Support for 16 bit activations in ExpandDims operation. #68293
Labels
comp:lite
TF Lite related issues
comp:ops
OPs related issues
stale
This label marks the issue/pr stale - to be closed automatically if no activity
stat:awaiting response
Status - Awaiting response from author
TF 2.16
type:feature
Feature requests
The task is to add support for 16-bit activations and 8-bit weights in ExpandDims operation. Currently, only float32 and int8_t types are supported:
https://github.com/tensorflow/tflite-micro/blob/8e22946b3faa51564df5dd9194f7540b2694892c/tensorflow/lite/micro/kernels/expand_dims.cc#L127C1-L134C13
The text was updated successfully, but these errors were encountered: