cuda-convnet-master
cuda-convnet代码,可以在http://code.google.com/p/cuda-convnet/下载到。上传到这里为了方便不能上google的童鞋。 Additional features This document will only describe the small differences between cuda-convnet as hosted on Google Code and this version. Dropout Dropout is a relatively new regularization technique for neural networks. See the Improving neural networks by preventing co-adaptation of feature detectors and Improving Neural Networks with Dropout papers for details.
文件列表
cuda-convnet-master.zip
(预估有个67文件)
cuda-convnet-master
README.rst
2KB
options.py
17KB
convdata.py
7KB
layer.py
61KB
cmake
findMKL.cmake
4KB
findThreads.cmake
9KB
shownet.py
15KB
convnet.py
10KB
用户评论