ConvRelu2d¶

class ConvRelu2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, conv_mode='cross_correlation', compute_mode='default', **kwargs)[源代码]¶: A QATModule include Conv2d and relu with QAT support. Could be applied with Observer and FakeQuantize.

Conv2d

ConvBn2d