Python 如何在图构建时获取张量（在 TensorFlow 中）的维度？
声明：本页面是StackOverFlow热门问题的中英对照翻译，遵循CC BY-SA 4.0协议，如果您需要使用它，必须同样遵循CC BY-SA许可，注明原文地址和作者信息，同时你必须将它归于原作者（不是我）：StackOverFlow
原文地址: http://stackoverflow.com/questions/36966316/
Warning: these are provided under cc-by-sa 4.0 license. You are free to use/share it, But you must attribute it to the original authors (not me):
StackOverFlow
How to get the dimensions of a tensor (in TensorFlow) at graph construction time?
提问by Thoran
I am trying an Op that is not behaving as expected.
我正在尝试一个行为不符合预期的操作。
graph = tf.Graph()
with graph.as_default():
train_dataset = tf.placeholder(tf.int32, shape=[128, 2])
embeddings = tf.Variable(
tf.random_uniform([50000, 64], -1.0, 1.0))
embed = tf.nn.embedding_lookup(embeddings, train_dataset)
embed = tf.reduce_sum(embed, reduction_indices=0)
So I need to know the dimensions of the Tensor embed. I know that it can be done at the run time but it's too much work for such a simple operation. What's the easier way to do it?
所以我需要知道 Tensor 的维度embed。我知道它可以在运行时完成，但是对于这样一个简单的操作来说工作量太大了。什么是更简单的方法？
回答by Shang
I see most people confused about tf.shape(tensor)and tensor.get_shape()Let's make it clear:
我看到大多数人对此感到困惑tf.shape(tensor)，tensor.get_shape()让我们说清楚：
tf.shape
tf.shape
tf.shapeis used for dynamic shape. If your tensor's shape is changable, use it.
An example: a input is an image with changable width and height, we want resize it to half of its size, then we can write something like:new_height = tf.shape(image)[0] / 2
tf.shape用于动态形状。如果张量的形状是可变的，请使用它。一个例子：输入是一个宽度和高度可变的图像，我们想要将它的大小调整为其大小的一半，然后我们可以这样写：new_height = tf.shape(image)[0] / 2
tensor.get_shape
tensor.get_shape
tensor.get_shapeis used for fixed shapes, which means the tensor's shape can be deducedin the graph.
tensor.get_shape用于固定形状，这意味着可以在图中推导出张量的形状。
Conclusion:
tf.shapecan be used almost anywhere, but t.get_shapeonly for shapes can be deduced from graph.
结论：
tf.shape几乎可以在任何地方使用，但t.get_shape仅适用于可以从图形中推断出的形状。
回答by Thoran
回答by Colin Swaney
A function to accessthe values:
访问值的函数：
def shape(tensor):
s = tensor.get_shape()
return tuple([s[i].value for i in range(0, len(s))])
Example:
例子：
batch_size, num_feats = shape(logits)
回答by Sung Kim
Just print out the embed after construction graph (ops) without running:
只需在不运行的情况下打印出构建图 (ops) 后的嵌入：
import tensorflow as tf
...
train_dataset = tf.placeholder(tf.int32, shape=[128, 2])
embeddings = tf.Variable(
tf.random_uniform([50000, 64], -1.0, 1.0))
embed = tf.nn.embedding_lookup(embeddings, train_dataset)
print (embed)
This will show the shape of the embed tensor:
这将显示嵌入张量的形状：
Tensor("embedding_lookup:0", shape=(128, 2, 64), dtype=float32)
Usually, it's good to check shapes of all tensors before training your models.
通常，在训练模型之前检查所有张量的形状是很好的。
回答by kmario23
Let's make it simple as hell. If you want a single number for the number of dimensions like 2, 3, 4, etc.,then just use tf.rank(). But, if you want the exact shape of the tensor then use tensor.get_shape()
让我们让它变得简单。如果你想要一个单一的维度数，2, 3, 4, etc.,那么只需使用tf.rank(). 但是，如果您想要张量的确切形状，请使用tensor.get_shape()
with tf.Session() as sess:
arr = tf.random_normal(shape=(10, 32, 32, 128))
a = tf.random_gamma(shape=(3, 3, 1), alpha=0.1)
print(sess.run([tf.rank(arr), tf.rank(a)]))
print(arr.get_shape(), ", ", a.get_shape())
# for tf.rank()
[4, 3]
# for tf.get_shape()
Output: (10, 32, 32, 128) , (3, 3, 1)
回答by cliffberg
The method tf.shape is a TensorFlow static method. However, there is also the method get_shape for the Tensor class. See
tf.shape 方法是一个 TensorFlow 静态方法。然而，Tensor 类也有 get_shape 方法。看
https://www.tensorflow.org/api_docs/python/tf/Tensor#get_shape
https://www.tensorflow.org/api_docs/python/tf/Tensor#get_shape
