tinynn/graph/quantization/qat_modules.py [210:248]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            input,
            self.weight_fake_quant(self.weight),
            self.bias,
            self.stride,
            self.padding,
            output_padding,
            self.groups,
            self.dilation,
        )

    @classmethod
    def from_float(cls, mod):
        r"""Create a qat module from a float module or qparams_dict

        Args: `mod` a float module, either produced by torch.quantization utilities
        or directly from user
        """
        assert type(mod) is cls._FLOAT_MODULE, (
            'qat.' + cls.__name__ + '.from_float only works for ' + cls._FLOAT_MODULE.__name__
        )
        assert hasattr(mod, 'qconfig'), 'Input float module must have qconfig defined'
        assert mod.qconfig, 'Input float module must have a valid qconfig'
        qconfig = mod.qconfig
        qat_conv = cls(
            mod.in_channels,
            mod.out_channels,
            mod.kernel_size,
            stride=mod.stride,
            padding=mod.padding,
            output_padding=mod.output_padding,
            groups=mod.groups,
            bias=mod.bias is not None,
            dilation=mod.dilation,
            padding_mode=mod.padding_mode,
            qconfig=qconfig,
        )
        qat_conv.weight = mod.weight
        qat_conv.bias = mod.bias
        return qat_conv
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tinynn/graph/quantization/qat_modules.py [321:359]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            input,
            self.weight_fake_quant(self.weight),
            self.bias,
            self.stride,
            self.padding,
            output_padding,
            self.groups,
            self.dilation,
        )

    @classmethod
    def from_float(cls, mod):
        r"""Create a qat module from a float module or qparams_dict

        Args: `mod` a float module, either produced by torch.quantization utilities
        or directly from user
        """
        assert type(mod) is cls._FLOAT_MODULE, (
            'qat.' + cls.__name__ + '.from_float only works for ' + cls._FLOAT_MODULE.__name__
        )
        assert hasattr(mod, 'qconfig'), 'Input float module must have qconfig defined'
        assert mod.qconfig, 'Input float module must have a valid qconfig'
        qconfig = mod.qconfig
        qat_conv = cls(
            mod.in_channels,
            mod.out_channels,
            mod.kernel_size,
            stride=mod.stride,
            padding=mod.padding,
            output_padding=mod.output_padding,
            groups=mod.groups,
            bias=mod.bias is not None,
            dilation=mod.dilation,
            padding_mode=mod.padding_mode,
            qconfig=qconfig,
        )
        qat_conv.weight = mod.weight
        qat_conv.bias = mod.bias
        return qat_conv
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -