gnh1201/wasm-micro-runtime
1
0
Fork 0
mirror of https://github.com/bytecodealliance/wasm-micro-runtime.git synced 2025-02-09 00:15:07 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity
5b144c491d
wasm-micro-runtime/core/iwasm/libraries/wasi-nn
History
tonibofarull e53ab91439
Integrate WASI-NN into WAMR (#1521) 
Initial integration of WASI-NN based on #1225:
- Implement the library core/iwasm/libraries/wasi-nn
- Support TensorFlow, CPU, F32 at the first stage
- Add cmake variable `-DWAMR_BUILD_WASI_NN`
- Add test case based on Docker image and update document

Refer to #1573
2022-10-12 12:09:29 +08:00
..
test Integrate WASI-NN into WAMR (#1521) 2022-10-12 12:09:29 +08:00
.dockerignore Integrate WASI-NN into WAMR (#1521) 2022-10-12 12:09:29 +08:00
logger.h Integrate WASI-NN into WAMR (#1521) 2022-10-12 12:09:29 +08:00
README.md Integrate WASI-NN into WAMR (#1521) 2022-10-12 12:09:29 +08:00
wasi_nn_common.h Integrate WASI-NN into WAMR (#1521) 2022-10-12 12:09:29 +08:00
wasi_nn_native.c Integrate WASI-NN into WAMR (#1521) 2022-10-12 12:09:29 +08:00
wasi_nn_tensorflow.cpp Integrate WASI-NN into WAMR (#1521) 2022-10-12 12:09:29 +08:00
wasi_nn_tensorflow.hpp Integrate WASI-NN into WAMR (#1521) 2022-10-12 12:09:29 +08:00
wasi_nn.cmake Integrate WASI-NN into WAMR (#1521) 2022-10-12 12:09:29 +08:00
wasi_nn.h Integrate WASI-NN into WAMR (#1521) 2022-10-12 12:09:29 +08:00

README.md

WASI-NN

How to use

Enable WASI-NN in the WAMR by spefiying it in the cmake building configuration as follows,

set (WAMR_BUILD_WASI_NN  1)

The definition of the functions provided by WASI-NN is in the header file core/iwasm/libraries/wasi-nn/wasi_nn.h.

By only including this file in your WASM application you will bind WASI-NN into your module.

Tests

To run the tests we assume that the current directory is the root of the repository.

  1. Build the docker image,
docker build -t wasi-nn -f core/iwasm/libraries/wasi-nn/test/Dockerfile .
  1. Run the container
docker run wasi-nn

If all the tests have run properly you will the the following message in the terminal,

Tests: passed!

What is missing

  • Only 1 model at a time is supported.
    • graph and graph-execution-context are ignored.
  • Only tensorflow (lite) is supported.
  • Only cpu is supported.