ConvReLU2d

class torch.ao.nn.intrinsic.qat.modules.conv_fused.ConvReLU2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, padding_mode='zeros', qconfig=None)

A ConvReLU2d module is a fused module of Conv2d and ReLU, attached with FakeQuantize modules for weight for quantization aware training.

We combined the interface of Conv2d and BatchNorm2d.

Variables:

weight_fake_quant – fake quant module for weight

forward(input)

Performs forward pass through fused Conv2d and ReLU.

classmethod from_float(mod, use_precomputed_fake_quant=False)

Creates a QAT module from a floating point module.