0

I have quantized ONNX model (exported from PyTorch). Is there any way to convert it to quantized TFLite model? It's important to apply quantization on the PyTorch side.

albert828
  • 50
  • 6
  • did you check - https://siliconlabs.github.io/mltk/mltk/tutorials/onnx_to_tflite.html – Vijay Mariappan Nov 24 '22 at 13:06
  • 1
    Yes, it doesn't work because OpenVino intermediate format uses FP32/FP16 precision. And with this approach, quantization is done at OpenVino -> TFLite conversion – albert828 Nov 24 '22 at 14:22

0 Answers0