tf.raw_ops.SparseMatrixSoftmax | TensorFlow v2.16.1 (original) (raw)
tf.raw_ops.SparseMatrixSoftmax
Stay organized with collections Save and categorize content based on your preferences.
Calculates the softmax of a CSRSparseMatrix.
View aliases
Compat aliases for migration
SeeMigration guide for more details.
tf.compat.v1.raw_ops.SparseMatrixSoftmax
tf.raw_ops.SparseMatrixSoftmax(
logits, type, name=None
)
Calculate the softmax of the innermost dimensions of a SparseMatrix.
Missing values are treated as -inf (i.e., logits of zero probability); and the output has the same sparsity structure as the input (though missing values in the output may now be treated as having probability zero).
| Args | |
|---|---|
| logits | A Tensor of type variant. A CSRSparseMatrix. |
| type | A tf.DType from: tf.float32, tf.float64. |
| name | A name for the operation (optional). |
| Returns |
|---|
| A Tensor of type variant. |
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.