Given a tensor input, this operation returns a tensor of the same type with
all dimensions of size 1 removed. If you don't want to remove all size 1
dimensions, you can remove specific size 1 dimensions by specifying
axis.
For example:
# 't' is a tensor of shape [1, 2, 1, 3, 1, 1]t=tf.ones([1,2,1,3,1,1])print(tf.shape(tf.squeeze(t)).numpy())[23]
Or, to remove specific size 1 dimensions:
# 't' is a tensor of shape [1, 2, 1, 3, 1, 1]t=tf.ones([1,2,1,3,1,1])print(tf.shape(tf.squeeze(t,[2,4])).numpy())[1231]
Args
input
A Tensor. The input to squeeze.
axis
An optional list of ints. Defaults to []. If specified, only
squeezes the dimensions listed. The dimension index starts at 0. It is an
error to squeeze a dimension that is not 1. Must be in the range
[-rank(input), rank(input)). Must be specified if input is a
RaggedTensor.
name
A name for the operation (optional).
squeeze_dims
Deprecated keyword argument that is now axis.
Returns
A Tensor. Has the same type as input.
Contains the same data as input, but has one or more dimensions of
size 1 removed.
[null,null,["Last updated 2024-04-26 UTC."],[],[],null,["# tf.compat.v1.squeeze\n\n\u003cbr /\u003e\n\n|-------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.16.1/tensorflow/python/ops/array_ops.py#L4199-L4251) |\n\nRemoves dimensions of size 1 from the shape of a tensor. (deprecated arguments) \n\n tf.compat.v1.squeeze(\n input, axis=None, name=None, squeeze_dims=None\n )\n\n### Used in the notebooks\n\n| Used in the tutorials |\n|----------------------------------------------------------------------------------|\n| - [Wiki40B Language Models](https://www.tensorflow.org/hub/tutorials/wiki40b_lm) |\n\n| **Deprecated:** SOME ARGUMENTS ARE DEPRECATED: `(squeeze_dims)`. They will be removed in a future version. Instructions for updating: Use the `axis` argument instead\n\nGiven a tensor `input`, this operation returns a tensor of the same type with\nall dimensions of size 1 removed. If you don't want to remove all size 1\ndimensions, you can remove specific size 1 dimensions by specifying\n`axis`.\n\n#### For example:\n\n # 't' is a tensor of shape [1, 2, 1, 3, 1, 1]\n t = tf.ones([1, 2, 1, 3, 1, 1])\n print(tf.shape(tf.squeeze(t)).numpy())\n [2 3]\n\nOr, to remove specific size 1 dimensions: \n\n # 't' is a tensor of shape [1, 2, 1, 3, 1, 1]\n t = tf.ones([1, 2, 1, 3, 1, 1])\n print(tf.shape(tf.squeeze(t, [2, 4])).numpy())\n [1 2 3 1]\n\n| **Note:** if `input` is a [`tf.RaggedTensor`](../../../tf/RaggedTensor), then this operation takes `O(N)` time, where `N` is the number of elements in the squeezed dimensions.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|----------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `input` | A `Tensor`. The `input` to squeeze. |\n| `axis` | An optional list of `ints`. Defaults to `[]`. If specified, only squeezes the dimensions listed. The dimension index starts at 0. It is an error to squeeze a dimension that is not 1. Must be in the range `[-rank(input), rank(input))`. Must be specified if `input` is a `RaggedTensor`. |\n| `name` | A name for the operation (optional). |\n| `squeeze_dims` | Deprecated keyword argument that is now axis. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| A `Tensor`. Has the same type as `input`. Contains the same data as `input`, but has one or more dimensions of size 1 removed. ||\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Raises ------ ||\n|--------------|----------------------------------------------------|\n| `ValueError` | When both `squeeze_dims` and `axis` are specified. |\n\n\u003cbr /\u003e"]]
View source on GitHub