安装fast-rcnn过程中出现编译错误

Question

src/caffe/layers/cudnn_conv_layer.cu(142): error: argument of type "double *" is incompatible with parameter of type "size_t" detected during instantiation of "void caffe::CuDNNConvolutionLayer::Backward_gpu(const std::vector *, std::allocator *>> &, const std::vector<__nv_bool, std::allocator<__nv_bool>> &, const std::vector *, std::allocator *>> &) [with Dtype=double]" (159): here
src/caffe/layers/cudnn_conv_layer.cu(142): error: too few arguments in function call detected during instantiation of "void caffe::CuDNNConvolutionLayer::Backward_gpu(const std::vector *, std::allocator *>> &, const std::vector<__nv_bool, std::allocator<__nv_bool>> &, const std::vector *, std::allocator *>> &) [with Dtype=double]" (159): here
20 errors detected in the compilation of "/tmp/tmpxft_00001284_00000000-16_cudnn_conv_layer.compute_50.cpp1.ii". make: * [.build_release/cuda/src/caffe/layers/cudnn_conv_layer.o] Error 1 make: * Waiting for unfinished jobs....

Answer 1

尝试按照 Rob 网站上的 these 说明安装快速 rcnn。

您还可以按照 these 说明（假设您使用的是 EC2 或 Ubuntu 14.04）检查问题是否与您的 cudnn 配置有关。

如果问题仍然存在，如果您能分享导致此错误的步骤以及您正在构建的机器 OS，将会有所帮助。

Answer 2

最近遇到了这个麻烦。编译fast-rcnn, but doesn't occur for py-faster-rcnn and enter link description here. After I read the caffe installation guide which is presented on web: Caffe Installation的项目时出现，我觉得可能是cuDNN的版本（前者是v3，后者是v4）导致的。我的cuDNN安装版本是v4.0.7，后两个项目运行良好

安装fast-rcnn过程中出现编译错误

Compilation error in the process of installing fast-rcnn

caffe