參考鏈接：https://blog.csdn.net/linolzhang/article/details/70306003
1.資源鏈接
代碼下載鏈接：https://github.com/CharlesShang/TFFRCNN
訓練好的網絡下載鏈接：
在 TFFRCNN-master 下新建文件夾 model，存放要下載入的 net（參考 Github 下載地址），推薦下載：
2.VGG16 - TFFRCNN (0.689 mAP on VOC07)：https://drive.google.com/file/d/0B_xFdh9onPagX0JWRlR0cTZ5OGc/view
3.VGG16 - TFFRCNN (0.748 mAP on VOC07)：https://drive.google.com/file/d/0B_xFdh9onPagVmt5VHlCU25vUEE/view
5.Resnet50 - TFFRCNN (0.712 mAP on VOC07)：https://drive.google.com/file/d/0B_xFdh9onPagbXk1b0FIeDRJaU0/view
2.Requirements: software
-
Requirements for Tensorflow (see: Tensorflow)
-
Python packages you might not have:
cython,python-opencv,easydict(recommend to install: Anaconda）
3.Requirements: hardware
- For training the end-to-end version of Faster R-CNN with VGG16, 3G of GPU memory is sufficient (using CUDNN)
4.Installation (sufficient for the demo)
1.Clone the Faster R-CNN repository
git clone https://github.com/CharlesShang/TFFRCNN.git
2.Build the Cython modules
cd TFFRCNN/lib
make # compile cython and roi_pooling_op, you may need to modify make.sh for your platform
我在編譯過程中遇到了一些錯誤需要修改lib/make.sh文件(修改如下圖紅色部分), 我的文件內容如下：
----- Begin ------
#!/usr/bin/env bash
TF_INC=$(python -c 'import tensorflow as tf; print(tf.sysconfig.get_include())')
echo $TF_INC
TF_LIB=$(python -c 'import tensorflow as tf; print(tf.sysconfig.get_lib())')
echo $TF_LIB
CUDA_PATH=/usr/local/cuda/
cd roi_pooling_layer
/usr/local/cuda-9.0/bin/nvcc -std=c++11 -c -o roi_pooling_op.cu.o roi_pooling_op_gpu.cu.cc \
-I $TF_INC -D GOOGLE_CUDA=1 -x cu -Xcompiler -fPIC -arch=sm_52
## if you install tf using already-built binary, or gcc version 4.x, uncomment the two lines below
#g++ -std=c++11 -shared -D_GLIBCXX_USE_CXX11_ABI=0 -o roi_pooling.so roi_pooling_op.cc \
# roi_pooling_op.cu.o -I $TF_INC -fPIC -lcudart -L $CUDA_PATH/lib64
# for gcc5-built tf
#g++ -std=c++11 -shared -D_GLIBCXX_USE_CXX11_ABI=1 -o roi_pooling.so roi_pooling_op.cc \
g++ -std=c++11 -shared -D_GLIBCXX_USE_CXX11_ABI=0 -o roi_pooling.so roi_pooling_op.cc \
roi_pooling_op.cu.o -I $TF_INC -fPIC -lcudart -L $CUDA_PATH/lib64 -L/usr/local/lib/python2.7/dist-packages/tensorflow -ltensorflow_framework \
-L/usr/local/cuda-9.0/targets/x86_64-linux/lib/ -L$TF_LIB
cd ..
# add building psroi_pooling layer
cd psroi_pooling_layer
/usr/local/cuda-9.0/bin/nvcc -std=c++11 -c -o psroi_pooling_op.cu.o psroi_pooling_op_gpu.cu.cc \
-I $TF_INC -D GOOGLE_CUDA=1 -x cu -Xcompiler -fPIC -arch=sm_52
g++ -std=c++11 -shared -D_GLIBCXX_USE_CXX11_ABI=0 -o psroi_pooling.so psroi_pooling_op.cc \
psroi_pooling_op.cu.o -I $TF_INC -fPIC -lcudart -L $CUDA_PATH/lib64i -L/usr/local/lib/python2.7/dist-packages/tensorflow -ltensorflow_framework \
-L/usr/local/cuda-9.0/targets/x86_64-linux/lib/ -L$TF_LIB
## if you install tf using already-built binary, or gcc version 4.x, uncomment the two lines below
#g++ -std=c++11 -shared -D_GLIBCXX_USE_CXX11_ABI=0 -o psroi_pooling.so psroi_pooling_op.cc \
# psroi_pooling_op.cu.o -I $TF_INC -fPIC -lcudart -L $CUDA_PATH/lib64
cd ..
----- End -----