%global _empty_manifest_terminate_build 0 Name: python-chainer-mask-rcnn Version: 0.5.24 Release: 1 Summary: Chainer Implementation of Mask R-CNN. License: MIT URL: http://github.com/wkentaro/chainer-mask-rcnn Source0: https://mirrors.aliyun.com/pypi/web/packages/60/f7/a49f7625cc190657118eaab1f34d79db1bde42c8bd7d06c38737b649e21c/chainer-mask-rcnn-0.5.24.tar.gz BuildArch: noarch %description # chainer-mask-rcnn [![PyPI version](https://badge.fury.io/py/chainer-mask-rcnn.svg)](https://badge.fury.io/py/chainer-mask-rcnn) [![Python Versions](https://img.shields.io/pypi/pyversions/chainer-mask-rcnn.svg)](https://pypi.org/project/chainer-mask-rcnn) [![GitHub Actions](https://github.com/wkentaro/chainer-mask-rcnn/workflows/CI/badge.svg)](https://github.com/wkentaro/chainer-mask-rcnn/actions) Chainer Implementation of [Mask R-CNN](https://arxiv.org/abs/1703.06870). ## Features - [x] ResNet50, ResNet101 backbone. - [x] [VOC and COCO training examples](https://github.com/wkentaro/chainer-mask-rcnn/blob/main/examples). - [x] **[Reproduced result of original work (ResNet50, COCO)](https://github.com/wkentaro/chainer-mask-rcnn/blob/main/#coco-results)**. - [x] Weight copy from pretrained model at [facebookresearch/Detectron](https://github.com/facebookresearch/Detectron). - [x] Training with batch size >= 2. - [ ] Support FPN backbones. - [ ] Keypoint detection.

*Fig 1. Mask R-CNN, ResNet50, 8GPU, Ours, COCO 31.4 mAP@50:95* ## COCO Results | Model | Implementation | N gpu training | mAP@50:95 | Log | |-------|----------------|----------------|-----------|-----| | Mask R-CNN, ResNet50 | [Ours](https://github.com/wkentaro/chainer-mask-rcnn/blob/main/.?raw=true) | 8 | 31.5 - 31.8 | [Log](https://drive.google.com/open?id=1WOEtVnxqYdHl35pAyIcp-H0HtTjI-l3V) | | Mask R-CNN, ResNet50 | [Detectron](https://github.com/facebookresearch/Detectron) | 8 | 31.4 (30.8 after copied) | [Log](https://drive.google.com/open?id=1xQBox3uMv2FoyXXpsC9ASNZ-92NgAbcT) | | FCIS, ResNet50 | [FCIS](https://github.com/msracver/FCIS) | 8 | 27.1 | - | ## Inference ```bash # you can use your trained model ./demo.py logs/ --img # COCO Example: Mask R-CNN, ResNet50, 31.4 mAP@50:95 cd examples/coco LOG_DIR=logs/20180730_081433 mkdir -p $LOG_DIR pip install gdown gdown https://drive.google.com/uc?id=1XC-Mx4HX0YBIy0Fbp59EjJFOF7a3XK0R -O $LOG_DIR/snapshot_model.npz gdown https://drive.google.com/uc?id=1fXHanL2pBakbkv83wn69QhI6nM6KjrzL -O $LOG_DIR/params.yaml ./demo.py $LOG_DIR # copy weight from caffe2 to chainer cd examples/coco ./convert_caffe2_to_chainer.py # or download from https://drive.google.com/open?id=1WOEtVnxqYdHl35pAyIcp-H0HtTjI-l3V ./demo.py logs/R-50-C4_x1_caffe2_to_chainer --img https://raw.githubusercontent.com/facebookresearch/Detectron/master/demo/33823288584_1d21cf0a26_k.jpg ./demo.py logs/R-50-C4_x1_caffe2_to_chainer --img https://raw.githubusercontent.com/facebookresearch/Detectron/master/demo/17790319373_bd19b24cfc_k.jpg ```

*Fig 2. Mask R-CNN, ResNet50, 8GPU, Copied from Detectron, COCO 31.4 mAP@50:95* ## Installation & Training ### Single GPU Training ```bash # Install Chainer Mask R-CNN. pip install opencv-python pip install . # Run training! cd examples/coco && ./train.py --gpu 0 ``` ### Multi GPU Training ```bash # Install OpenMPI wget https://www.open-mpi.org/software/ompi/v3.0/downloads/openmpi-3.0.0.tar.gz tar zxvf openmpi-3.0.0.tar.gz cd openmpi-3.0.0 ./configure --with-cuda make -j4 sudo make install sudo ldconfig # Install NCCL # dpkg -i nccl-repo-ubuntu1404-2.1.4-ga-cuda8.0_1-1_amd64.deb dpkg -i nccl-repo-ubuntu1604-2.1.15-ga-cuda9.1_1-1_amd64.deb sudo apt update sudo apt install libnccl2 libnccl-dev # Install ChainerMN pip install chainermn # Finally, install Chainer Mask R-CNN. pip install opencv-python pip install . # Run training! cd examples/coco && mpirun -n 4 ./train.py --multi-node ``` ## Testing ```bash pip install flake8 pytest flake8 . pytest -v tests ``` %package -n python3-chainer-mask-rcnn Summary: Chainer Implementation of Mask R-CNN. Provides: python-chainer-mask-rcnn BuildRequires: python3-devel BuildRequires: python3-setuptools BuildRequires: python3-pip %description -n python3-chainer-mask-rcnn # chainer-mask-rcnn [![PyPI version](https://badge.fury.io/py/chainer-mask-rcnn.svg)](https://badge.fury.io/py/chainer-mask-rcnn) [![Python Versions](https://img.shields.io/pypi/pyversions/chainer-mask-rcnn.svg)](https://pypi.org/project/chainer-mask-rcnn) [![GitHub Actions](https://github.com/wkentaro/chainer-mask-rcnn/workflows/CI/badge.svg)](https://github.com/wkentaro/chainer-mask-rcnn/actions) Chainer Implementation of [Mask R-CNN](https://arxiv.org/abs/1703.06870). ## Features - [x] ResNet50, ResNet101 backbone. - [x] [VOC and COCO training examples](https://github.com/wkentaro/chainer-mask-rcnn/blob/main/examples). - [x] **[Reproduced result of original work (ResNet50, COCO)](https://github.com/wkentaro/chainer-mask-rcnn/blob/main/#coco-results)**. - [x] Weight copy from pretrained model at [facebookresearch/Detectron](https://github.com/facebookresearch/Detectron). - [x] Training with batch size >= 2. - [ ] Support FPN backbones. - [ ] Keypoint detection.

*Fig 2. Mask R-CNN, ResNet50, 8GPU, Copied from Detectron, COCO 31.4 mAP@50:95* ## Installation & Training ### Single GPU Training ```bash # Install Chainer Mask R-CNN. pip install opencv-python pip install . # Run training! cd examples/coco && ./train.py --gpu 0 ``` ### Multi GPU Training ```bash # Install OpenMPI wget https://www.open-mpi.org/software/ompi/v3.0/downloads/openmpi-3.0.0.tar.gz tar zxvf openmpi-3.0.0.tar.gz cd openmpi-3.0.0 ./configure --with-cuda make -j4 sudo make install sudo ldconfig # Install NCCL # dpkg -i nccl-repo-ubuntu1404-2.1.4-ga-cuda8.0_1-1_amd64.deb dpkg -i nccl-repo-ubuntu1604-2.1.15-ga-cuda9.1_1-1_amd64.deb sudo apt update sudo apt install libnccl2 libnccl-dev # Install ChainerMN pip install chainermn # Finally, install Chainer Mask R-CNN. pip install opencv-python pip install . # Run training! cd examples/coco && mpirun -n 4 ./train.py --multi-node ``` ## Testing ```bash pip install flake8 pytest flake8 . pytest -v tests ``` %package help Summary: Development documents and examples for chainer-mask-rcnn Provides: python3-chainer-mask-rcnn-doc %description help # chainer-mask-rcnn [![PyPI version](https://badge.fury.io/py/chainer-mask-rcnn.svg)](https://badge.fury.io/py/chainer-mask-rcnn) [![Python Versions](https://img.shields.io/pypi/pyversions/chainer-mask-rcnn.svg)](https://pypi.org/project/chainer-mask-rcnn) [![GitHub Actions](https://github.com/wkentaro/chainer-mask-rcnn/workflows/CI/badge.svg)](https://github.com/wkentaro/chainer-mask-rcnn/actions) Chainer Implementation of [Mask R-CNN](https://arxiv.org/abs/1703.06870). ## Features - [x] ResNet50, ResNet101 backbone. - [x] [VOC and COCO training examples](https://github.com/wkentaro/chainer-mask-rcnn/blob/main/examples). - [x] **[Reproduced result of original work (ResNet50, COCO)](https://github.com/wkentaro/chainer-mask-rcnn/blob/main/#coco-results)**. - [x] Weight copy from pretrained model at [facebookresearch/Detectron](https://github.com/facebookresearch/Detectron). - [x] Training with batch size >= 2. - [ ] Support FPN backbones. - [ ] Keypoint detection.

*Fig 2. Mask R-CNN, ResNet50, 8GPU, Copied from Detectron, COCO 31.4 mAP@50:95* ## Installation & Training ### Single GPU Training ```bash # Install Chainer Mask R-CNN. pip install opencv-python pip install . # Run training! cd examples/coco && ./train.py --gpu 0 ``` ### Multi GPU Training ```bash # Install OpenMPI wget https://www.open-mpi.org/software/ompi/v3.0/downloads/openmpi-3.0.0.tar.gz tar zxvf openmpi-3.0.0.tar.gz cd openmpi-3.0.0 ./configure --with-cuda make -j4 sudo make install sudo ldconfig # Install NCCL # dpkg -i nccl-repo-ubuntu1404-2.1.4-ga-cuda8.0_1-1_amd64.deb dpkg -i nccl-repo-ubuntu1604-2.1.15-ga-cuda9.1_1-1_amd64.deb sudo apt update sudo apt install libnccl2 libnccl-dev # Install ChainerMN pip install chainermn # Finally, install Chainer Mask R-CNN. pip install opencv-python pip install . # Run training! cd examples/coco && mpirun -n 4 ./train.py --multi-node ``` ## Testing ```bash pip install flake8 pytest flake8 . pytest -v tests ``` %prep %autosetup -n chainer-mask-rcnn-0.5.24 %build %py3_build %install %py3_install install -d -m755 %{buildroot}/%{_pkgdocdir} if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi pushd %{buildroot} if [ -d usr/lib ]; then find usr/lib -type f -printf "\"/%h/%f\"\n" >> filelist.lst fi if [ -d usr/lib64 ]; then find usr/lib64 -type f -printf "\"/%h/%f\"\n" >> filelist.lst fi if [ -d usr/bin ]; then find usr/bin -type f -printf "\"/%h/%f\"\n" >> filelist.lst fi if [ -d usr/sbin ]; then find usr/sbin -type f -printf "\"/%h/%f\"\n" >> filelist.lst fi touch doclist.lst if [ -d usr/share/man ]; then find usr/share/man -type f -printf "\"/%h/%f.gz\"\n" >> doclist.lst fi popd mv %{buildroot}/filelist.lst . mv %{buildroot}/doclist.lst . %files -n python3-chainer-mask-rcnn -f filelist.lst %dir %{python3_sitelib}/* %files help -f doclist.lst %{_docdir}/* %changelog * Tue Jun 20 2023 Python_Bot - 0.5.24-1 - Package Spec generated