tf.zeros_like
Stay organized with collections
Save and categorize content based on your preferences.
Creates a tensor with all elements set to zero.
tf.zeros_like(
tensor, dtype=None, name=None, optimize=True
)
Given a single tensor (tensor), this operation returns a tensor of the
same type and shape as tensor with all elements set to zero. Optionally,
you can use dtype to specify a new type for the returned tensor.
For example:
tensor = tf.constant([[1, 2, 3], [4, 5, 6]])
tf.zeros_like(tensor) # [[0, 0, 0], [0, 0, 0]]
Args |
|---|
tensor
|
A Tensor.
|
dtype
|
A type for the returned Tensor. Must be float16, float32,
float64, int8, uint8, int16, uint16, int32, int64,
complex64, complex128, bool or string.
|
name
|
A name for the operation (optional).
|
optimize
|
if true, attempt to statically determine the shape of 'tensor' and
encode it as a constant.
|
Returns |
|---|
A Tensor with all elements set to zero.
|
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2020-10-01 UTC.
[null,null,["Last updated 2020-10-01 UTC."],[],[],null,["# tf.zeros_like\n\n\u003cbr /\u003e\n\n|--------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------|\n| [TensorFlow 2 version](/api_docs/python/tf/zeros_like) | [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/ops/array_ops.py#L2355-L2383) |\n\nCreates a tensor with all elements set to zero.\n\n#### View aliases\n\n\n**Compat aliases for migration**\n\nSee\n[Migration guide](https://www.tensorflow.org/guide/migrate) for\nmore details.\n\n[`tf.compat.v1.zeros_like`](/api_docs/python/tf/compat/v1/zeros_like)\n\n\u003cbr /\u003e\n\n tf.zeros_like(\n tensor, dtype=None, name=None, optimize=True\n )\n\nGiven a single tensor (`tensor`), this operation returns a tensor of the\nsame type and shape as `tensor` with all elements set to zero. Optionally,\nyou can use `dtype` to specify a new type for the returned tensor.\n\n#### For example:\n\n tensor = tf.constant([[1, 2, 3], [4, 5, 6]])\n tf.zeros_like(tensor) # [[0, 0, 0], [0, 0, 0]]\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `tensor` | A `Tensor`. |\n| `dtype` | A type for the returned `Tensor`. Must be `float16`, `float32`, `float64`, `int8`, `uint8`, `int16`, `uint16`, `int32`, `int64`, `complex64`, `complex128`, `bool` or `string`. |\n| `name` | A name for the operation (optional). |\n| `optimize` | if true, attempt to statically determine the shape of 'tensor' and encode it as a constant. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| A `Tensor` with all elements set to zero. ||\n\n\u003cbr /\u003e"]]
TensorFlow 2 version
View source on GitHub