tflite-micro

tflite-micro copied to clipboard

Add support for 16 bit activations in ExpandDims operation.

1

The change introduces the support for ML models with 16 bit activations and 8 bit weights in the ExpandDims operation. BUG=fixes #68293

robertkamara

Int8 Inference Speed Drasticly Dropped

1

I quantized a cnn to an int8 one and measured the average inference speed, the latency is 2x slower than the original fp32 model. Then I used the profile tools...

zyw02

Begin using -std=c++17 and -std=c17 in Makefile builds on all platforms. Bazel builds have been using C++17 since 52c9568. BUG=see description

rkuester

@tensorflow/micro initial header file changes/additions. bug=#2646

ddavis-2015

Cortex-M CI Run Failed

4

Cortex-M [run number 1544](http://github.com/tensorflow/tflite-micro/actions/runs/10087978372) failed. This issue has been automatically generated for notification purposes.

github-actions[bot]

@tensorflow/micro Initial header file changes/additions

ddavis-2015

I am trying to run the Mini speech commands example and am facing the error `Didn't find op for builtin opcode 'CONV_2D' version '3'. An older version of this builtin...

rishita-asl

testing

ddavis-2015

feat: add fixed-capacity, statically-allocated type tflite::StaticVector

1

Add a type, tflite::StaticVector, which behaves like std::vector, but which avoids heap memory allocation. BUG=#2636

rkuester

Adding this for tracking as recommended in the contribution guidelines. ``` Type 'INT16' is not supported by gather. Node GATHER (number 4f) failed to prepare with status 1 ```

andresovela