Parsing-R-CNN
Parsing R-CNN for Instance-Level Human Analysis
File Explorer
Download Latest Version (.zip)- e2e_parsing_rcnn_R-50-FPN_1x_ms.yaml
- e2e_parsing_rcnn_R-50-FPN_3x_ms.yaml
- e2e_parsing_rcnn_R-50-FPN_s1x_ms.yaml
- e2e_parsing_rcnn_R-50-FPN_1x_ms.yaml
- e2e_parsing_rcnn_R-50-FPN_3x_ms.yaml
- README.md
- output.png
- parsing_rcnn.png
- __init__.py
- hrnet.py
- mobilenet_v1.py
- mobilenet_v2.py
- mobilenet_v3.py
- resnet.py
- resnext.py
- utils.py
- vovnet.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
- ml_nms.cu
- nms.cu
- PoolPointsInterp_cuda.cu
- ROIAlign_cuda.cu
- ROIPool_cuda.cu
- SigmoidFocalLoss_cuda.cu
- vision.h
- deform_conv.h
- deform_pool.h
- ml_nms.h
- nms.h
- PoolPointsInterp.h
- ROIAlign.h
- ROIPool.h
- SigmoidFocalLoss.h
- vision.cpp
- __init__.py
- deform_conv_func.py
- deform_conv_module.py
- deform_pool_func.py
- deform_pool_module.py
- __init__.py
- adjust_smooth_l1_loss.py
- affine.py
- batch_norm.py
- bilinear_interpolation2d.py
- boxes.py
- context_block.py
- conv2d_samepadding.py
- conv2d_ws.py
- cython_bbox.c
- cython_bbox.pyx
- cython_nms.c
- cython_nms.pyx
- dropblock.py
- iou_loss.py
- l2_loss.py
- l2norm.py
- label_smoothing.py
- lovasz_hinge_loss.py
- misc.py
- mixture_batchnorm.py
- nms.py
- nonlocal2d.py
- pool_points_interp.py
- scale.py
- setup_rcnn.py
- setup_ssd.py
- sigmoid_focal_loss.py
- smooth_l1_loss.py
- squeeze_excitation.py
- __init__.py
- __init__.py
- config.py
- test.py
- test_engine.py
- __init__.py
- dataset.py
- dataset_catalog.py
- evaluation.py
- transform.py
- __init__.py
- HRNet.py
- MobileNet_v1.py
- MobileNet_v2.py
- MobileNet_v3.py
- ResNet.py
- ResNeXt.py
- VoVNet.py
- __init__.py
- convfc_heads.py
- mlp_heads.py
- __init__.py
- cascade_rcnn.py
- inference.py
- loss.py
- outputs.py
- __init__.py
- convfc_heads.py
- mlp_heads.py
- __init__.py
- fast_rcnn.py
- inference.py
- loss.py
- outputs.py
- __init__.py
- FPN.py
- HRFPN.py
- __init__.py
- convx_heads.py
- gce_heads.py
- __init__.py
- inference.py
- keypoint_rcnn.py
- loss.py
- outputs.py
- __init__.py
- convx_heads.py
- __init__.py
- inference.py
- loss.py
- mask_rcnn.py
- outputs.py
- __init__.py
- convx_heads.py
- gce_heads.py
- __init__.py
- inference.py
- loss.py
- outputs.py
- parsing_rcnn.py
- __init__.py
- anchor_generator.py
- inference.py
- loss.py
- rpn.py
- __init__.py
- convx_heads.py
- gce_heads.py
- inference.py
- loss.py
- outputs.py
- uv_rcnn.py
- model_builder.py
- registry.py
- __init__.py
- deform_pool.py
- roi_align.py
- roi_pool.py
- __init__.py
- balanced_positive_negative_sampler.py
- box_coder.py
- matcher.py
- misc.py
- poolers.py
- __init__.py
- _init_paths.py
- test_net.py
- train_net.py
- __init__.py
- coco.py
- concat_dataset.py
- densepose_cocoeval.py
- densepose_methods.py
- parsing_eval.py
- __init__.py
- distributed.py
- grouped_batch_sampler.py
- iteration_based_batch_sampler.py
- range_sampler.py
- repeat_factor.py
- __init__.py
- bounding_box.py
- boxlist_ops.py
- densepose_uv.py
- image_list.py
- keypoint.py
- parsing.py
- segmentation_mask.py
- __init__.py
- transforms.py
- __init__.py
- collate_batch.py
- dataset_catalog.py
- __init__.py
- checkpointer.py
- collections.py
- colormap.py
- comm.py
- image.py
- logger.py
- lr_scheduler.py
- measure.py
- misc.py
- net.py
- optimizer.py
- registry.py
- subprocess.py
- timer.py
- vis.py
- README.md
- INSTALL.md
- LICENSE
- make.sh
- README.md
- requirements.txt
# Installation Guide
1. Get the code
git clone https://github.com/soeaver/Parsing-R-CNN
Downloads the entire project code from GitHub to your computer.
cd Parsing-R-CNN
Moves into the project folder you just downloaded.
2. Python
Easy RecommendedPrerequisites
python -m torch.distributed.launch --nproc_per_node=8 tools/train_net.py --cfg cfgs/CIHP/e2e_rp_rcnn_R-50-FPN_3x_ms.yaml
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)