fast rcnn cudnn 5.0
2017.01.08 15:47
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
댓글 0
번호 | 제목 | 글쓴이 | 날짜 | 조회 수 |
---|---|---|---|---|
274 | faster rcnn resnet 101 | WHRIA | 2018.09.09 | 175 |
273 | usb 3.1 + DP | WHRIA | 2020.01.07 | 172 |
272 | concat network [3] | WHRIA | 2020.08.27 | 171 |
271 | pytorch optimize | WHRIA | 2020.08.01 | 170 |
270 | resnest50 caffe | WHRIA | 2020.06.21 | 168 |
269 | pytorch pretrained | WHRIA | 2020.10.28 | 168 |
268 | CORS | WHRIA | 2021.01.22 | 168 |
267 | 역시 개원해서는 돈 버는 재미밖에 없다. | WHRIA | 2016.06.17 | 164 |
266 | pROC package [3] | WHRIA | 2019.05.11 | 161 |
» | fast rcnn cudnn 5.0 | WHRIA | 2017.01.08 | 160 |
264 | Transformer | WHRIA | 2020.10.09 | 160 |
263 | yolo custom | WHRIA | 2019.07.25 | 159 |
262 | SAS controller SAS 9212-4i | WHRIA | 2019.12.08 | 159 |
261 | file lock | WHRIA | 2020.09.22 | 159 |
260 | startup , 미국 | WHRIA | 2020.07.30 | 156 |