![](https://img-blog.csdnimg.cn/20201014180756780.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
tensorflow
文章平均质量分 69
昵称123333
这个作者很懒,什么都没留下…
展开
-
tensorflow function笔记: tf.nn.conv2d
tf.nn.conv2d(input, filter, strides, padding, use_cudnn_on_gpu=None, data_format=None, name=None)Argumentsinput shape: [batch, in_height, in_width, in_channels]filter shape: [filter_height, filter原创 2017-03-20 17:02:11 · 454 阅读 · 0 评论 -
tensorflow function笔记: dropout
tf.nn.dropout(x, keep_prob, noise_shape=None, seed=None, name=None)原创 2017-03-13 23:29:22 · 339 阅读 · 0 评论 -
tensorflow function笔记: tf.expand_dims and tf.squeeze
tf.expand_dims()Functiontf.expand_dims(input, axis=None, name=None, dim=None)Inserts a dimension of 1 into a tensor’s shape. 在第axis位置增加一个维度Given a tensor input, this operation inserts a dimension of 1原创 2017-03-31 11:22:03 · 4378 阅读 · 0 评论 -
tensorflow function笔记: tf.tile
tf.tileFunctiontf.tile(input, multiples, name=None)tile n. 瓷砖通过拼接一个给定的tensor构建一个新的tensor Constructs a tensor by tiling a given tensor.output tensor 的第i维有 input.dims(i) * multiples[i] 个元素 This operat原创 2017-03-31 11:33:00 · 6067 阅读 · 0 评论