确保安装库的版本
protobuf==2.6.1
sudo pip install protobuf==2.6.1
numpy==1.110
sudo pip install -U numpy==1.11.0
### Installation (sufficient for the demo)
1. Clone the Faster R-CNN repository
```Shell
# Make sure to clone with --recursive
git clone --recursive https://github.com/rbgirshick/py-faster-rcnn.git
```
2. We'll call the directory that you cloned Faster R-CNN into `FRCN_ROOT`
*Ignore notes 1 and 2 if you followed step 1 above.*
**Note 1:** If you didn't clone Faster R-CNN with the `--recursive` flag, then you'll need to manually clone the `caffe-fast-rcnn` submodule:
```Shell
git submodule update --init --recursive
```
**Note 2:** The `caffe-fast-rcnn` submodule needs to be on the `faster-rcnn` branch (or equivalent detached state). This will happen automatically *if you followed step 1 instructions*.
3. Build the Cython modules
```Shell
cd $FRCN_ROOT/lib
make
```
4. Build Caffe and pycaffe
```Shell
cd $FRCN_ROOT/caffe-fast-rcnn
# Now follow the Caffe installation instructions here:
# http://caffe.berkeleyvision.org/installation.html
# If you're experienced with Caffe and have all of the requirements installed
# and your Makefile.config in place, then simply do:
make -j8 && make pycaffe
```
或者用cmake-gui进行编译。
cmake-gui
make -j8 && make pycaffe
5. Download pre-computed Faster R-CNN detectors
```Shell
cd $FRCN_ROOT
./data/scripts/fetch_faster_rcnn_models.sh
```
This will populate the `$FRCN_ROOT/data` folder with `faster_rcnn_models`. See `data/README.md` for details.
These models were trained on VOC 2007 trainval.
6.run demo
python ./tools/demo.py
7.install py-faster-rcnn libs
cd py-faster-rcnn
sudo python ./lib/setup.py install
cd lib
cp ./build/lib.linux-x86_64-2.7/nms/* ./nms/
cp ./build/lib.linux-x86_64-2.7/pycocotools/* ./pycocotools/
cp ./build/lib.linux-x86_64-2.7/utils/* ./utils/
训练数据集
### Beyond the demo: installation for training and testing models
1. Download the training, validation, test data and VOCdevkit
```Shell
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCdevkit_08-Jun-2007.tar
```
2. Extract all of these tars into one directory named `VOCdevkit`
```Shell
tar xvf VOCtrainval_06-Nov-2007.tar
tar xvf VOCtest_06-Nov-2007.tar
tar xvf VOCdevkit_08-Jun-2007.tar
```
3. It should have this basic structure
```Shell
$VOCdevkit/ # development kit
$VOCdevkit/VOCcode/ # VOC utility code
$VOCdevkit/VOC2007 # image sets, annotations, etc.
# ... and several other directories ...
```
### Download pre-trained ImageNet models
Pre-trained ImageNet models can be downloaded for the three networks described in the paper: ZF and VGG16.
```Shell
cd $FRCN_ROOT
./data/scripts/fetch_imagenet_models.sh
```
VGG16 comes from the [Caffe Model Zoo](https://github.com/BVLC/caffe/wiki/Model-Zoo), but is provided here for your convenience.
ZF was trained at MSRA.
### Usage
To train and test a Faster R-CNN detector using the **approximate joint training** method, use `experiments/scripts/faster_rcnn_end2end.sh`.
Output is written underneath `$FRCN_ROOT/output`.
```Shell
cd $FRCN_ROOT
./experiments/scripts/faster_rcnn_end2end.sh [GPU_ID] [NET] [--set ...]
# GPU_ID is the GPU you want to train on
# NET in {ZF, VGG_CNN_M_1024, VGG16} is the network arch to use
# --set ... allows you to specify fast_rcnn.config options, e.g.
# --set EXP_DIR seed_rng1701 RNG_SEED 1701
```
```
for example:
./experiments/scripts/faster_rcnn_end2end.sh 0 VGG16 pascal_voc
编译遇到问题：
a)问题：In file included from ./include/caffe/util/cudnn.hpp:5:0,
from ./include/caffe/util/device_alternate.hpp:40,
from ./include/caffe/common.hpp:19,
from src/caffe/data_reader.cpp:6:
/usr/local/cuda/include/cudnn.h:799:27: note: declared here
cudnnStatus_t CUDNNWINAPI cudnnSetPooling2dDescriptor(
解决方法：
faster rcnn 代码默认是使用的cudnn v4, 但是为了体验最新的v5, 或者使用GTX1080 ,我们编译faster rcnn的时候就会报错：
手动修改文件，参考了卜居大神的博客 http://blog.csdn.net/kkk584520/article/details/51163564
步骤如下：
用最新caffe源码的以下文件替换掉faster rcnn 的对应文件
include/caffe/layers/cudnn_relu_layer.hpp, src/caffe/layers/cudnn_relu_layer.cpp, src/caffe/layers/cudnn_relu_layer.cu
include/caffe/layers/cudnn_sigmoid_layer.hpp, src/caffe/layers/cudnn_sigmoid_layer.cpp, src/caffe/layers/cudnn_sigmoid_layer.cu
include/caffe/layers/cudnn_tanh_layer.hpp, src/caffe/layers/cudnn_tanh_layer.cpp, src/caffe/layers/cudnn_tanh_layer.cu
用caffe源码中的这个文件替换掉faster rcnn 对应文件
include/caffe/util/cudnn.hpp
将 faster rcnn 中的 src/caffe/layers/cudnn_conv_layer.cu 文件中的所有
cudnnConvolutionBackwardData_v3 函数名替换为 cudnnConvolutionBackwardData
cudnnConvolutionBackwardFilter_v3函数名替换为 cudnnConvolutionBackwardFilter
b)问题：./include/caffe/util/cudnn.hpp:5:19: fatal error: cudnn.h: 没有那个文件或目录
解决方法：在Makefile.config中添加#include<cudnn.h>
c)问题：ImportError:No module named yaml解决方案
解决方法：sudo apt-get install python-yaml
d)编译caffe-fast-rcnn使用protobuf 2.6.1版本
解决方法：下载protobuf 源码https://github.com/google/protobuf/releases/download/v2.6.1/protobuf-2.6.1.tar.gz
cd protobuf-**目录
假如 你希望编译成功后输出的目录 为 /home/work /protobuf/ 则输入如下两条命令：
./configure --prefix=/home/work/protobuf/
make && make install
编译成功后将export PATH= /home/work /protobuf/bin:$PATH加入到环境变量中
最后输入 protoc --version命令，如显示protobuf-**则安装成功
e):TypeError numpy.float64 object cannot be interpreted as an index
在运行py-faster-rcnn的时候碰到了这个问题，结果把numpy的版本由1.12.0降为1.11.0问题得以解决。
sudo pip install -U numpy==1.11.0
f):AttributeError: 'module' object has no attribute 'text_format'
解决方法：sudo pip install protobuf==2.6.0
或：在文件./lib/fast_rcnn/train.py增加一行：import google.protobuf.text_format
g):ImportError: numpy.core.multiarray failed to import
没有运行文件./lib/setup.py
解决方法：编译py-faster-rcnn/lib/setup.py，并将编译好的nms,pycocotools,utils内的文件替换与lib文件夹下对应的文件
cd py-faster-rcnn
sudo python ./lib/setup.py install
cd lib
cp ./build/lib.linux-x86_64-2.7/nms/* ./nms/
cp ./build/lib.linux-x86_64-2.7/pycocotools/* ./pycocotools/
cp ./build/lib.linux-x86_64-2.7/utils/* ./utils/
protobuf==2.6.1
sudo pip install protobuf==2.6.1
numpy==1.110
sudo pip install -U numpy==1.11.0
### Installation (sufficient for the demo)
1. Clone the Faster R-CNN repository
```Shell
# Make sure to clone with --recursive
git clone --recursive https://github.com/rbgirshick/py-faster-rcnn.git
```
2. We'll call the directory that you cloned Faster R-CNN into `FRCN_ROOT`
*Ignore notes 1 and 2 if you followed step 1 above.*
**Note 1:** If you didn't clone Faster R-CNN with the `--recursive` flag, then you'll need to manually clone the `caffe-fast-rcnn` submodule:
```Shell
git submodule update --init --recursive
```
**Note 2:** The `caffe-fast-rcnn` submodule needs to be on the `faster-rcnn` branch (or equivalent detached state). This will happen automatically *if you followed step 1 instructions*.
3. Build the Cython modules
```Shell
cd $FRCN_ROOT/lib
make
```
4. Build Caffe and pycaffe
```Shell
cd $FRCN_ROOT/caffe-fast-rcnn
# Now follow the Caffe installation instructions here:
# http://caffe.berkeleyvision.org/installation.html
# If you're experienced with Caffe and have all of the requirements installed
# and your Makefile.config in place, then simply do:
make -j8 && make pycaffe
```
或者用cmake-gui进行编译。
cmake-gui
make -j8 && make pycaffe
5. Download pre-computed Faster R-CNN detectors
```Shell
cd $FRCN_ROOT
./data/scripts/fetch_faster_rcnn_models.sh
```
This will populate the `$FRCN_ROOT/data` folder with `faster_rcnn_models`. See `data/README.md` for details.
These models were trained on VOC 2007 trainval.
6.run demo
python ./tools/demo.py
7.install py-faster-rcnn libs
cd py-faster-rcnn
sudo python ./lib/setup.py install
cd lib
cp ./build/lib.linux-x86_64-2.7/nms/* ./nms/
cp ./build/lib.linux-x86_64-2.7/pycocotools/* ./pycocotools/
cp ./build/lib.linux-x86_64-2.7/utils/* ./utils/
训练数据集
### Beyond the demo: installation for training and testing models
1. Download the training, validation, test data and VOCdevkit
```Shell
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCdevkit_08-Jun-2007.tar
```
2. Extract all of these tars into one directory named `VOCdevkit`
```Shell
tar xvf VOCtrainval_06-Nov-2007.tar
tar xvf VOCtest_06-Nov-2007.tar
tar xvf VOCdevkit_08-Jun-2007.tar
```
3. It should have this basic structure
```Shell
$VOCdevkit/ # development kit
$VOCdevkit/VOCcode/ # VOC utility code
$VOCdevkit/VOC2007 # image sets, annotations, etc.
# ... and several other directories ...
```
### Download pre-trained ImageNet models
Pre-trained ImageNet models can be downloaded for the three networks described in the paper: ZF and VGG16.
```Shell
cd $FRCN_ROOT
./data/scripts/fetch_imagenet_models.sh
```
VGG16 comes from the [Caffe Model Zoo](https://github.com/BVLC/caffe/wiki/Model-Zoo), but is provided here for your convenience.
ZF was trained at MSRA.
### Usage
To train and test a Faster R-CNN detector using the **approximate joint training** method, use `experiments/scripts/faster_rcnn_end2end.sh`.
Output is written underneath `$FRCN_ROOT/output`.
```Shell
cd $FRCN_ROOT
./experiments/scripts/faster_rcnn_end2end.sh [GPU_ID] [NET] [--set ...]
# GPU_ID is the GPU you want to train on
# NET in {ZF, VGG_CNN_M_1024, VGG16} is the network arch to use
# --set ... allows you to specify fast_rcnn.config options, e.g.
# --set EXP_DIR seed_rng1701 RNG_SEED 1701
```
```
for example:
./experiments/scripts/faster_rcnn_end2end.sh 0 VGG16 pascal_voc
编译遇到问题：
a)问题：In file included from ./include/caffe/util/cudnn.hpp:5:0,
from ./include/caffe/util/device_alternate.hpp:40,
from ./include/caffe/common.hpp:19,
from src/caffe/data_reader.cpp:6:
/usr/local/cuda/include/cudnn.h:799:27: note: declared here
cudnnStatus_t CUDNNWINAPI cudnnSetPooling2dDescriptor(
解决方法：
faster rcnn 代码默认是使用的cudnn v4, 但是为了体验最新的v5, 或者使用GTX1080 ,我们编译faster rcnn的时候就会报错：
手动修改文件，参考了卜居大神的博客 http://blog.csdn.net/kkk584520/article/details/51163564
步骤如下：
用最新caffe源码的以下文件替换掉faster rcnn 的对应文件
include/caffe/layers/cudnn_relu_layer.hpp, src/caffe/layers/cudnn_relu_layer.cpp, src/caffe/layers/cudnn_relu_layer.cu
include/caffe/layers/cudnn_sigmoid_layer.hpp, src/caffe/layers/cudnn_sigmoid_layer.cpp, src/caffe/layers/cudnn_sigmoid_layer.cu
include/caffe/layers/cudnn_tanh_layer.hpp, src/caffe/layers/cudnn_tanh_layer.cpp, src/caffe/layers/cudnn_tanh_layer.cu
用caffe源码中的这个文件替换掉faster rcnn 对应文件
include/caffe/util/cudnn.hpp
将 faster rcnn 中的 src/caffe/layers/cudnn_conv_layer.cu 文件中的所有
cudnnConvolutionBackwardData_v3 函数名替换为 cudnnConvolutionBackwardData
cudnnConvolutionBackwardFilter_v3函数名替换为 cudnnConvolutionBackwardFilter
b)问题：./include/caffe/util/cudnn.hpp:5:19: fatal error: cudnn.h: 没有那个文件或目录
解决方法：在Makefile.config中添加#include<cudnn.h>
c)问题：ImportError:No module named yaml解决方案
解决方法：sudo apt-get install python-yaml
d)编译caffe-fast-rcnn使用protobuf 2.6.1版本
解决方法：下载protobuf 源码https://github.com/google/protobuf/releases/download/v2.6.1/protobuf-2.6.1.tar.gz
cd protobuf-**目录
假如 你希望编译成功后输出的目录 为 /home/work /protobuf/ 则输入如下两条命令：
./configure --prefix=/home/work/protobuf/
make && make install
编译成功后将export PATH= /home/work /protobuf/bin:$PATH加入到环境变量中
最后输入 protoc --version命令，如显示protobuf-**则安装成功
e):TypeError numpy.float64 object cannot be interpreted as an index
在运行py-faster-rcnn的时候碰到了这个问题，结果把numpy的版本由1.12.0降为1.11.0问题得以解决。
sudo pip install -U numpy==1.11.0
f):AttributeError: 'module' object has no attribute 'text_format'
解决方法：sudo pip install protobuf==2.6.0
或：在文件./lib/fast_rcnn/train.py增加一行：import google.protobuf.text_format
g):ImportError: numpy.core.multiarray failed to import
没有运行文件./lib/setup.py
解决方法：编译py-faster-rcnn/lib/setup.py，并将编译好的nms,pycocotools,utils内的文件替换与lib文件夹下对应的文件
cd py-faster-rcnn
sudo python ./lib/setup.py install
cd lib
cp ./build/lib.linux-x86_64-2.7/nms/* ./nms/
cp ./build/lib.linux-x86_64-2.7/pycocotools/* ./pycocotools/
cp ./build/lib.linux-x86_64-2.7/utils/* ./utils/