tflite-micro icon indicating copy to clipboard operation
tflite-micro copied to clipboard

Infrastructure to enable deployment of ML models to low-power resource-constrained embedded targets (including microcontrollers and digital signal processors).

Results 62 tflite-micro issues
Sort by recently updated
recently updated
newest added

**System information** - OS Platform and Distribution (e.g., Linux Ubuntu 22.04): - TensorFlow installed from (source or binary): pip - TensorFlow version (or github SHA if from source): 2.15.0.post1 **Background...

https://github.com/google-ai-edge should be used rather than tensorflow.lite

I get -WShadow build errors when compiling from tensorflow/lite/kernels/internal/reference/mul.h and tensorflow/lite/kernels/internal/reference/sub.h from a few functions that use the word 'params' twice in the header. I worked around this issue by...

Run-CI [run number 705](http://github.com/tensorflow/tflite-micro/actions/runs/10938822367) failed. This issue has been automatically generated for notification purposes.

ci:bot_issue

[tensorflow==2.15.0.post1 ](https://github.com/tensorflow/tflite-micro/blob/c01ca97f52ca451bfba714d7eb8ae0349d85f537/third_party/python_requirements.txt#L704) is not existing for aarch64. I am proposing to do a new update which should probably solve it: `bazel run //third_party:python_requirements.update` Some more background on the issue: https://github.com/tensorflow/tflite-micro/issues/2499#issuecomment-2009260738

Stale

Adds per channel quantization support for fully connnected reference and cmsis-nn kernel. BUG=missing support for FC per channel quantization

@tensorflow/micro Changes for TFLM compression: MicroAllocator RecordingMicroAllocator generic benchmark

This PR adds int16 support to OP_RELU6. This is already supported in TF Lite. bug=#2681

This is already supported in TF Lite: https://github.com/tensorflow/tensorflow/blob/53df8c0156cfb3c3a318cfe70bb24f44b5ff8f9e/tensorflow/lite/kernels/activations.cc#L1003-L1005