experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
mm-fix-macos-protobuf-segfault
STT-tensorflow/tensorflow/lite/experimental/acceleration/compatibility
History
A. Unique TensorFlower 1c279b93da Update TFLite GPU delegate compatibility listing with newest telemetry. Roughly 0.3% of users devices were changed from unsupported to supported, and roughly 0.5% from supported to unsupported. The biggest change for the 0.5% new unsupported devices was marking the SDM429 SoC as unsupported due to initialization timeouts. 
Adds the new SM7250 SoC as supported.

PiperOrigin-RevId: 346763951
Change-Id: I7049a1774c539c4a83af2232f80e1329929bbc14
2020-12-10 05:35:28 -08:00
..
android_info.cc
android_info.h
BUILD Rename exec_tools to tools 2020-11-16 11:18:05 +01:00
convert_binary_to_cc_source.py
database.fbs Export GPU allowlist database and flatbuffer java library BUILD targets. 2020-08-13 12:04:23 -07:00
devicedb_test.cc Update documentation about the possible values of support status. 2020-08-17 04:38:23 -07:00
devicedb-sample.json Update documentation about the possible values of support status. 2020-08-17 04:38:23 -07:00
devicedb.cc
devicedb.h
gpu_compatibility_test.cc Added GpuApi to GpuInfo. 2020-11-18 18:16:44 -08:00
gpu_compatibility.bin Update TFLite GPU delegate compatibility listing with newest telemetry. Roughly 0.3% of users devices were changed from unsupported to supported, and roughly 0.5% from supported to unsupported. The biggest change for the 0.5% new unsupported devices was marking the SDM429 SoC as unsupported due to initialization timeouts. 2020-12-10 05:35:28 -08:00
gpu_compatibility.cc Added GpuApi to GpuInfo. 2020-11-18 18:16:44 -08:00
gpu_compatibility.h Add method for validating GPUCompatibilityList flatbuffer 2020-09-21 07:41:29 -07:00
json_to_fb.cc
README.md
variables.h Update documentation about the possible values of support status. 2020-08-17 04:38:23 -07:00

README.md

GPU delegate compatibility database

This package provides data and code for deciding if the GPU delegate is supported on a specific Android device.

Customizing the database

  • Convert from checked-in flatbuffer to json by running flatc -t --raw-binary --strict-json database.fbs -- gpu_compatibility.bin
  • Edit the json
  • Convert from json to flatbuffer flatc -b database.fbs -- gpu_compatibility.json
  • Rebuild ../../../java:tensorflow-lite-gpu