- Sort Score
- Result 10 results
- Languages All
Results 1 - 1 of 1 for doFinal (0.15 sec)
-
RELEASE.md
* `tf.math.argmin`/`tf.math.argmax` for input data type `tf.bool` on CPU. * `tf.nn.gelu` op for output data type `tf.float32` and quantization on CPU. * Add nominal support for unsigned 16-bit integer tensor types. Note that very few TFLite kernels support this type natively, so its use in mobile ML authoring is generally discouraged.
Plain Text - Registered: Tue May 07 12:40:20 GMT 2024 - Last Modified: Mon Apr 29 19:17:57 GMT 2024 - 727.7K bytes - Viewed (8)