目标检测代码Faster-RCNN_TF

(1)编译时报错：

/usr/local/lib/python2.7/dist-packages/tensorflow/include/tensorflow/core/platform/default/mutex.h:25:22: fatal error: nsync_cv.h: No such file or directory

（之前TFFRCNN-master改用python2.7版本时好像也出了这个问题）

解决办法：

sudo gedit /usr/local/lib/python2.7/dist-packages/tensorflow/include/tensorflow/core/platform/default/mutex.h

添加路径：

#include "/usr/local/lib/python2.7/dist-packages/tensorflow/include/external/nsync/public/nsync_cv.h"

#include "/usr/local/lib/python2.7/dist-packages/tensorflow/include/external/nsync/public/nsync_mu.h"

(2)跑demo

python ./tools/demo.py --model model/VGGnet_fast_rcnn_iter_70000.ckpt

报错：

tensorflow.python.framework.errors_impl.NotFoundError: /home/carsmart/users/yangxing/TFFRCNN-master/lib/roi_pooling_layer/roi_pooling.so: undefined symbol: _ZTIN10tensorflow8OpKernelE

（TFFRCNN-master改用python2.7版本时一样的问题）

解决办法：修改make.sh文件

TF_LIB=$(python -c 'import tensorflow as tf; print(tf.sysconfig.get_lib())')

g++ -std=c++11 -shared -o roi_pooling.so roi_pooling_op.cc -D_GLIBCXX_USE_CXX11_ABI=0 \

roi_pooling_op.cu.o -I $TF_INC -L $TF_LIB -ltensorflow_framework -D GOOGLE_CUDA=1 \

-fPIC $CXXFLAGS -lcudart -L $CUDA_PATH/lib64

报错：

ImportError: No module named yaml

解决办法：

sudo apt-get install python-yaml

(3)训练和测试模型

./experiments/scripts/faster_rcnn_end2end.sh gpu 1 VGG16 pascal_voc

报错：

test_net.py: error: argument --weights: expected one argument

这是因为tensorflow问题并没有在/output/faster_rcnn_end2end/voc_2007_trainval 中生成VGGnet_fast_rcnn_iter_70000.ckpt文件

解决办法：

修改： lib/fast_rcnn/train.py :

from tensorflow.core.protobuf import saver_pb2

self.saver = tf.train.Saver(max_to_keep=100,write_version=saver_pb2.SaverDef.V1)

报错：

grep: experiments/logs/faster_rcnn_end2end_VGG16_.txt.2018-01-04_13-10-24: No such file or directory

解决办法：

1. 在./experiment/下手动添加logs文件夹

2.手动调用训练好的模型去测试

CUDA_VISIBLE_DEVICES=" 1 " python ./tools/test_net.py --device gpu --device_id 0 --weights output/faster_rcnn_end2end/voc_2007_trainval/VGGnet_fast_rcnn_iter_70000.ckpt --imdb voc_2007_test --cfg experiments/cfgs/faster_rcnn_end2end.yml --network VGGnet_test