ConvBnRelu2d

class ConvBnRelu2d(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)[源代码]

融合了 Conv2d, BatchNorm2dreluModule . 可以调用 quantize_qat 替换成 QATModule 型的 ConvBnRelu2d .