
- eval_instances.py
- __init__.py
- abs_to_coco.py
- coco_eval.py
- coco_eval_wrapper.py
- __init__.py
- voc_eval.py
- __init__.py
- __init__.py
- abstract.py
- cityscapes.py
- coco.py
- concat_dataset.py
- list_dataset.py
- voc.py
- __init__.py
- distributed.py
- grouped_batch_sampler.py
- iteration_based_batch_sampler.py
- __init__.py
- build.py
- transforms.py
- __init__.py
- build.py
- collate_batch.py
- README.md
- __init__.py
- bbox_aug.py
- inference.py
- trainer.py
- __init__.py
- deform_conv_func.py
- deform_conv_module.py
- deform_pool_func.py
- deform_pool_module.py
- __init__.py
- _utils.py
- batch_norm.py
- misc.py
- nms.py
- roi_align.py
- roi_pool.py
- sigmoid_focal_loss.py
- smooth_l1_loss.py
- __init__.py
- backbone.py
- fbnet.py
- fbnet_builder.py
- fbnet_modeldef.py
- fpn.py
- resnet.py
- __init__.py
- detectors.py
- generalized_rcnn.py
- __init__.py
- box_head.py
- inference.py
- loss.py
- roi_box_feature_extractors.py
- roi_box_predictors.py
- __init__.py
- inference.py
- keypoint_head.py
- loss.py
- roi_keypoint_feature_extractors.py
- roi_keypoint_predictors.py
- __init__.py
- inference.py
- loss.py
- mask_head.py
- roi_mask_feature_extractors.py
- roi_mask_predictors.py
- __init__.py
- roi_heads.py
- __init__.py
- inference.py
- loss.py
- retinanet.py
- __init__.py
- anchor_generator.py
- inference.py
- loss.py
- rpn.py
- utils.py
- __init__.py
- balanced_positive_negative_sampler.py
- box_coder.py
- make_layers.py
- matcher.py
- poolers.py
- registry.py
- utils.py
- __init__.py
- build.py
- lr_scheduler.py
- __init__.py
- bounding_box.py
- boxlist_ops.py
- image_list.py
- keypoint.py
- segmentation_mask.py
- __init__.py
- c2_model_loading.py
- checkpoint.py
- collect_env.py
- comm.py
- cv2_util.py
- env.py
- imports.py
- logger.py
- metric_logger.py
- miscellaneous.py
- model_serialization.py
- model_zoo.py
- README.md
- registry.py
- timer.py
- __init__.py
- env.py
- checkpoint.py
- test_backbones.py
- test_box_coder.py
- test_configs.py
- test_data_samplers.py
- test_detectors.py
- test_fbnet.py
- test_feature_extractors.py
- test_metric_logger.py
- test_nms.py
- test_predictors.py
- test_rpn_heads.py
- test_segmentation_mask.py
- utils.py
- convert_cityscapes_to_coco.py
- instances2dict_with_polygons.py
- test_net.py
- train_net.py
- .flake8
- .gitignore
- ABSTRACTIONS.md
- CODE_OF_CONDUCT.md
- CONTRIBUTING.md
- INSTALL.md
- LICENSE
- MODEL_ZOO.md
- README.md
- requirements.txt
- setup.py
- TROUBLESHOOTING.md
π Installation Guide
1. Get the code
git clone https://github.com/facebookresearch/maskrcnn-benchmark
Downloads the entire project code from GitHub to your computer.
cd maskrcnn-benchmark
Moves into the project folder you just downloaded.
2. Docker
Easy RecommendedPrerequisites
- Git Needed to download the project code from GitHub.
- Docker Desktop Needed to build and run containers. Install it and keep it running in the background.
docker build -f docker/Dockerfile -t maskrcnn-benchmark .
Builds a runnable image based on the Dockerfile.
docker run -p 8080:80 maskrcnn-benchmark
Runs the built image as an actual container.
Run docker compose ps to check the containers are Up. If the README mentions a port, open http://localhost:PORT in your browser.
3. Python
EasyPrerequisites
python -m torch.distributed.launch --nproc_per_node=$NGPUS /path_to_maskrcnn_benchmark/tools/train_net.py --config-file "path/to/config/file.yaml" MODEL.RPN.FPN_POST_NMS_TOP_N_TRAIN images_per_gpu x 1000
Runs the Python script (or module).
python -m torch.distributed.launch --nproc_per_node=$NGPUS /path_to_maskrcnn_benchmark/tools/train_net.py --config-file "path/to/config/file.yaml" MODEL.RPN.FPN_POST_NMS_TOP_N_TRAIN images_per_gpu x 1000 DTYPE "float16"
Runs the Python script (or module).
python -m torch.distributed.launch --nproc_per_node=$NGPUS /path_to_maskrcnn_benchmark/tools/test_net.py --config-file "configs/e2e_mask_rcnn_R_50_FPN_1x.yaml" TEST.IMS_PER_BATCH 16
Runs the Python script (or module).
If it runs without errors and prints output in the terminal, it worked.
Pulled directly from this repo's README.
// repository documentation
Was this content helpful?
(0 ratings)