文件mylayer.py中，定义了myconv

def MyConv(nn.Module): ... def forward(): ...

训练代码中，

extra_config = { 'extra_qconfig_dict': { 'w_observer': 'MSEObserver', # custom weight observer 'a_observer': 'MSEObserver', # custom activation observer 'w_fakequantize': 'AdaRoundFakeQuantize', # custom weight fake quantize function 'a_fakequantize': 'FixedFakeQuantize', # custom activation fake quantize function 'w_qscheme': { 'bit': 8, # custom bitwidth for weight, 'symmetry': False, # custom whether quant is symmetric for weight, 'per_channel': True, # custom whether quant is per-channel or per-tensor for weight, 'pot_scale': True, # custom whether scale is power of two for weight. 'p': 2.4 }, 'a_qscheme': { 'bit': 8, # custom bitwidth for activation, 'symmetry': False, # custom whether quant is symmetric for activation, 'per_channel': True, # custom whether quant is per-channel or per-tensor for activation, 'pot_scale': False, # custom whether scale is power of two for activation. 'p': 2.4 } }, 'extra_quantizer_dict': {

'additional_function_type': [operator.add,], # additional function type, a list, use function full name, like operator.add.

    'additional_module_type': (MyConv, ),            # additional module type, a tuple, use class full name, like torch.nn.Upsample.
    # 'additional_node_name': [layer1_1_conv1] ,                # addition node name, a list, use full node name, like layer1_1_conv1.

},

}

...

myModel = prepare_by_platform(myModel, BackendType.Academic, extra_config)

但是print(myModel)后，发现MyConv并没有被替换，怎么办？谢谢

ModelTC / MQBench

如何添加定制的conv #261

'additional_function_type': [operator.add,], # additional function type, a list, use function full name, like operator.add.