轉載：https://blog.csdn.net/jasonzzj/article/details/60811035
TensorFlow中，想要維度增加一維，可以使用tf.expand_dims(input, dim, name=None)函數。當然，我們常用tf.reshape(input, shape=[])也可以達到相同效果，但是有些時候在構建圖的過程中，placeholder沒有被feed具體的值，這時就會包下面的錯誤：TypeError: Expected binary or unicode string, got 1
在這種情況下，我們就可以考慮使用expand_dims來將維度加1。比如我自己代碼中遇到的情況，在對圖像維度降到二維做特定操作后，要還原成四維[batch, height, width, channels]，前后各增加一維。如果用reshape，則因為上述原因報錯
one_img2 = tf.reshape(one_img, shape=[1, one_img.get_shape()[0].value, one_img.get_shape()[1].value, 1])
用下面的方法可以實現：
one_img = tf.expand_dims(one_img, 0) one_img = tf.expand_dims(one_img, -1) #-1表示最后一維
在最后，給出官方的例子和說明
# 't' is a tensor of shape [2] shape(expand_dims(t, 0)) ==> [1, 2] shape(expand_dims(t, 1)) ==> [2, 1] shape(expand_dims(t, -1)) ==> [2, 1] # 't2' is a tensor of shape [2, 3, 5] shape(expand_dims(t2, 0)) ==> [1, 2, 3, 5] shape(expand_dims(t2, 2)) ==> [2, 3, 1, 5] shape(expand_dims(t2, 3)) ==> [2, 3, 5, 1]
Args:
input: A Tensor.
dim: A Tensor. Must be one of the following types: int32, int64. 0-D (scalar). Specifies the dimension index at which to expand the shape of input.
name: A name for the operation (optional).
Returns:
A Tensor. Has the same type as input. Contains the same data as input, but its shape has an additional dimension of size 1 added.