Caffe 运行平台支持DSSD模型

Posted 2022-12-12 楚兴

DSSD源码：https://github.com/chengyangfu/caffe/tree/dssd

在cuda9环境下编译，首先把Makefile.config里面的USE_CUDNN := 1开关打开，编译报如下的错：

make: *** [.build_release/src/caffe/layers/multibox_loss_layer.o] Error 1
In file included from ./include/caffe/util/device_alternate.hpp:40:0,
                 from ./include/caffe/common.hpp:19,
                 from ./include/caffe/blob.hpp:8,
                 from ./include/caffe/caffe.hpp:7,
                 from src/caffe/parallel.cpp:12:
./include/caffe/util/cudnn.hpp: In function 'void caffe::cudnn::setConvolutionDesc(cudnnConvolutionStruct**, cudnnTensorDescriptor_t, cudnnFilterDescriptor_t, int, int, int, int)':
./include/caffe/util/cudnn.hpp:112:3: error: too few arguments to function 'cudnnStatus_t cudnnSetConvolution2dDescriptor(cudnnConvolutionDescriptor_t, int, int, int, int, int, int, cudnnConvolutionMode_t, cudnnDataType_t)'
   CUDNN_CHECK(cudnnSetConvolution2dDescriptor(*conv,
   ^
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 ./include/caffe/blob.hpp:8,
                 from ./include/caffe/caffe.hpp:7,
                 from src/caffe/parallel.cpp:12:
/usr/local/cuda/include/cudnn.h:537:27: note: declared here
 cudnnStatus_t CUDNNWINAPI cudnnSetConvolution2dDescriptor( cudnnConvolutionDescriptor_t convDesc,
                           ^

原因：上述DSSD的代码是基于老版本的caffe开发，老版本的caffe不支持新版本的cudnn，从而报错。

老版本的caffe代码如下：

template <typename Dtype>
inline void setConvolutionDesc(cudnnConvolutionDescriptor_t* conv,
    cudnnTensorDescriptor_t bottom, cudnnFilterDescriptor_t filter,
    int pad_h, int pad_w, int stride_h, int stride_w) 
  CUDNN_CHECK(cudnnSetConvolution2dDescriptor(*conv,
      pad_h, pad_w, stride_h, stride_w, 1, 1, CUDNN_CROSS_CORRELATION));

新版本的caffe代码如下：

//定义宏CUDNN_VERSION_MIN，从而支持高版本CUDNN。
template <typename Dtype>
inline void setConvolutionDesc(cudnnConvolutionDescriptor_t* conv,
    cudnnTensorDescriptor_t bottom, cudnnFilterDescriptor_t filter,
    int pad_h, int pad_w, int stride_h, int stride_w) 
#if CUDNN_VERSION_MIN(6, 0, 0)
  CUDNN_CHECK(cudnnSetConvolution2dDescriptor(*conv,
      pad_h, pad_w, stride_h, stride_w, 1, 1, CUDNN_CROSS_CORRELATION,
      dataType<Dtype>::type));
#else
    CUDNN_CHECK(cudnnSetConvolution2dDescriptor(*conv,
      pad_h, pad_w, stride_h, stride_w, 1, 1, CUDNN_CROSS_CORRELATION));
#endif

所以为了让现有运行平台支持DSSD模型，后面的解决方案是：

1. 把dssd中新增加的layer添加到现有运行平台的caffe依赖中，即把xxx_layer.hpp加到/include/caffe/layers。
2. 重新编译libcaffe.so.1.0.0
3. 把新.so文件替换原有的.so文件
4. 把新的include目录替换老的include目录（可以通过make distribute生成）