假设我有一个 Tensorflow 张量。如何获取张量的尺寸(形状)作为整数值?我知道有两种方法,
tensor.get_shape()
和tf.shape(tensor)
,但我无法获取整数int32
值的形状值。
例如,下面我创建了一个二维张量,我需要获取行数和列数为
int32
,以便我可以调用reshape()
来创建形状为(num_rows * num_cols, 1)
的张量。但是,方法 tensor.get_shape()
返回 Dimension
类型的值,而不是 int32
。
import tensorflow as tf
import numpy as np
sess = tf.Session()
tensor = tf.convert_to_tensor(np.array([[1001,1002,1003],[3,4,5]]), dtype=tf.float32)
sess.run(tensor)
# array([[ 1001., 1002., 1003.],
# [ 3., 4., 5.]], dtype=float32)
tensor_shape = tensor.get_shape()
tensor_shape
# TensorShape([Dimension(2), Dimension(3)])
print tensor_shape
# (2, 3)
num_rows = tensor_shape[0] # ???
num_cols = tensor_shape[1] # ???
tensor2 = tf.reshape(tensor, (num_rows*num_cols, 1))
# Traceback (most recent call last):
# File "<stdin>", line 1, in <module>
# File "/usr/local/lib/python2.7/site-packages/tensorflow/python/ops/gen_array_ops.py", line 1750, in reshape
# name=name)
# File "/usr/local/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 454, in apply_op
# as_ref=input_arg.is_ref)
# File "/usr/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 621, in convert_to_tensor
# ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
# File "/usr/local/lib/python2.7/site-packages/tensorflow/python/framework/constant_op.py", line 180, in _constant_tensor_conversion_function
# return constant(v, dtype=dtype, name=name)
# File "/usr/local/lib/python2.7/site-packages/tensorflow/python/framework/constant_op.py", line 163, in constant
# tensor_util.make_tensor_proto(value, dtype=dtype, shape=shape))
# File "/usr/local/lib/python2.7/site-packages/tensorflow/python/framework/tensor_util.py", line 353, in make_tensor_proto
# _AssertCompatible(values, dtype)
# File "/usr/local/lib/python2.7/site-packages/tensorflow/python/framework/tensor_util.py", line 290, in _AssertCompatible
# (dtype.name, repr(mismatch), type(mismatch).__name__))
# TypeError: Expected int32, got Dimension(6) of type 'Dimension' instead.
要获取整数列表形式的形状,请执行
tensor.get_shape().as_list()
。
要完成您的
tf.shape()
通话,请尝试 tensor2 = tf.reshape(tensor, tf.TensorShape([num_rows*num_cols, 1]))
。或者你可以直接做tensor2 = tf.reshape(tensor, tf.TensorShape([-1, 1]))
,可以推断出它的第一个维度。
解决这个问题的另一种方法是这样的:
tensor_shape[0].value
这将返回 Dimension 对象的 int 值。
2.0兼容答案:在
Tensorflow 2.x (2.1)
中,您可以获得张量的维度(形状)作为整数值,如下面的代码所示:
方法1(使用
tf.shape
):
import tensorflow as tf
c = tf.constant([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]])
Shape = c.shape.as_list()
print(Shape) # [2,3]
方法2(使用
tf.get_shape()
):
import tensorflow as tf
c = tf.constant([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]])
Shape = c.get_shape().as_list()
print(Shape) # [2,3]
对于二维张量,您可以使用以下代码获取 int32 形式的行数和列数:
rows, columns = map(lambda i: i.value, tensor.get_shape())
另一个简单的解决方案是使用
map()
,如下所示:
tensor_shape = map(int, my_tensor.shape)
这会将所有
Dimension
对象转换为 int
在更高版本(使用 TensorFlow 1.14 进行测试)中,有一种更像 numpy 的方法来获取张量的形状。您可以使用
tensor.shape
来获取张量的形状。
tensor_shape = tensor.shape
print(tensor_shape)
使用这行代码:
tensor_shape[0].value
它会给你格式化为整数的张量的形状。