
深度学习
threadroc
771811549
展开
专栏收录文章
- 默认排序
- 最新发布
- 最早发布
- 最多阅读
- 最少阅读
-
神经网络参考链接
AlexNet的Tensorflow实现(python):https://github.com/SidHard/tfAlexNet 卷积神经网络CNN经典模型整理Lenet,Alexnet,Googlenet,VGG,Deep Residual Learning:http://blog.csdn.net/xbinworld/article/details/45619685 CNN(卷积神经网络转载 2016-12-14 17:48:38 · 749 阅读 · 0 评论 -
安装windows tensorflow-gpu
1.用驱动精灵安装nvidia最新版本驱动 2.下载cuda8.0 https://developer.nvidia.com/cuda-downloads 3.下载cudnn,需要注册登录下载 https://developer.nvidia.com/cudnn 我win7系统下载的:cudnn-8.0-windows7-x64-v5.1 解压将bin-include-lib3个目录复制粘原创 2016-12-15 14:40:14 · 1281 阅读 · 0 评论 -
tiny-cnn配置
参考链接: http://blog.csdn.net/fengbingchun/article/details/50573841 http://blog.csdn.net/linshuhe1/article/details/51177487原创 2016-12-24 16:14:53 · 1628 阅读 · 0 评论 -
tensorflow的cross_entropy(loss)=nan问题
解决方案1: cross_entropy = -tf.reduce_sum(y_*tf.log(tf.clip_by_value(y_conv,1e-10,1.0))) 解决方案2:(推荐) cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv + 1e-10)) 原文参考:http://stackoverflow.com/qu转载 2017-01-01 18:33:41 · 6281 阅读 · 0 评论 -
tensorflow设置显存自适应和显存比例.
转自:http://blog.csdn.net/cq361106306/article/details/52950081 用惯了theano.再用tensoflow发现一运行显存就满载了,吓得我吃了一个苹果。 用天朝搜索引擎毛都搜不到,于是翻墙找了下问题的解决方法,原来有两种 1. 按比例 config = tf.ConfigProto() config.gpu_options.per转载 2017-02-03 20:02:50 · 1545 阅读 · 0 评论 -
tensorflow项目构建流程
转自:http://blog.csdn.net/hjimce/article/details/51899683 tensorflow项目构建流程 博客:http://blog.csdn.net/hjimce 微博:黄锦池-hjimce qq:1393852684 一、构建路线 个人感觉对于任何一个深度学习库,如mxnet、tensorflow、theano转载 2017-04-16 15:16:26 · 2473 阅读 · 0 评论 -
seq2seq
1.错误:Couldn't open CUDA library cupti64_80.dll 解决方案:添加环境变量path:C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v8.0\extras\CUPTI\libx64 2.hook报错的地方注释. AttributeError: module 'tensorflow.contrib.原创 2017-05-11 06:46:57 · 608 阅读 · 0 评论 -
gan资料收集
1.wgan https://github.com/martinarjovsky/WassersteinGAN https://github.com/igul222/improved_wgan_training 2.dcgan https://github.com/carpedm20/DCGAN-tensorflow转载 2017-05-26 15:14:46 · 389 阅读 · 0 评论 -
使用DCGAN-tensorflow-master出现错误
转自:http://bbs.csdn.net/topics/392087841 我的电脑是windows7系统,安装了anaconda,里面是python3.5。 按照DCGAN-tensorflow-master的readme 在命令行中,转换到工作目录下, 第一步输入了python download.py mnist 第二步输入main.py --dataset转载 2017-05-29 13:02:18 · 1680 阅读 · 1 评论