why the scale and zero_point not update in Learnablefakequantize? I used different methods to quantize the yolov5

[buzhou1]

` kwargs = { 'input_shape_dict': {'data': [1, 3, opt.imgsz, opt.imgsz]}, 'output_path': output_dir, 'model_name': model_name, 'dummy_input': None, 'onnx_model_path': os.path.join(output_dir, '{}_ori.onnx'.format(model_name)), } module_tmp = copy.deepcopy(model) module_tmp = module_tmp.cpu() convert_onnx(module_tmp.eval(), **kwargs) del module_tmp model = model.train()

exit(0)

backend = BackendType.Tensorrt
if opt.quantize:
    prepare_custom_config_dict= {
        'extra_qconfig_dict':{'w_fakequantize':'LearnableFakeQuantize'},
        'concrete_args':{'augment_1':False, 'profile_1':False, 'visualize_1':False}
    } 

    # print('named_modules:', dict(model.named_modules())[''])
    model.train()
    model = model.to(device)
    model = prepare_by_platform(model, backend, prepare_custom_config_dict)
    # print('prepared module:', model)
    enable_calibration(model)
    calibration_flag = True
    model = model.to(device)`

I didn't change outher code

[buzhou1]

This is the onnx scale parameters about 1st(left) and 4th(right) for LearnableFakequantize ,they are same

[Tracin]

Check if scales are in your Optimizer.

[buzhou1]

thanks！ now the parameters can upgrade

[github-actions[bot]]

This issue has not received any updates in 120 days. Please reply to this issue if this still unresolved!