基于tf.shape(tensor)和tensor.shape()的区别说明

a=tf.zeros([4,5,4,5,6])
print(type(a.shape))
print(a.shape.ndims)#多少个维度
print(a.shape.as_list())#返回列表
print(type(tf.shape(a)))
print(type(tf.shape(a)[0]))
b=a.shape.as_list()
c=tf.shape(a)
b[1]=tf.shape(a)[1]
print(b)
sess=tf.Session()
d=sess.run(c)
print(d)

outputs:

5
[4, 5, 4, 5, 6]


[4, , 4, 5, 6]
[4 5 4 5 6]

import tensorflow.compat.v1 as tf
from tensorflow.python.framework import tensor_shape
from tensorflow.python.framework import constant_op
 
tensor_test1=[10,10,10]
tensor_test2 = [None,10,10]
 
p1 = tensor_shape.as_shape(tensor_test1) # 得到的是一个类实例，该类实例包含一个属性，是 tensor_test1 的value
const = constant_op.constant(p1.as_list())
 
print("type(p1) = ",type(p1))
print("p1 = ",p1) # 使用p1时会自动调用p1中的value属性
print("p1.is_fully_defined() = ",p1.is_fully_defined())# is_fully_defined 是 TensorShape 类的一个内部函数
print("p1.ndims = ",p1.ndims) # ndims 也是TensorShape的一个属性值
print("p1.as_list() = ",p1.as_list()) # 把TensorShape的value属性转换成python中的list类型
print("const = ",const)

type(p1) = 
p1 = (10, 10, 10)
p1.is_fully_defined() = True
p1.ndims = 3
p1.as_list() = [10, 10, 10]
const = Tensor("Const:0", shape=(3,), dtype=int32)