ubuntu16.04 cuda9 faster-rcnn配置
2018-03-05 19:36
543 查看
python faster-rcnn github
报错
src/caffe/layers/cudnn_relu_layer.cu(43): error: argument of type "cudnnActivationMode_t" is incompatible with parameter of type "cudnnActivationDescriptor_t"
detected during instantiation of "void caffe::CuDNNReLULayer<Dtype>::Backward_gpu(const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &, const std::vector<__nv_bool, std::allocator<__nv_bool>> &, const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &) [with Dtype=float]"
(52): here
解决办法:
1。安装软件依赖
sudo pip install cython
sudo pip install easydict
2。替换最新cudnn相关文件
1).将/py-faster-rcnn/caffe-fast-rcnn/include/caffe/util/cudnn.hpp 换成最新版的caffe里的cudnn的实现,即相应的cudnn.hpp.
2).将/py-faster-rcnn/caffe-fast-rcnn/src/caffe/layer里的,所有以cudnn开头的文件,例如cudnn_lrn_layer.cu,cudnn_pooling_layer.cpp,cudnn_sigmoid_layer.cu。
都替换成最新版的caffe里的相应的同名文件。
3。重新编译
cd caffe-fast-rcnn #进入caffe目录,可能你的是cd caffe-master
sudo make clean #清除原编译
sudo make -j4 # make -j4或者make -j8 这根据你自己电脑来定
sudo make pycaffe
报错
src/caffe/layers/cudnn_relu_layer.cu(43): error: argument of type "cudnnActivationMode_t" is incompatible with parameter of type "cudnnActivationDescriptor_t"
detected during instantiation of "void caffe::CuDNNReLULayer<Dtype>::Backward_gpu(const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &, const std::vector<__nv_bool, std::allocator<__nv_bool>> &, const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &) [with Dtype=float]"
(52): here
解决办法:
1。安装软件依赖
sudo pip install cython
sudo pip install easydict
2。替换最新cudnn相关文件
1).将/py-faster-rcnn/caffe-fast-rcnn/include/caffe/util/cudnn.hpp 换成最新版的caffe里的cudnn的实现,即相应的cudnn.hpp.
2).将/py-faster-rcnn/caffe-fast-rcnn/src/caffe/layer里的,所有以cudnn开头的文件,例如cudnn_lrn_layer.cu,cudnn_pooling_layer.cpp,cudnn_sigmoid_layer.cu。
都替换成最新版的caffe里的相应的同名文件。
3。重新编译
cd caffe-fast-rcnn #进入caffe目录,可能你的是cd caffe-master
sudo make clean #清除原编译
sudo make -j4 # make -j4或者make -j8 这根据你自己电脑来定
sudo make pycaffe
相关文章推荐
- Ubuntu16.04+cuda8.0+cudnnV5.1配置faster-rcnn的方法
- Ubuntu16.04+CUDA8.0+OpenCV3.1+python+caffe+faster-rcnn环境配置
- Ubuntu16.04+GTX1070+cuda8.0+cudnn5.1配置faster-rcnn的方法
- Ubuntu16.04+cuda8.0+cudnn5.1配置faster-rcnn的方法以及训练自己的数据出现的问题
- ubuntu16.04 cuda8.0 cudnn6.0 faster-rcnn配置
- Ubuntu16.04+GT720M + Cuda8.0+py-faster-rcnn(caffe)
- AWS-G2-Ubuntu16.04下安装cuda,caffe和py-faster-rcnn
- Ubuntu 14.04+cuda 7.0+cudnn 7.0+caffe安装配置+faster-rcnn安装
- ubuntu16.04配置py-faster-rcnn
- Ubuntu16.04 cuda8.0+cudnn5.1 opencv3.3 caffe-faster-rcnn 服务器配置
- Ubuntu 14.04 64位机上不带CUDA支持的Caffe配置编译操作过程+faster-rcnn
- Ubuntu16.04 cuda8.0+cudnn5.1 opencv3.3 caffe-faster-rcnn
- Ubuntu16.04+Cuda8.0+1080ti+caffe+免OpenCV3.2.0+faster-rCNN教程
- faster-rcnn在ubuntu16.04环境下的超级详细的配置
- ubuntu16.04配置py-faster-rcnn(CPU版)
- Ubuntu 16.04+CUDA8+CUDNN v5配置faster rcnn
- ubuntu16.04配置py-faster-rcnn
- Ubuntu16.04+CUDA8.0+caffe配置
- Ubuntu16.04 +cuda8.0+cudnn+opencv3.1.0+tensorflow+torch配置明细
- py-faster-rcnn配置运行faster_rcnn_end2end—VGG_CNN_M_1024(Ubuntu14.04)