Sachini Wickramasinghe comments

Repositories
Issues
Comments

Results 1 comments of


                                            Sachini Wickramasinghe

Quantized ONNX Model Still Has Float32 Input/Output Tensors

Hi, I am performing INT16 post training quantization (W16A16) on a model using the ONNX runtime static quantization function. I am using the QDQ format since INT16 is only supported...