tensorflow--张量变换--2-- tf.shape 、tf.reshape

一、tf.shape

tf.shape(Tensor)

Returns the shape of a tensor.返回张量的形状。但是注意，tf.shape函数本身也是返回一个张量。而在tf中，张量是需要用sess.run(Tensor)来得到具体的值的。

labels = [1,2,3]
shape = tf.shape(labels)

print(shape)
# >>>Tensor("Shape:0", shape=(1,), dtype=int32)

sess = tf.InteractiveSession()

print(sess.run(shape))
# >>>[3]

二、tf.reshape

reshape(tensor, shape, name=None)

顾名思义，就是将tensor按照新的shape重新排列。一般来说，shape有三种用法：

• 如果 shape=[-1], 表示要将tensor展开成一个list
• 如果 shape=[a,b,c,…] 其中每个a,b,c,..均>0，那么就是常规用法
• 如果 shape=[a,-1,c,…] 此时b=-1，a,c,..依然>0。这表示tf会根据tensor的原尺寸，自动计算b的值。

代码示例：

# tensor 't' is [1, 2, 3, 4, 5, 6, 7, 8, 9]
# tensor 't' has shape [9]
reshape(t, [3, 3]) ==> [[1, 2, 3],
                        [4, 5, 6],
                        [7, 8, 9]]

# tensor 't' is [[[1, 1], [2, 2]],
#                [[3, 3], [4, 4]]]
# tensor 't' has shape [2, 2, 2]
reshape(t, [2, 4]) ==> [[1, 1, 2, 2],
                        [3, 3, 4, 4]]

# tensor 't' is [[[1, 1, 1],
#                 [2, 2, 2]],
#                [[3, 3, 3],
#                 [4, 4, 4]],
#                [[5, 5, 5],
#                 [6, 6, 6]]]
# tensor 't' has shape [3, 2, 3]
# pass '[-1]' to flatten 't'
reshape(t, [-1]) ==> [1, 1, 1, 2, 2, 2, 3, 3, 3, 4, 4, 4, 5, 5, 5, 6, 6, 6]

# -1 can also be used to infer the shape
# -1 is inferred to be 9:
reshape(t, [2, -1]) ==> [[1, 1, 1, 2, 2, 2, 3, 3, 3],
                         [4, 4, 4, 5, 5, 5, 6, 6, 6]]

# -1 is inferred to be 2:
reshape(t, [-1, 9]) ==> [[1, 1, 1, 2, 2, 2, 3, 3, 3],
                         [4, 4, 4, 5, 5, 5, 6, 6, 6]]

# -1 is inferred to be 3:
reshape(t, [ 2, -1, 3]) ==> [[[1, 1, 1],
                              [2, 2, 2],
                              [3, 3, 3]],
                             [[4, 4, 4],
                              [5, 5, 5],
                              [6, 6, 6]]]