tflite-micro
tflite-micro copied to clipboard
tensorflow
Infrastructure to enable deployment of ML models to low-power resource-constrained embedded targets (including microcontrollers and digital signal processors).
An issue to track the implementation of model compression. ### Queue The [commits along the branch rkuester/compress-next](https://github.com/tensorflow/tflite-micro/compare/main...rkuester:tflite-micro:compress-next) are queued, so to speak, for submission via PRs. ### Integration Use the...
Hello, recently I encountered an issue when deploying the model from [YOLO-World](https://github.com/AILab-CVC/YOLO-World) to a device using TFLM. I found that with the same INT8 per-channel quantized TFLite model and using...
I need to compile the hello world sample in an offline environment，what dependencies do I need to download in advance？
Hi! I'm currently trying to compile a tensorflow lite model _model_2.tflite_ for edge TPU, but I'm getting the error: ``` Edge TPU Compiler version 16.0.384591198 ERROR: Didn't find op for...
In tensorflow/lite/micro/kernels/cmsis_nn/depthwise_conv.cc the variable per_channel_output_multiplier is only initialized (line 96) for Int8 network leading to a crash if the passed network is UInt8 I propose to return an error when...
I'd like to propose a feature to allow the interpreter to use more than one tensor arena. The use case is as follows: the platform running the interpreter has more...
Hi, I am currently trying to make a large model (YOLO) run on the ESP32-S3 (and later the P4), and since the model (> 2MB) doesn't fit in SRAM and...
On a project I'm working on, we have a dependency both on [tensorflow](https://github.com/tensorflow/tensorflow) and [tflite-micro](https://github.com/tensorflow/tflite-micro). We recently had an issue due to duplicated namespaces in the workspace, i.e. both tensorflow...
Hello everyone, In the issue [Can this be done in TFLM](https://github.com/tensorflow/tflite-micro/issues/2478), it was mentionned that the kernels `Rfft2d` and `ComplexAbs` were not supported by TFLM. (kernels used in tflite for...
Metadata
Owner
Metadata
Infrastructure to enable deployment of ML models to low-power resource-constrained embedded targets (including microcontrollers and digital signal processors).