caffe项目工程化封装FRCNN

各种坑!!想要做好,一定要自己一步步试,下载别人的总会出现各种问题.

步骤如下:(可以把这些文件打包在一个文件加下,分两个文件libs,include,一定要是自己的文件)

1 首先是配置caffe的VC++目录中的include和库文件。配置include lib dll都是坑，而且还分debug和release两个版本。添加输入项目需要注意，而且需要把编译好的caffe.lib等等一系列东西拷贝到当前项目下。也就是caffe bulid文件夹下面的东西，包括caffe.lib 、libcaffe.lib、还有很多dll.

这个是debug_include配置图

这个是debug_lib配置图

这个是release_include配置图

这个是release_lib配置图

同时也需要在，项目属性页的链接器输入中，填写相应的lib，其中debug和release是不同的。以下是需要填写的相应lib

//debug
opencv_calib3d2413d.lib
opencv_contrib2413d.lib
opencv_core2413d.lib
opencv_features2d2413d.lib
opencv_flann2413d.lib
opencv_gpu2413d.lib
opencv_highgui2413d.lib
opencv_imgproc2413d.lib
opencv_legacy2413d.lib
opencv_ml2413d.lib
opencv_objdetect2413d.lib
opencv_ts2413d.lib
opencv_video2413d.lib
caffe.lib
libcaffe.lib
cudart.lib
cublas.lib
curand.lib
gflagsd.lib
libglog.lib
libopenblas.dll.a
libprotobuf.lib
leveldb.lib
hdf5.lib
hdf5_hl.lib
Shlwapi.lib
//release
opencv_calib3d2410.lib
opencv_contrib2410.lib
opencv_core2410.lib
opencv_features2d2410.lib
opencv_flann2410.lib
opencv_gpu2410.lib
opencv_highgui2410.lib
opencv_imgproc2410.lib
opencv_legacy2410.lib
opencv_ml2410.lib
opencv_objdetect2410.lib
opencv_ts2410.lib
opencv_video2410.lib
caffe.lib
libcaffe.lib
cudart.lib
cublas.lib
curand.lib
gflags.lib
libglog.lib
libopenblas.dll.a
libprotobuf.lib
leveldb.lib
lmdb.lib
hdf5.lib
hdf5_hl.lib
Shlwapi.lib

3 直接编译后会出现的问题是F0519 14:54:12.494139 14504 layer_factory.hpp:77] Check failed: registry.count(t ype) == 1 (0 vs. 1) Unknown layer type: Input (known types: Input ),百度后发现是要加头文件！http://blog.csdn.net/fangjin_kl/article/details/50936952#0-tsina-1-63793-397232819ff9a47a7b7e80a40613cfe1

因此安装上面说的新建一个head.h

参考

 1 #include<caffe/common.hpp>
 2 #include<caffe/proto/caffe.pb.h>
 3 #include<caffe/layers/batch_norm_layer.hpp>
 4 #include<caffe/layers/bias_layer.hpp>
 5 #include <caffe/layers/concat_layer.hpp>
 6 #include <caffe/layers/conv_layer.hpp>
 7 #include <caffe/layers/dropout_layer.hpp>
 8 #include<caffe/layers/input_layer.hpp>
 9 #include <caffe/layers/inner_product_layer.hpp>
10 #include "caffe/layers/lrn_layer.hpp"
11 #include <caffe/layers/pooling_layer.hpp>
12 #include <caffe/layers/relu_layer.hpp>
13 #include "caffe/layers/softmax_layer.hpp"
14 #include<caffe/layers/scale_layer.hpp>
15 namespace caffe
16 {
17     extern INSTANTIATE_CLASS(BatchNormLayer);
18     extern INSTANTIATE_CLASS(BiasLayer);
19     extern INSTANTIATE_CLASS(InputLayer);
20     extern INSTANTIATE_CLASS(InnerProductLayer);
21     extern INSTANTIATE_CLASS(DropoutLayer);
22     extern INSTANTIATE_CLASS(ConvolutionLayer);
23     REGISTER_LAYER_CLASS(Convolution);
24     extern INSTANTIATE_CLASS(ReLULayer);
25     REGISTER_LAYER_CLASS(ReLU);
26     extern INSTANTIATE_CLASS(PoolingLayer);
27     REGISTER_LAYER_CLASS(Pooling);
28     extern INSTANTIATE_CLASS(LRNLayer);
29     REGISTER_LAYER_CLASS(LRN);
30     extern INSTANTIATE_CLASS(SoftmaxLayer);
31     REGISTER_LAYER_CLASS(Softmax);
32     extern INSTANTIATE_CLASS(ScaleLayer);
33     extern INSTANTIATE_CLASS(ConcatLayer);
34
35 }

同时需要把

#include <caffe/proto/caffe.pb.h>
#include "head.h"

这两个头文件放到.cpp中，不要放.h里。