-
### Problem Description
NNEF tools updates
https://github.com/KhronosGroup/NNEF-Tools/tree/nnef-v1.0.0
### Operating System
ALL
### CPU
ALL
### GPU
AMD Instinct MI300
### Other
_No respons…
-
Khronos Neural Net Exchange Format ([NNEF](https://www.khronos.org/nnef)) is an open-source model format. It would be good to visualize these models using Netron.
[Tools](https://github.com/Khronos…
-
Hey
Are ANN classes available from the CLI? From the docs it isn't apparent.
How can we use it otherwise?
-
People have proposed adding a test to vet to catch certain unused errors. This can be very noisy, and there are many cases where the error is genuinely known to be nil and can be ignored, such as in a…
-
Running the Squeezenet ONNX model 1000 times using tract-onnx takes ~20 seconds on my machine. Running the same model using the Microsoft ONNX runtime in C++ takes about 9 seconds.
The output resul…
-
I currently have a simple TF Lite model which I successfully converted into an NNEF one using the conversion script from this repository. Now I would like to quantise the NNEF model (into a quantised …
-
TensorFlow C++ API is needed in the plugin, at the bare minimum, for its functionality to load models and generate predictions live during gameplay (aka model inference).
Update: While researchin…
-
hi,
I have a model in TFLite format which I quantized via "full integer quantization of weights and activations" under tensorflow-2.1 (https://www.tensorflow.org/model_optimization/guide/quantization…
-
Hello! I'm attempt to run the tflite model for MobileBert to do QA in tract (ultimately run it in WebAssembly). However, I've hit a snag trying to run the model and get the same outputs as tflite dire…
-
Hello
Attempting to convert a standard `transformer` model from `onnx` format to `nnef` format fails.
The model works as expected in `onnx` format when ran using `tract-onnx`.
Here is the com…