ConvAddReLU2d

class torch.ao.nn.intrinsic.quantized.modules.conv_add.ConvAddReLU2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, padding_mode='zeros', device=None, dtype=None)

A ConvAddReLU2d module is a fused module of Conv2d, Add and Relu

We adopt the same interface as torch.ao.nn.quantized.Conv2d.

Variables:

torch.ao.nn.quantized.Conv2d (Same as) –

forward(input, extra_input)

Applies fused quantized Conv2d, addition, and ReLU.

classmethod from_float(mod, use_precomputed_fake_quant=False)

Creates a quantized module from a float module.

classmethod from_reference(ref_qconv, output_scale, output_zero_point)

Creates a quantized module from a reference module.