tf.squeeze

来源：https://tensorflow.google.cn/api_docs/python/tf/squeeze

tf.squeeze(
    input,
    axis=None,
    name=None,
    squeeze_dims=None
)

Removes dimensions of size 1 from the shape of a tensor. (deprecated arguments) 

从Tensor的shape中去除size大小为1的维度们。。可以全部去除，也可以指定axis

举例：

# 't' is a tensor of shape [1, 2, 1, 3, 1, 1]
tf.shape(tf.squeeze(t))  # [2, 3]

# 't' is a tensor of shape [1, 2, 1, 3, 1, 1]
tf.shape(tf.squeeze(t, [2, 4]))  # [1, 2, 3, 1]

Args:

• input: A Tensor. The input to squeeze.
• axis: An optional list of ints. Defaults to []. If specified, only squeezes the dimensions listed. The dimension index starts at 0. It is an error to squeeze a dimension that is not 1. Must be in the range [-rank(input), rank(input)).
• name: A name for the operation (optional).
• squeeze_dims: Deprecated keyword argument that is now axis.