本文首發於我的博客kezunlin.me/post/b90033…,歡迎閱讀!html
Install and Configure Caffe on ubuntu 16.04python
requirements:linux
默認的protobuf,2.6.1測試經過。ios
此處,使用最新的3.6.1 也能夠,編譯caffe須要加上
-std=c++11
c++
see install and configure cuda 9.2 with cudnn 7.1 on ubuntu 16.04git
tips: we need to recompile caffe with cudnn 7.1github
before we compile caffe, move caffe/python/caffe/selective_search_ijcv_with_python
folder outside caffe source folder, otherwise error occurs.ubuntu
see Part 1: compile protobuf-cpp on ubuntu 16.04vim
which protoc
/usr/local/bin/protoc複製代碼
protoc --version
libprotoc 3.6.1複製代碼
caffe使用static的libprotoc 3.6.1windows
see compile opencv on ubuntu 16.04
which opencv_version
/usr/local/bin/opencv_version複製代碼
opencv_version
3.3.0複製代碼
python --version
Python 2.7.12複製代碼
check numpy
version
import numpy
numpy.__version__
'1.15.1'複製代碼
import numpy
import inspect
inspect.getfile(numpy)
'/usr/local/lib/python2.7/dist-packages/numpy/__init__.pyc'
複製代碼
git clone https://github.com/BVLC/caffe.git
cd caffe複製代碼
update at 20180822.
if you change your local Makefile and git pull origin master
merge conflict, solution
git checkout HEAD Makefile
git pull origin master
複製代碼
mkdir build && cd build && cmake-gui ..複製代碼
cmake-gui options
USE_CUDNN ON
USE_OPENCV ON
Build_python ON
Build_python_layer ON複製代碼
BLAS atlas
CMAKE_CXX_FLGAS -std=c++11複製代碼
CMAKE_INSTALL_PREFIX /home/kezunlin/program/caffe/build/install複製代碼
使用
-std=c++11
configure output
Dependencies:
BLAS : Yes (Atlas)
Boost : Yes (ver. 1.66)
glog : Yes
gflags : Yes
protobuf : Yes (ver. 3.6.1)
lmdb : Yes (ver. 0.9.17)
LevelDB : Yes (ver. 1.18)
Snappy : Yes (ver. 1.1.3)
OpenCV : Yes (ver. 3.1.0)
CUDA : Yes (ver. 9.2)複製代碼
NVIDIA CUDA:
Target GPU(s) : Auto
GPU arch(s) : sm_61
cuDNN : Yes (ver. 7.1.4)複製代碼
Python:
Interpreter : /usr/bin/python2.7 (ver. 2.7.12)
Libraries : /usr/lib/x86_64-linux-gnu/libpython2.7.so (ver 2.7.12)
NumPy : /usr/lib/python2.7/dist-packages/numpy/core/include (ver 1.51.1)複製代碼
Documentaion:
Doxygen : /usr/bin/doxygen (1.8.11)
config_file : /home/kezunlin/program/caffe/.Doxyfile複製代碼
Install:
Install path : /home/kezunlin/program/caffe-wy/build/install複製代碼
Configuring done複製代碼
we can also use
python3.5
andnumpy 1.16.2
Python:
Interpreter : /usr/bin/python3 (ver. 3.5.2)
Libraries : /usr/lib/x86_64-linux-gnu/libpython3.5m.so (ver 3.5.2)
NumPy : /home/kezunlin/.local/lib/python3.5/site-packages/numpy/core/include (ver 1.16.2)複製代碼
use -std=c++11
, otherwise errors occur
make -j8
[ 1%] Running C++/Python protocol buffer compiler on /home/kezunlin/program/caffe-wy/src/caffe/proto/caffe.proto
Scanning dependencies of target caffeproto
[ 1%] Building CXX object src/caffe/CMakeFiles/caffeproto.dir/__/__/include/caffe/proto/caffe.pb.cc.o
In file included from /usr/include/c++/5/mutex:35:0,
from /usr/local/include/google/protobuf/stubs/mutex.h:33,
from /usr/local/include/google/protobuf/stubs/common.h:52,
from /home/kezunlin/program/caffe-wy/build/include/caffe/proto/caffe.pb.h:9,
from /home/kezunlin/program/caffe-wy/build/include/caffe/proto/caffe.pb.cc:4:
/usr/include/c++/5/bits/c++0x_warning.h:32:2: error: #error This file requires compiler and library support for the ISO C++ 2011 standard. This support must be enabled with the -std=c++11 or -std=gnu++11 compiler options.
#error This file requires compiler and library support \
複製代碼
vim /usr/local/cuda/include/host_config.h
# 將其中的第115行註釋掉:
#error-- unsupported GNU version! gcc versions later than 4.9 are not supported!
======>
//#error-- unsupported GNU version! gcc versions later than 4.9 are not supported!
複製代碼
Comment out the ifndef
// #ifndef GFLAGS_GFLAGS_H_
namespace gflags = google;
// #endif // GFLAGS_GFLAGS_H_
複製代碼
make clean
make -j8
make pycaffe複製代碼
output
[ 1%] Running C++/Python protocol buffer compiler on /home/kezunlin/program/caffe-wy/src/caffe/proto/caffe.proto
Scanning dependencies of target caffeproto
[ 1%] Building CXX object src/caffe/CMakeFiles/caffeproto.dir/__/__/include/caffe/proto/caffe.pb.cc.o
[ 1%] Linking CXX static library ../../lib/libcaffeproto.a
[ 1%] Built target caffeproto複製代碼
libcaffeproto.a
static library
make install複製代碼
ls build/install
bin include lib python share
複製代碼
will install to
build/install
folder
ls build/install/lib複製代碼
libcaffeproto.a libcaffe.so libcaffe.so.1.0.0
複製代碼
Target "caffe" has an INTERFACELINKLIBRARIES property which differs from its LINKINTERFACELIBRARIES properties.
fix ipython 6.1 version conflict
vim caffe/python/requirements.txt
ipython>=3.0.0
====>
ipython==5.4.1複製代碼
reinstall ipython
pip install -r requirements.txt複製代碼
cd caffe/python
python
>>>import caffe
複製代碼
sudo apt-get install graphviz
sudo pip install theano=0.9複製代碼
# for theano d3viz
sudo pip install pydot==1.1.0
sudo pip install pydot-ng
複製代碼
# other usefull tools
sudo pip install jupyter
sudo pip install seaborn複製代碼
we need to install graphviz, otherwise we get ERROR:"dot" not found in path
draw net
cd $CAFFE_HOME
./python/draw_net.py ./examples/mnist/lenet.prototxt ./examples/mnist/lenet.png
eog ./examples/mnist/lenet.png複製代碼
cd caffe
./examples/mnist/create_mnist.sh
./examples/mnist/train_lenet.sh 複製代碼
cat ./examples/mnist/train_lenet.sh 複製代碼
./build/tools/caffe train --solver=examples/mnist/lenet_solver.prototxt $@複製代碼
output results
I0912 15:57:28.812655 14094 solver.cpp:327] Iteration 10000, loss = 0.00272129
I0912 15:57:28.812675 14094 solver.cpp:347] Iteration 10000, Testing net (#0)
I0912 15:57:28.891481 14100 data_layer.cpp:73] Restarting data prefetching from start.
I0912 15:57:28.893678 14094 solver.cpp:414] Test net output #0: accuracy = 0.9904
I0912 15:57:28.893707 14094 solver.cpp:414] Test net output #1: loss = 0.0276084 (* 1 = 0.0276084 loss)
I0912 15:57:28.893714 14094 solver.cpp:332] Optimization Done.
I0912 15:57:28.893719 14094 caffe.cpp:250] Optimization Done.
複製代碼
tips, for
caffe
, errors because no imdb data.
I0417 13:28:17.764714 35030 layer_factory.hpp:77] Creating layer mnist
F0417 13:28:17.765067 35030 db_lmdb.hpp:15] Check failed: mdb_status == 0 (2 vs. 0) No such file or directory
--------------------- 複製代碼
./tools/upgrade_net_proto_text old.prototxt new.prototxt
./tools/upgrade_net_proto_binary old.caffemodel new.caffemodel複製代碼
./build/tools/caffe time --model='det/yolov3/yolov3.prototxt' --iterations=100 --gpu=0複製代碼
I0313 10:15:41.888208 12527 caffe.cpp:408] Average Forward pass: 49.7012 ms.
I0313 10:15:41.888213 12527 caffe.cpp:410] Average Backward pass: 84.946 ms.
I0313 10:15:41.888248 12527 caffe.cpp:412] Average Forward-Backward: 134.85 ms.
複製代碼
./build/tools/caffe time --model='det/autotrain/yolo3-autotrain-mbn-416-5c.prototxt' --iterations=100 --gpu=0複製代碼
I0313 10:19:27.283625 12894 caffe.cpp:408] Average Forward pass: 38.4823 ms.
I0313 10:19:27.283630 12894 caffe.cpp:410] Average Backward pass: 74.1656 ms.
I0313 10:19:27.283638 12894 caffe.cpp:412] Average Forward-Backward: 112.732 ms.
複製代碼
#include <caffe/caffe.hpp>
#ifdef USE_OPENCV
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#endif // USE_OPENCV
#include <algorithm>
#include <iosfwd>
#include <memory>
#include <string>
#include <utility>
#include <vector>
#ifdef USE_OPENCV
using namespace caffe; // NOLINT(build/namespaces)
using std::string;
/* Pair (label, confidence) representing a prediction. */
typedef std::pair<string, float> Prediction;
class Classifier {
public:
Classifier(const string& model_file,
const string& trained_file,
const string& mean_file,
const string& label_file);
std::vector<Prediction> Classify(const cv::Mat& img, int N = 5);
private:
void SetMean(const string& mean_file);
std::vector<float> Predict(const cv::Mat& img);
void WrapInputLayer(std::vector<cv::Mat>* input_channels);
void Preprocess(const cv::Mat& img,
std::vector<cv::Mat>* input_channels);
private:
shared_ptr<Net<float> > net_;
cv::Size input_geometry_;
int num_channels_;
cv::Mat mean_;
std::vector<string> labels_;
};
Classifier::Classifier(const string& model_file,
const string& trained_file,
const string& mean_file,
const string& label_file) {
#ifdef CPU_ONLY
Caffe::set_mode(Caffe::CPU);
#else
Caffe::set_mode(Caffe::GPU);
#endif
/* Load the network. */
net_.reset(new Net<float>(model_file, TEST));
net_->CopyTrainedLayersFrom(trained_file);
CHECK_EQ(net_->num_inputs(), 1) << "Network should have exactly one input.";
CHECK_EQ(net_->num_outputs(), 1) << "Network should have exactly one output.";
Blob<float>* input_layer = net_->input_blobs()[0];
num_channels_ = input_layer->channels();
CHECK(num_channels_ == 3 || num_channels_ == 1)
<< "Input layer should have 1 or 3 channels.";
input_geometry_ = cv::Size(input_layer->width(), input_layer->height());
/* Load the binaryproto mean file. */
SetMean(mean_file);
/* Load labels. */
std::ifstream labels(label_file.c_str());
CHECK(labels) << "Unable to open labels file " << label_file;
string line;
while (std::getline(labels, line))
labels_.push_back(string(line));
Blob<float>* output_layer = net_->output_blobs()[0];
CHECK_EQ(labels_.size(), output_layer->channels())
<< "Number of labels is different from the output layer dimension.";
}
static bool PairCompare(const std::pair<float, int>& lhs,
const std::pair<float, int>& rhs) {
return lhs.first > rhs.first;
}
/* Return the indices of the top N values of vector v. */
static std::vector<int> Argmax(const std::vector<float>& v, int N) {
std::vector<std::pair<float, int> > pairs;
for (size_t i = 0; i < v.size(); ++i)
pairs.push_back(std::make_pair(v[i], i));
std::partial_sort(pairs.begin(), pairs.begin() + N, pairs.end(), PairCompare);
std::vector<int> result;
for (int i = 0; i < N; ++i)
result.push_back(pairs[i].second);
return result;
}
/* Return the top N predictions. */
std::vector<Prediction> Classifier::Classify(const cv::Mat& img, int N) {
std::vector<float> output = Predict(img);
N = std::min<int>(labels_.size(), N);
std::vector<int> maxN = Argmax(output, N);
std::vector<Prediction> predictions;
for (int i = 0; i < N; ++i) {
int idx = maxN[i];
predictions.push_back(std::make_pair(labels_[idx], output[idx]));
}
return predictions;
}
/* Load the mean file in binaryproto format. */
void Classifier::SetMean(const string& mean_file) {
BlobProto blob_proto;
ReadProtoFromBinaryFileOrDie(mean_file.c_str(), &blob_proto);
/* Convert from BlobProto to Blob<float> */
Blob<float> mean_blob;
mean_blob.FromProto(blob_proto);
CHECK_EQ(mean_blob.channels(), num_channels_)
<< "Number of channels of mean file doesn't match input layer.";
/* The format of the mean file is planar 32-bit float BGR or grayscale. */
std::vector<cv::Mat> channels;
float* data = mean_blob.mutable_cpu_data();
for (int i = 0; i < num_channels_; ++i) {
/* Extract an individual channel. */
cv::Mat channel(mean_blob.height(), mean_blob.width(), CV_32FC1, data);
channels.push_back(channel);
data += mean_blob.height() * mean_blob.width();
}
/* Merge the separate channels into a single image. */
cv::Mat mean;
cv::merge(channels, mean);
/* Compute the global mean pixel value and create a mean image
* filled with this value. */
cv::Scalar channel_mean = cv::mean(mean);
mean_ = cv::Mat(input_geometry_, mean.type(), channel_mean);
}
std::vector<float> Classifier::Predict(const cv::Mat& img) {
Blob<float>* input_layer = net_->input_blobs()[0];
input_layer->Reshape(1, num_channels_,
input_geometry_.height, input_geometry_.width);
/* Forward dimension change to all layers. */
net_->Reshape();
std::vector<cv::Mat> input_channels;
WrapInputLayer(&input_channels);
Preprocess(img, &input_channels);
net_->Forward();
/* Copy the output layer to a std::vector */
Blob<float>* output_layer = net_->output_blobs()[0];
const float* begin = output_layer->cpu_data();
const float* end = begin + output_layer->channels();
return std::vector<float>(begin, end);
}
/* Wrap the input layer of the network in separate cv::Mat objects
* (one per channel). This way we save one memcpy operation and we
* don't need to rely on cudaMemcpy2D. The last preprocessing
* operation will write the separate channels directly to the input
* layer. */
void Classifier::WrapInputLayer(std::vector<cv::Mat>* input_channels) {
Blob<float>* input_layer = net_->input_blobs()[0];
int width = input_layer->width();
int height = input_layer->height();
float* input_data = input_layer->mutable_cpu_data();
for (int i = 0; i < input_layer->channels(); ++i) {
cv::Mat channel(height, width, CV_32FC1, input_data);
input_channels->push_back(channel);
input_data += width * height;
}
}
void Classifier::Preprocess(const cv::Mat& img,
std::vector<cv::Mat>* input_channels) {
/* Convert the input image to the input image format of the network. */
cv::Mat sample;
if (img.channels() == 3 && num_channels_ == 1)
cv::cvtColor(img, sample, cv::COLOR_BGR2GRAY);
else if (img.channels() == 4 && num_channels_ == 1)
cv::cvtColor(img, sample, cv::COLOR_BGRA2GRAY);
else if (img.channels() == 4 && num_channels_ == 3)
cv::cvtColor(img, sample, cv::COLOR_BGRA2BGR);
else if (img.channels() == 1 && num_channels_ == 3)
cv::cvtColor(img, sample, cv::COLOR_GRAY2BGR);
else
sample = img;
cv::Mat sample_resized;
if (sample.size() != input_geometry_)
cv::resize(sample, sample_resized, input_geometry_);
else
sample_resized = sample;
cv::Mat sample_float;
if (num_channels_ == 3)
sample_resized.convertTo(sample_float, CV_32FC3);
else
sample_resized.convertTo(sample_float, CV_32FC1);
cv::Mat sample_normalized;
cv::subtract(sample_float, mean_, sample_normalized);
/* This operation will write the separate BGR planes directly to the
* input layer of the network because it is wrapped by the cv::Mat
* objects in input_channels. */
cv::split(sample_normalized, *input_channels);
CHECK(reinterpret_cast<float*>(input_channels->at(0).data)
== net_->input_blobs()[0]->cpu_data())
<< "Input channels are not wrapping the input layer of the network.";
}
int main(int argc, char** argv) {
if (argc != 6) {
std::cerr << "Usage: " << argv[0]
<< " deploy.prototxt network.caffemodel"
<< " mean.binaryproto labels.txt img.jpg" << std::endl;
return 1;
}
::google::InitGoogleLogging(argv[0]);
string model_file = argv[1];
string trained_file = argv[2];
string mean_file = argv[3];
string label_file = argv[4];
Classifier classifier(model_file, trained_file, mean_file, label_file);
string file = argv[5];
std::cout << "---------- Prediction for "
<< file << " ----------" << std::endl;
cv::Mat img = cv::imread(file, -1);
CHECK(!img.empty()) << "Unable to decode image " << file;
std::vector<Prediction> predictions = classifier.Classify(img);
/* Print the top N predictions. */
for (size_t i = 0; i < predictions.size(); ++i) {
Prediction p = predictions[i];
std::cout << std::fixed << std::setprecision(4) << p.second << " - \""
<< p.first << "\"" << std::endl;
}
}
#else
int main(int argc, char** argv) {
LOG(FATAL) << "This example requires OpenCV; compile with USE_OPENCV.";
}
#endif // USE_OPENCV複製代碼
find_package(OpenCV REQUIRED)
set(Caffe_DIR "/home/kezunlin/program/caffe-wy/build/install/share/Caffe") # caffe-wy caffe
# for CaffeConfig.cmake/ caffe-config.cmake
find_package(Caffe)
# offical caffe : There is no Caffe_INCLUDE_DIRS and Caffe_DEFINITIONS
# refinedet caffe: OK.
add_definitions(${Caffe_DEFINITIONS})
MESSAGE( [Main] " Caffe_INCLUDE_DIRS = ${Caffe_INCLUDE_DIRS}")
MESSAGE( [Main] " Caffe_DEFINITIONS = ${Caffe_DEFINITIONS}")
MESSAGE( [Main] " Caffe_LIBRARIES = ${Caffe_LIBRARIES}") # caffe
MESSAGE( [Main] " Caffe_CPU_ONLY = ${Caffe_CPU_ONLY}")
MESSAGE( [Main] " Caffe_HAVE_CUDA = ${Caffe_HAVE_CUDA}")
MESSAGE( [Main] " Caffe_HAVE_CUDNN = ${Caffe_HAVE_CUDNN}")
include_directories(${Caffe_INCLUDE_DIRS})
target_link_libraries(demo
${OpenCV_LIBS}
${Caffe_LIBRARIES}
)複製代碼
ldd demo複製代碼
if error occurs:
libcaffe.so.1.0.0 => not found複製代碼
fix
vim .bashrc複製代碼
# for caffe
export LD_LIBRARY_PATH=/home/kezunlin/program/caffe-wy/build/install/lib:$LD_LIBRARY_PATH
複製代碼