提问人:stackoverflowuser2010 提问时间:11/18/2016 最后编辑:Joel Carneirostackoverflowuser2010 更新时间:7/7/2020 访问量:145891
如何获取 Tensorflow 张量维度(形状)作为 int 值?
How to get Tensorflow tensor dimensions (shape) as int values?
问:
假设我有一个 Tensorflow 张量。如何将张量的维度(形状)获取为整数值?我知道有两种方法,和 ,但我无法将形状值作为整数值。tensor.get_shape()
tf.shape(tensor)
int32
例如,下面我创建了一个二维张量,我需要获取行数和列数,以便我可以调用来创建形状的张量。但是,该方法以 type 的形式返回值,而不是 。int32
reshape()
(num_rows * num_cols, 1)
tensor.get_shape()
Dimension
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.
答:
要以整数列表的形式获取形状,请执行 .tensor.get_shape().as_list()
要完成通话,请尝试 。或者你可以直接在可以推断出它的第一个维度的地方做。tf.shape()
tensor2 = tf.reshape(tensor, tf.TensorShape([num_rows*num_cols, 1]))
tensor2 = tf.reshape(tensor, tf.TensorShape([-1, 1]))
评论
tf.reshape()
num_rows
num_cols
tensor.get_shape().as_list()
num_rows, num_cols = x.get_shape().as_list()
解决此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。
对于二维张量,您可以使用以下代码以 int32 的形式获取行数和列数:
rows, columns = map(lambda i: i.value, tensor.get_shape())
评论
在更高版本(使用 TensorFlow 1.14 测试)中,有一种更类似于 numpy 的方法来获取张量的形状。你可以用它来获取张量的形状。tensor.shape
tensor_shape = tensor.shape
print(tensor_shape)
2.0 兼容答案:在 Tensorflow 2.x (2.1
) 中,可以将张量的维度(形状)获取为整数值,如下代码所示:
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]
另一个简单的解决方案是按如下方式使用:map()
tensor_shape = map(int, my_tensor.shape)
这会将所有对象转换为Dimension
int
评论