tf.reshape

官方文档链接

https://www.tensorflow.org/api_docs/python/tf/reshape

调用

tf.reshape(
    tensor,
    shape,
    name=None
)

It means that tf.reshape produces a new tensor.

x = tf.constant([29.05088806,  27.61298943,  31.19073486,  29.35532951,
  30.97266006,  26.67541885,  38.08450317,  20.74983215,
  34.94445419,  34.45999146,  29.06485367,  36.01657104,
  27.88236427,  20.56035233,  30.20379066,  29.51215172,
  33.71149445,  28.59134293,  36.05556488,  28.66994858])
y = x	#只是将一个变量y指向了x所指向的Tensor对象，并没有创建新的Tensor，用以判断进行了reshape操作后，原Tensor是否改变，是否创建了新的Tensor对象
x = tf.reshape(x,[5,-1]) 

print(sess.run(x))
print(sess.run(y))
[[29.050888 27.61299  31.190735 29.35533 ]
 [30.97266  26.675419 38.084503 20.749832]
 [34.944454 34.45999  29.064854 36.01657 ]
 [27.882364 20.560352 30.20379  29.512152]
 [33.711494 28.591343 36.055565 28.669949]]
 
[29.050888 27.61299  31.190735 29.35533  30.97266  26.675419 38.084503
 20.749832 34.944454 34.45999  29.064854 36.01657  27.882364 20.560352
 30.20379  29.512152 33.711494 28.591343 36.055565 28.669949]