Skip to content
This repository has been archived by the owner on Nov 25, 2023. It is now read-only.

[ENHANCE] 增加TFLite,编译太慢先不考虑 #28

Closed
ysh329 opened this issue Aug 21, 2020 · 3 comments
Closed

[ENHANCE] 增加TFLite,编译太慢先不考虑 #28

ysh329 opened this issue Aug 21, 2020 · 3 comments
Labels
enhancement New feature or request new framework Add new inference deep learning framework to benchmark

Comments

@ysh329
Copy link
Contributor

ysh329 commented Aug 21, 2020

https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite

@ysh329 ysh329 added the enhancement New feature or request label Aug 21, 2020
@ysh329 ysh329 changed the title [ENHANCE] 增加TFLite [ENHANCE] 增加TFLite,编译太慢先不考虑 Aug 21, 2020
@ysh329 ysh329 added the new framework Add new inference deep learning framework to benchmark label Aug 23, 2020
@ysh329 ysh329 pinned this issue Aug 23, 2020
@ysh329
Copy link
Contributor Author

ysh329 commented Aug 29, 2020

@ysh329
Copy link
Contributor Author

ysh329 commented Aug 29, 2020

++ cd /usr/local/lib/bazel/bin
./build_tflite_android.sh: line 29: cd: /usr/local/lib/bazel/bin: No such file or directory
++ cd -
/home/runner/work/embedded-ai.bench/embedded-ai.bench
++ cp ../configure.py.bench ./configure.py
cp: cannot stat '../configure.py.bench': No such file or directory
++ ./configure
./build_tflite_android.sh: line 34: ./configure: No such file or directory
++ bazel build -c opt --config=android_arm tensorflow/lite/tools/benchmark:benchmark_model
2020/08/29 15:17:16 Downloading https://releases.bazel.build/3.4.1/release/bazel-3.4.1-linux-x86_64...
Extracting Bazel installation...
Picked up JAVA_TOOL_OPTIONS: -Dfile.encoding=UTF8

@ysh329
Copy link
Contributor Author

ysh329 commented Sep 28, 2020

已支持

@ysh329 ysh329 closed this as completed Sep 28, 2020
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
enhancement New feature or request new framework Add new inference deep learning framework to benchmark
Projects
None yet
Development

No branches or pull requests

1 participant