Archived

This repository has been archived on 2023-11-05. You can view files and clone it, but cannot push or open issues or pull requests.

History

Wenyong Huang 8b96f4fb71 Update sample workload's scripts to align with latest emcc (#609 ) And enable auxiliary stack overflow/underflow check in JIT mode		2021-04-13 13:42:08 +08:00
..
build.sh	Update sample workload's scripts to align with latest emcc (#609 )	2021-04-13 13:42:08 +08:00
README.md	Update build scripts and documents of workload samples for wasi-sdk-12.0 (#484 )	2020-12-29 14:41:09 +08:00
tf_lite.patch	Fix interpreter not update memory size after call native func (#563 )	2021-03-10 15:07:16 +08:00

"tensorflow" sample introduction

This sample demonstrates how to build tensorflow into WebAssembly with emsdk toolchain and run it with iwasm. Please first install emsdk:

git clone https://github.com/emscripten-core/emsdk.git
cd emsdk
./emsdk install latest
./emsdk activate latest

And set up ensdk environment:

source emsdk_env.sh

Then run

./build.sh
# for linux platform, or
./build.sh --sgx
# for linux-sgx platform

to build tensorflow and run it with iwasm, which basically contains the following steps:

hack emcc to delete some objects in libc.a
build tf-lite with emcc compiler
build iwasm with pthread enable and include libiary under libc-emcc
run benchmark model with iwasm: --max-secs 300: means the max training time cost is 5 minutes, you can adjust by yourself