ConvBn2d

class ConvBn2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, conv_mode='cross_correlation', compute_mode='default', eps=1e-05, momentum=0.9, affine=True, track_running_stats=True, padding_mode='zeros', **kwargs)

A fused Module including Conv2d and BatchNorm2d. Could be replaced with QATModule version ConvBn2d using quantize_qat.

previous

ConvRelu2d

next

ConvBnRelu2d