tf.raw_ops.SparseSegmentSqrtNGradV2
Stay organized with collections Save and categorize content based on your preferences.
Computes gradients for SparseSegmentSqrtN.
tf.raw_ops.SparseSegmentSqrtNGradV2(
grad, indices, segment_ids, dense_output_dim0, name=None
)
Returns tensor "output" with same shape as grad, except for dimension 0 whose value is the number of unique indexes in "indices". Also returns vector "sorted_unique_indices" containing the corresponding indexes from "indices".
Args |
|---|
grad | A Tensor. Must be one of the following types: bfloat16, half, float32, float64. gradient propagated to the SparseSegmentSqrtN op. |
indices | A Tensor. Must be one of the following types: int32, int64. indices passed to the corresponding SparseSegmentSqrtN op. |
segment_ids | A Tensor. Must be one of the following types: int32, int64. segment_ids passed to the corresponding SparseSegmentSqrtN op. |
dense_output_dim0 | A Tensor of type int32. dimension 0 of "data" passed to SparseSegmentSqrtN op. |
name | A name for the operation (optional). |
Returns |
|---|
A tuple of Tensor objects (output, sorted_unique_indices). |
output | A Tensor. Has the same type as grad. |
sorted_unique_indices | A Tensor. Has the same type as indices. |
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. Some content is licensed under the numpy license.
Last updated 2024-04-26 UTC.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2024-04-26 UTC."],[],[]]