2017-10-19 108 views

回答

0

这取决于你打算如何填补它。举例如下:

# Assuming input is a tensor with shape (?, 28, 28, 1) 
output = tf.pad(input, [[0, 0], [2,2], [2,2], [0,0]]) 
# print(tf.shape(output)) should be (?, 32, 32, 1)