tf.extract_volume_patches
Stay organized with collections
Save and categorize content based on your preferences.
Extract patches from input and put them in the "depth" output dimension. 3D extension of extract_image_patches.
tf.extract_volume_patches(
input, ksizes, strides, padding, name=None
)
Args |
|---|
input
|
A Tensor. Must be one of the following types: float32, float64, int32, uint8, int16, int8, int64, bfloat16, uint16, half, uint32, uint64.
5-D Tensor with shape [batch, in_planes, in_rows, in_cols, depth].
|
ksizes
|
A list of ints that has length >= 5.
The size of the sliding window for each dimension of input.
|
strides
|
A list of ints that has length >= 5.
1-D of length 5. How far the centers of two consecutive patches are in
input. Must be: [1, stride_planes, stride_rows, stride_cols, 1].
|
padding
|
A string from: "SAME", "VALID".
The type of padding algorithm to use.
We specify the size-related attributes as:
ksizes = [1, ksize_planes, ksize_rows, ksize_cols, 1]
strides = [1, stride_planes, strides_rows, strides_cols, 1]
|
name
|
A name for the operation (optional).
|
Returns |
|---|
A Tensor. Has the same type as input.
|
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.extract_volume_patches\n\n\u003cbr /\u003e\n\n|-----------------------------------------------------------------------------------|\n| [TensorFlow 1 version](/versions/r1.15/api_docs/python/tf/extract_volume_patches) |\n\nExtract `patches` from `input` and put them in the \"depth\" output dimension. 3D extension of `extract_image_patches`.\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.extract_volume_patches`](/api_docs/python/tf/extract_volume_patches)\n\n\u003cbr /\u003e\n\n tf.extract_volume_patches(\n input, ksizes, strides, padding, name=None\n )\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|-----------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `input` | A `Tensor`. Must be one of the following types: `float32`, `float64`, `int32`, `uint8`, `int16`, `int8`, `int64`, `bfloat16`, `uint16`, `half`, `uint32`, `uint64`. 5-D Tensor with shape `[batch, in_planes, in_rows, in_cols, depth]`. |\n| `ksizes` | A list of `ints` that has length `\u003e= 5`. The size of the sliding window for each dimension of `input`. |\n| `strides` | A list of `ints` that has length `\u003e= 5`. 1-D of length 5. How far the centers of two consecutive patches are in `input`. Must be: `[1, stride_planes, stride_rows, stride_cols, 1]`. |\n| `padding` | A `string` from: `\"SAME\", \"VALID\"`. The type of padding algorithm to use. \u003cbr /\u003e We specify the size-related attributes as: ksizes = [1, ksize_planes, ksize_rows, ksize_cols, 1] strides = [1, stride_planes, strides_rows, strides_cols, 1] \u003cbr /\u003e |\n| `name` | A name for the operation (optional). |\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`. ||\n\n\u003cbr /\u003e"]]
TensorFlow 1 version