tflite_gles_app icon indicating copy to clipboard operation
tflite_gles_app copied to clipboard

OpenCL backend tflite gpu delegate

Open rose-jinyang opened this issue 3 years ago • 7 comments

Hello How are you? Thanks for contributing to this project. I am going to use the OpenCL backend tflite runtime on RK3399 Ubuntu 18.04 aarch64. I found that u provided a script to build tflite gpu delegate so file for aarch64. (https://github.com/terryky/tflite_gles_app/blob/master/tools/scripts/tf2.4/build_libtflite_r2.4_aarch64.sh) Do u think that the gpu delegate so file built by your script can use the OpenCL on RK3399 Mali T860? Thanks

rose-jinyang avatar Jan 14 '21 01:01 rose-jinyang

yes, I think it will works although I've never tested it on RK3399.

terryky avatar Jan 14 '21 05:01 terryky

I got the built gpu delegate so file "libtensorflowlite_gpu_delegate.so" BTW where can I get the built main tensorflowlite library file? I could not find the file.

rose-jinyang avatar Jan 14 '21 10:01 rose-jinyang

./tensorflow/bazel-bin/tensorflow/lite/libtensorflowlite.so could you read README.md?

terryky avatar Jan 14 '21 10:01 terryky

thanks

rose-jinyang avatar Jan 14 '21 10:01 rose-jinyang

Did u try to build/use the GPU enabled tflite runtime for Python? if so, could u let me know about the steps/methods? Thanks

rose-jinyang avatar Jan 14 '21 10:01 rose-jinyang

Unfortunatelly, no. I'm not familiar with tflite-python-API.

terryky avatar Jan 14 '21 11:01 terryky

Did u try to build/use the GPU enabled tflite runtime for Python? if so, could u let me know about the steps/methods? Thanks

you can refer aid learning . it make Python calling gpu in tflite directly

aidlearning avatar Jan 19 '21 08:01 aidlearning