tensorflow-yolov4-tflite icon indicating copy to clipboard operation
tensorflow-yolov4-tflite copied to clipboard
verified publisher icon hunglc007

Duplicated quantization flag assignment makes impossible to create a fully int8 quantized model

Open juandoso opened this issue 3 years ago • 0 comments

https://github.com/hunglc007/tensorflow-yolov4-tflite/blob/9f16748aa3f45ff240608da4bd9b1216a29127f5/convert_tflite.py#L39-L41

The second assignment to converter.target_spec.supported_ops supersedes the first that contains the int8 flag for full integer quantization

juandoso avatar May 22 '22 03:05 juandoso