maskrcnn-benchmark
This is the official code of High-Resolution Representations for Object Detection. We extend the high-resolution representation (HRNet) [1] by augmenting the high-resolution representation by aggregating the (upsampled) representations from all the parallel convolutions, leading to stronger representations. We build a multi-level representation from the high resolution and apply it to the Faster R-CNN, Mask R-CNN and Cascade R-CNN framework. This proposed approach achieves superior results to existing single-model networks on COCO object detection. The code is based on maskrcnn-benchmark
HRNetV2 ImageNet pretrained models are now available! Codes and pretrained models are in HRNets for Image Classification
All models are trained on COCO train2017 set and evaluated on COCO val2017 set. Detailed settings or configurations are in configs/hrnet
.
Note: Models are trained with the newly released code and the results have minor differences with that in the paper.
Current results will be updated soon and more models and results are comming.
All models are trained on COCO train2017 set and evaluated on COCO val2017 set. Detailed settings or configurations are in configs/hrnet
.
Backbone | lr sched | mAP | model |
---|---|---|---|
HRNetV2-W18 | 1x | 36.0 | FasterR-CNN-HR18-1x.pth |
HRNetV2-W18 | 2x | 38.4 | FasterR-CNN-HR18-2x.pth |
HRNetV2-W32 | 1x | 39.6 | FasterR-CNN-HR32-1x.pth |
HRNetV2-W32 | 2x | 40.9 | FasterR-CNN-HR32-2x.pth |
HRNetV2-W40 | 1x | 40.4 | FasterR-CNN-HR40-1x.pth |
HRNetV2-W40 | 2x | 41.4 | FasterR-CNN-HR40-2x.pth |
HRNetV2-W48 | 1x | 41.3 | FasterR-CNN-HR48-1x.pth |
HRNetV2-W48 | 2x | 41.8 | FasterR-CNN-HR48-2x.pth |
Backbone | lr sched | mAP | model |
---|---|---|---|
HRNetV2-W32 | 1x | 39.6 | FasterR-CNN-HR32-1x.pth |
HRNetV2-W32 | 2x | 40.9 | FasterR-CNN-HR32-2x.pth |
HRNetV2-W32 | 3x | 41.4 | FasterR-CNN-HR32-3x.pth |
HRNetV2-W32 | 4x | 41.6 | FasterR-CNN-HR32-4x.pth |
Our HRNets will obtain larger gain when training with more iterations.
Install PyTorch 1.0 following the official instructions
Install pycocotools
git clone https://github.com/cocodataset/cocoapi.git && cd cocoapi/PythonAPI && python setup.py build_ext install && cd ../../
Install HRNet-MaskRCNN-Benchmark
git clone https://github.com/HRNet/HRNet-MaskRCNN-Benchmark.gitcd HRNet-MaskRCNN-Benchmark python setup.py build develop pip install -r requirements.txt
for more details, see INSTALL.md
cd HRNet-MaskRCNN-Benchmark# Download pretrained models into this foldermkdir hrnetv2_pretrained
Please specify the configuration file in configs
(learning rate should be adjusted when the number of GPUs is changed).
python -m torch.distributed.launch --nproc_per_node <GPU NUMS> tools/train_net.py --config-file <CONFIG FILE># example (4 gpus)python -m torch.distributed.launch --nproc_per_node 4 tools/train_net.py --config-file configs/hrnet/e2e_faster_rcnn_hrnet_w18_1x.yaml
python -m torch.distributed.launch --nproc_per_node <GPU NUMS> tools/test_net.py --config-file <CONFIG-FILE> MODEL.WEIGHT <WEIGHT>#example (4gpus)python -m torch.distributed.launch --nproc_per_node 4 tools/test_net.py --config-file configs/hrnet/e2e_faster_rcnn_hrnet_w18_1x.yaml MODEL.WEIGHT FasterR-CNN-HR18-1x.pth
NOTE: If you meet some problems, you may find a solution in issues of official maskrcnn-benchmarkor submit a new issue in our repo.
Object detection(based on mmdetection)
If you find this work or code is helpful in your research, please cite:
@inproceedings{SunXLW19, title={Deep High-Resolution Representation Learning for Human Pose Estimation}, author={Ke Sun and Bin Xiao and Dong Liu and Jingdong Wang}, booktitle={CVPR}, year={2019} } @article{WangSCJDZLMTWLX19, title={Deep High-Resolution Representation Learning for Visual Recognition}, author={Jingdong Wang and Ke Sun and Tianheng Cheng and Borui Jiang and Chaorui Deng and Yang Zhao and Dong Liu and Yadong Mu and Mingkui Tan and Xinggang Wang and Wenyu Liu and Bin Xiao}, journal = {CoRR}, volume = {abs/1908.07919}, year={2019} }
[1] Deep High-Resolution Representation Learning for Human Pose Estimation. Ke Sun, Bin Xiao, Dong Liu, and Jingdong Wang. CVPR 2019. download
[2] Cascade R-CNN: Delving into High Quality Object Detection. Zhaowei Cai, and Nuno Vasconcetos. CVPR 2018.
还没有评论,说两句吧!
热门资源
Keras-ResNeXt
Keras ResNeXt Implementation of ResNeXt models...
seetafaceJNI
项目介绍 基于中科院seetaface2进行封装的JAVA...
spark-corenlp
This package wraps Stanford CoreNLP annotators ...
capsnet-with-caps...
CapsNet with capsule-wise convolution Project ...
inferno-boilerplate
This is a very basic boilerplate example for pe...
智能在线
400-630-6780
聆听.建议反馈
E-mail: support@tusaishared.com