
卷积神经网络
牛奶蜜糖
这个作者很懒,什么都没留下…
展开
-
【DeepLearning-Note】Implementation of Convolutiona Netural Network
Basic Knowledge1 INPUT[32*32*3]*filter[3*3*3]=feature map[(32-3+1)*(32-3+1)]=feature map[30*30]卷积操作是点乘相加,INPUT[width*height*depth/channel] filter[width_*height_*depth/channel] ...原创 2018-04-02 14:43:38 · 347 阅读 · 0 评论 -
【DeepLearning-Note】转置卷积理解
参考链接 添加output_shapes的原因https://blog.youkuaiyun.com/mao_xiao_feng/article/details/71713358 padding的不确定性:https://blog.youkuaiyun.com/wuguangbin1230/article/details/79218593原创 2018-04-19 15:12:24 · 279 阅读 · 0 评论