Method forward

src/models/resnet.py:51–83

(self, hidden_states, output_size=None)

            self.conv = InflatedConv3d(self.channels, self.out_channels, 3, padding=1)

    def forward(self, hidden_states, output_size=None):
        assert hidden_states.shape[1] == self.channels

        if self.use_conv_transpose:
            raise NotImplementedError

        # Cast to float32 to as 'upsample_nearest2d_out_frame' op does not support bfloat16
        dtype = hidden_states.dtype
        if dtype == torch.bfloat16:
            hidden_states = hidden_states.to(torch.float32)

        # upsample_nearest_nhwc fails with large batch sizes. see https://github.com/huggingface/diffusers/issues/984
        if hidden_states.shape[0] >= 64:
            hidden_states = hidden_states.contiguous()

        # if `output_size` is passed we force the interpolation output
        # size and do not make use of `scale_factor=2`
        if output_size is None:
            hidden_states = F.interpolate(
                hidden_states, scale_factor=[1.0, 2.0, 2.0], mode="nearest"
            )
        else:
            hidden_states = F.interpolate(
                hidden_states, size=output_size, mode="nearest"
            )

        # If the input is bfloat16, we cast back to bfloat16
        if dtype == torch.bfloat16:
            hidden_states = hidden_states.to(dtype)

        hidden_states = self.conv(hidden_states)

        return hidden_states


class Downsample3D(nn.Module):