wasm-micro-runtime/core
tonibofarull 0b0af1b3df
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/).
2023-08-11 07:55:40 +08:00
..
app-framework Readme refactoring (#2038) 2023-03-19 08:05:57 +08:00
app-mgr Readme refactoring (#2038) 2023-03-19 08:05:57 +08:00
deps wasi-nn: Simplify cmake and headers' location (#2308) 2023-06-26 09:29:05 +08:00
iwasm wasi-nn: Support uint8 quantized networks (#2433) 2023-08-11 07:55:40 +08:00
shared Remove unnecessary and extra zero length check in mem functions' macro (#2428) 2023-08-08 08:52:25 +08:00
config.h Bring up WAMR on esp32-s3 device (#2348) 2023-07-21 07:54:13 +08:00
version.h Update version number and release notes (#2213) 2023-05-16 12:39:22 +08:00