wasi-nn: Support uint8 quantized networks (#2433)

Support (non-full) uint8 quantized networks.
Inputs and outputs are still required to be `float`. The (de)quantization is done internally by wasi-nn.

Example generated from `quantized_model.py`:
![Screenshot from 2023-08-07 17-57-05](https://github.com/bytecodealliance/wasm-micro-runtime/assets/80318361/91f12ff6-870c-427a-b1dc-e307f7d1f5ee)

Visualization with [netron](https://netron.app/).

This commit is contained in:

tonibofarull

2023-08-11 07:55:40 +08:00

committed by

GitHub

parent a550f4d9f7

commit 0b0af1b3df

7 changed files with 176 additions and 17 deletions

core/iwasm/libraries/wasi-nn/.gitignore

View File

@@ -0,0 +1,2 @@
 **/*.wasm
 **/*.tflite