Faster R-CNN 兼容不同版本的cudnn

faster rcnn 代码默认是使用的cudnn v4,但是为了体验不同版本的cudnn,我们编译faster rcnn的时候就会报错:
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(

为此提供2种解决方案:

(1)取自github @manipopopo

            cd caffe-fast-rcnn 

            git remote add caffe https://github.com/BVLC/caffe.git  

            git fetch caffe  

          git merge caffe/master Remove self_.attr("phase") = static_cast(this->phase_); from include/caffe/layers/python_layer.hpp after merging.

(2)手动修改文件,参考了卜居大神的博客 http://blog.csdn.net/kkk584520/article/details/51163564

方案1简单方便,但是当我们编译的是其他人修改过得源码,可能就会出错。

方案2 步骤如下:

1. 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

2. 用caffe源码中的这个文件替换掉faster rcnn 对应文件

            include/caffe/util/cudnn.hpp

3. 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

你可能感兴趣的:(目标识别)