Faster RCNN pytorch 复现

柔情只为你懂 2022-05-12 05:26 234阅读 0赞

本文参考的复现代码为[Faster RCNN with PyTorch][]。

1.Install the requirements

pip install pyyaml sympy h5py cython numpy scipy menpo

·install opencv3  
1.1 Update packages

sudo apt-get update
    sudo apt-get upgrade

1.2 Install OS libraries

Remove any previous installations of x264</h3>
    sudo apt-get remove x264 libx264-dev
     
    We will Install dependencies now
     
    sudo apt-get install build-essential checkinstall cmake pkg-config yasm
    sudo apt-get install git gfortran
    sudo apt-get install libjpeg8-dev libjasper-dev libpng12-dev
     
    # If you are using Ubuntu 14.04
    sudo apt-get install libtiff4-dev
    # If you are using Ubuntu 16.04
    sudo apt-get install libtiff5-dev
     
    sudo apt-get install libavcodec-dev libavformat-dev libswscale-dev libdc1394-22-dev
    sudo apt-get install libxine2-dev libv4l-dev
    sudo apt-get install libgstreamer0.10-dev libgstreamer-plugins-base0.10-dev
    sudo apt-get install qt5-default libgtk2.0-dev libtbb-dev
    sudo apt-get install libatlas-base-dev
    sudo apt-get install libfaac-dev libmp3lame-dev libtheora-dev
    sudo apt-get install libvorbis-dev libxvidcore-dev
    sudo apt-get install libopencore-amrnb-dev libopencore-amrwb-dev
    sudo apt-get install x264 v4l-utils
     
    # Optional dependencies
    sudo apt-get install libprotobuf-dev protobuf-compiler
    sudo apt-get install libgoogle-glog-dev libgflags-dev
    sudo apt-get install libgphoto2-dev libeigen3-dev libhdf5-dev doxygen

1.3 Download OpenCV and OpenCV\_contrib  
1.3.1 Download opencv from Github

git clone https://github.com/opencv/opencv.git
    cd opencv 
    git checkout 3.3.1 
    cd ..

1.3.2 Download opencv\_contrib from Github

git clone https://github.com/opencv/opencv_contrib.git
    cd opencv_contrib
    git checkout 3.3.1
    cd ..

1.4 Compile and install OpenCV with contrib modules  
1.4.1 Create a build directory

cd opencv
    mkdir build
    cd build

1.4.2 Run CMake

cmake -D CMAKE_BUILD_TYPE=RELEASE \
          -D CMAKE_INSTALL_PREFIX=/usr/local \
          -D INSTALL_C_EXAMPLES=ON \
          -D INSTALL_PYTHON_EXAMPLES=ON \
          -D WITH_TBB=ON \
          -D WITH_V4L=ON \
          -D WITH_QT=ON \
          -D WITH_OPENGL=ON \
          -D OPENCV_EXTRA_MODULES_PATH=../../opencv_contrib/modules \
          -D BUILD_EXAMPLES=ON ..

1.4.3 Compile and Install

# find out number of CPU cores in your machine
    nproc
    # substitute 4 by output of nproc
    make -j4
    sudo make install
    sudo sh -c 'echo "/usr/local/lib" >> /etc/ld.so.conf.d/opencv.conf'
    sudo ldconfig

2.Clone the Faster R-CNN repository

git clone https://github.com/longcw/faster_rcnn_pytorch.git

3.Build the Cython modules for nms and the roi\_pooling layer

cd faster_rcnn_pytorch/faster_rcnn
    ./make.sh

4.Download the trained model [VGGnet\_fast\_rcnn\_iter\_70000.h5][VGGnet_fast_rcnn_iter_70000.h5] and set the model path in [demo.py][]![在这里插入图片描述][70]

5.set image in the “demo” : 0.00545.jpg  
![在这里插入图片描述][70 1]

![在这里插入图片描述][70 2]

![在这里插入图片描述][70 3]

6.python [demo.py][]  
![在这里插入图片描述][70 4]

![在这里插入图片描述][70 5]

如有不当，请指教；如有疑问，欢迎留言交流～

[Faster RCNN with PyTorch]: https://github.com/longcw/faster_rcnn_pytorch
[VGGnet_fast_rcnn_iter_70000.h5]: https://drive.google.com/open?id=0B4pXCfnYmG1WOXdpYVFybWxiZFE
[demo.py]: http://demo.py
[70]: https://img-blog.csdn.net/20180919145515898?watermark/2/text/aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3p3X19jaGVu/font/5a6L5L2T/fontsize/400/fill/I0JBQkFCMA==/dissolve/70
[70 1]: /images/20220512/7e2bae902e4b45e4a670ad29a30a2b40.png
[70 2]: /images/20220512/c50678a794c94fb286514e2d4dc963ac.png
[70 3]: /images/20220512/04d41ba15aa941c2a4002ac26680bdff.png
[70 4]: /images/20220512/db3072974774421e8b498d35103385ad.png
[70 5]: /images/20220512/5637a1ad79dd4683a2f7492a2a38cdfb.png