QuantizedConvTranspose2d¶

class aimet_torch.nn.QuantizedConvTranspose2d(*args, **kwargs)[source]¶

Quantized subclass of torch.nn.ConvTranspose2d

forward(self, input: torch.Tensor, output_size: List[int] | None = None) → torch.Tensor

Quantized forward of torch.nn.ConvTranspose2d.

The input(s), parameter(s) (if any), and output(s) will be quantized with self.input_quantizers, self.param_quantizers, and self.output_quantizers respectively.

For more information, see QuantizationMixin.