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
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
..
compatibility 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
configuration Implement a telemetry library for delegates to report their settings/status for A@S 2020-12-07 13:23:18 -08:00
README.md Replace instances of "whitelist" with "allowlist" where possible. See Google Developer guidelines at https://developers.google.com/style/word-list#blacklist for more information. 2020-07-08 10:13:43 -07:00

README.md

Accelerator allowlisting

Experimental library and tools for determining whether an accelerator engine works well on a given device, and for a given model.

Platform-agnostic, Android-first

Android-focused, since the much smaller set of configurations on iOS means there is much less need for allowlisting on iOS.

Not just for TfLite

This code lives in the TfLite codebase, since TfLite is the first open-source customer. It is however meant to support other users (direct use of NNAPI, mediapipe).