How to get the dimensions of a tensor (in TensorFlow) at graph construction time?

Question

I am trying an Op that is not behaving as expected.

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?

Shang · Answer 1 · 2017-04-09T04:16:47.080

I see most people confused about tf.shape(tensor) and tensor.get_shape() Let's make it clear:

tf.shape

tf.shape is 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

tensor.get_shape

tensor.get_shape is used for fixed shapes, which means the tensor's shape can be deduced in the graph.

Conclusion: tf.shape can be used almost anywhere, but t.get_shape only for shapes can be deduced from graph.

score 47 · Accepted Answer · edited May 23 '17 at 11:54

47

Tensor.get_shape() from this post.

From documentation:

c = tf.constant([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]])
print(c.get_shape())
==> TensorShape([Dimension(2), Dimension(3)])

edited May 23 '17 at 11:54

Community

1
1

answered May 01 '16 at 13:06

Thoran

8,884
7
41
50

4

If anyone wonders: `tf.shape(c)` returns a 1-D integer tensor representing the shape of `c`. In the example given in this answer, `tf.shape(c)` returns `Tensor("Shape:0", shape=(2,), dtype=int32)` – Franck Dernoncourt Feb 18 '17 at 16:12
2

@nobar if the dimension is `None` (i.e., if it is unspecified), you might need to use `tf.shape(c)`. For example, if `a = tf.placeholder(tf.int32, (None,2))`, and you run `tf.Session().run(tf.constant(a.get_shape().as_list()[0]), {a:[[1,2]]}) ` you will get error, but you can get the dimension by: `tf.Session().run(tf.shape(a)[0], {a:[[1,2]]})`. – Saeid BK Apr 09 '17 at 02:31

score 13 · Answer 3 · answered Jan 20 '17 at 19:48

13

A function to access the values:

def shape(tensor):
    s = tensor.get_shape()
    return tuple([s[i].value for i in range(0, len(s))])

Example:

batch_size, num_feats = shape(logits)

answered Jan 20 '17 at 19:48

Colin Swaney

141
1
2

1

`return tuple(tensor.get_shape().as_list())` if you want a tuple, or directly return the python list as in `return tensor.get_shape().as_list()` – Mr_and_Mrs_D Mar 27 '18 at 10:07

score 5 · Answer 4 · answered May 01 '16 at 13:08

Just print out the embed after construction graph (ops) without running:

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:

Tensor("embedding_lookup:0", shape=(128, 2, 64), dtype=float32)

Usually, it's good to check shapes of all tensors before training your models.

While the answer I gave before you post yours was correct, your answer gives more information about the tensor than just its shape, hence, I accept it as the correct answer ;) — Thoran, May 01 '16 at 13:13

score 4 · Answer 5 · answered Apr 08 '17 at 16:57

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()

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)

score 1 · Answer 6 · answered Nov 09 '17 at 19:38

1

The method tf.shape is a TensorFlow static method. However, there is also the method get_shape for the Tensor class. See

https://www.tensorflow.org/api_docs/python/tf/Tensor#get_shape

answered Nov 09 '17 at 19:38

cliffberg

11
2

None really - I was just trying to explain it as succinctly as possible ;-) – cliffberg Nov 10 '17 at 20:07

score 0 · Answer 7 · answered Mar 28 '22 at 14:33

To create tensor in tensorflow using tf.constant()

This is to import the library

import tensorflow as tf

This will create the tensor

tensor = tf.constant([[[2,4,5], [5,6,6]], [[9,7,8], [4,8,2]], [[7,1,3], [4,8,9]]])

This will show the tensor

tensor

this will show the number of dimension

tensor.ndim

score 0 · Answer 8 · answered Mar 28 '22 at 14:39

#create a tensor

tensor = tf.constant([[[1, 2, 3],
                   [3, 4, 5]],
                  [[5, 6, 7],
                   [8, 6, 9]],
                  [[2, 1, 5],
                   [5, 7, 8]]])
tensor

#Display result

<tf.Tensor: shape=(3, 2, 3), dtype=int32, numpy= array([[[1, 2, 3],[3, 4, 5]],

   [[5, 6, 7],
    [8, 6, 9]],

   [[2, 1, 5],
    [5, 7, 8]]], dtype=int32)>

How to get the dimensions of a tensor (in TensorFlow) at graph construction time?

8 Answers8

Linked