py-faster-rcnn在caffe下运行make报错cudnnStatus_t status = condition；

最新推荐文章于 2022-06-07 01:22:16 发布

原创最新推荐文章于 2022-06-07 01:22:16 发布 · 298 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#caffe #深度学习

人工智能专栏收录该内容

7 篇文章

订阅专栏

本文解决了py-faster-rcnn在使用特定版本的caffe时出现的编译错误问题，主要错误涉及cudnn版本不兼容导致的函数参数数量不符等问题。通过替换相关cudnn文件到兼容版本，成功解决了编译错误。

项目场景：

ubuntu16.04
py-faster-rcnn在caffe下运行make报错cudnnStatus_t status = condition;

问题描述：

faster-rcnn在caffe下运行make：报错：

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/fast_rcnn_layers.hpp:13,
                 from src/caffe/layers/smooth_L1_loss_layer.cpp:8:
./include/caffe/util/cudnn.hpp: In function ‘const char* cudnnGetErrorString(cudnnStatus_t)’:
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_PREREQUISITE_MISSING’ not handled in switch [-Wswitch]
   switch (status) {
          ^
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_IN_PROGRESS’ not handled in switch [-Wswitch]
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_FP_OVERFLOW’ not handled in switch [-Wswitch]
./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:108:70: error: too few arguments to function ‘cudnnStatus_t cudnnSetConvolution2dDescriptor(cudnnConvolutionDescriptor_t, int, int, int, int, int, int, cudnnConvolutionMode_t, cudnnDataType_t)’
       pad_h, pad_w, stride_h, stride_w, 1, 1, CUDNN_CROSS_CORRELATION));
                                                                      ^
./include/caffe/util/cudnn.hpp:15:28: note: in definition of macro ‘CUDNN_CHECK’
     cudnnStatus_t status = condition; \
                            ^
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/fast_rcnn_layers.hpp:13,
                 from src/caffe/layers/smooth_L1_loss_layer.cpp:8:
/usr/local/cuda/include/cudnn.h:537:27: note: declared here
 cudnnStatus_t CUDNNWINAPI cudnnSetConvolution2dDescriptor( cudnnConvolutionDescriptor_t convDesc,
                           ^
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/fast_rcnn_layers.hpp:13,
                 from src/caffe/layers/smooth_L1_loss_layer.cpp:8:
./include/caffe/util/cudnn.hpp: In function ‘void caffe::cudnn::createPoolingDesc(cudnnPoolingStruct**, caffe::PoolingParameter_PoolMethod, cudnnPoolingMode_t*, int, int, int, int, int, int)’:
./include/caffe/util/cudnn.hpp:127:41: error: too few arguments to function ‘cudnnStatus_t cudnnSetPooling2dDescriptor(cudnnPoolingDescriptor_t, cudnnPoolingMode_t, cudnnNanPropagation_t, int, int, int, int, int, int)’
         pad_h, pad_w, stride_h, stride_w));
                                         ^
./include/caffe/util/cudnn.hpp:15:28: note: in definition of macro ‘CUDNN_CHECK’
     cudnnStatus_t status = condition; \
                            ^
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/fast_rcnn_layers.hpp:13,
                 from src/caffe/layers/smooth_L1_loss_layer.cpp:8:
/usr/local/cuda/include/cudnn.h:1031:27: note: declared here
 cudnnStatus_t CUDNNWINAPI cudnnSetPooling2dDescriptor(

原因分析：

cudnn的版本和caffe的版本有冲突：

解决方案：

解决办法：

把CAFFEROOT/src/caffe/util/，把下面命令行的目录改成自己的caffe和py-faster-rcnn目录

sudo cp -r /home/lijing/caffe/src/caffe/util/cudnn* /home/lijing/py-faster-rcnn/caffe-fast-rcnn/src/caffe/util/

CAFFEROOT/src/caffe/layers/，把下面命令行的目录改成自己的caffe和py-faster-rcnn目录

sudo cp -r /home/lijing/caffe/src/caffe/layers/cudnn* /home/lijing/py-faster-rcnn/caffe-fast-rcnn/src/caffe/layers/

CAFFEROOT/include/caffe/util/，把下面命令行的目录改成自己的caffe和py-faster-rcnn目录

sudo cp -r /home/lijing/caffe/include/caffe/util/cudnn* /home/lijing/py-faster-rcnn/caffe-fast-rcnn/include/caffe/util/

CAFFEROOT/include/caffe/layers/，把下面命令行的目录改成自己的caffe和py-faster-rcnn目录

sudo cp -r /home/lijing/caffe/include/caffe/layers/cudnn* /home/lijing/py-faster-rcnn/caffe-fast-rcnn/include/caffe/layers

这四个文件夹里面所有cudnn开头的文件用之前可以编译通过的caffe中的cudnn中的文件代替，就没问题啦。