ConvTranspose2d

class ConvTranspose2d(in_channels, out_channels, kernel_size, stride=1, padding=0, output_padding=0, dilation=1, groups=1, bias=True, conv_mode='cross_correlation', compute_mode='default', **kwargs)

A QATModule ConvTranspose2d with QAT support. Could be applied with Observer and FakeQuantize.

classmethod from_float_module(float_module)

Return a QATModule instance converted from a float Module instance.

previous

ConvBnRelu2d

next

BatchMatMulActivation