ConvBn2d

class torch.nn.intrinsic.qat.ConvBn2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=None, padding_mode='zeros', eps=1e-05, momentum=0.1, freeze_bn=False, qconfig=None)

A ConvBn2d module is a module fused from Conv2d and BatchNorm2d, attached with FakeQuantize modules for weight, used in quantization aware training.

We combined the interface of torch.nn.Conv2d and torch.nn.BatchNorm2d.

Similar to torch.nn.Conv2d, with FakeQuantize modules initialized to default.

Variables:

• freeze_bn –

• weight_fake_quant – fake quant module for weight