Method get_fold_unfold

ldm/models/diffusion/ddpm.py:722–772

:param x: img of size (bs, c, h, w) :return: n img crops of size (n, bs, c, kernel_size[0], kernel_size[1])

(self, x, kernel_size, stride, uf=1, df=1)

        return weighting

    def get_fold_unfold(self, x, kernel_size, stride, uf=1, df=1):  # todo load once not every time, shorten code
        """
        :param x: img of size (bs, c, h, w)
        :return: n img crops of size (n, bs, c, kernel_size[0], kernel_size[1])
        """
        bs, nc, h, w = x.shape

        # number of crops in image
        Ly = (h - kernel_size[0]) // stride[0] + 1
        Lx = (w - kernel_size[1]) // stride[1] + 1

        if uf == 1 and df == 1:
            fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
            unfold = torch.nn.Unfold(**fold_params)

            fold = torch.nn.Fold(output_size=x.shape[2:], **fold_params)

            weighting = self.get_weighting(kernel_size[0], kernel_size[1], Ly, Lx, x.device).to(x.dtype)
            normalization = fold(weighting).view(1, 1, h, w)  # normalizes the overlap
            weighting = weighting.view((1, 1, kernel_size[0], kernel_size[1], Ly * Lx))

        elif uf > 1 and df == 1:
            fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
            unfold = torch.nn.Unfold(**fold_params)

            fold_params2 = dict(kernel_size=(kernel_size[0] * uf, kernel_size[0] * uf),
                                dilation=1, padding=0,
                                stride=(stride[0] * uf, stride[1] * uf))
            fold = torch.nn.Fold(output_size=(x.shape[2] * uf, x.shape[3] * uf), **fold_params2)

            weighting = self.get_weighting(kernel_size[0] * uf, kernel_size[1] * uf, Ly, Lx, x.device).to(x.dtype)
            normalization = fold(weighting).view(1, 1, h * uf, w * uf)  # normalizes the overlap
            weighting = weighting.view((1, 1, kernel_size[0] * uf, kernel_size[1] * uf, Ly * Lx))

        elif df > 1 and uf == 1:
            fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
            unfold = torch.nn.Unfold(**fold_params)

            fold_params2 = dict(kernel_size=(kernel_size[0] // df, kernel_size[0] // df),
                                dilation=1, padding=0,
                                stride=(stride[0] // df, stride[1] // df))
            fold = torch.nn.Fold(output_size=(x.shape[2] // df, x.shape[3] // df), **fold_params2)

            weighting = self.get_weighting(kernel_size[0] // df, kernel_size[1] // df, Ly, Lx, x.device).to(x.dtype)
            normalization = fold(weighting).view(1, 1, h // df, w // df)  # normalizes the overlap
            weighting = weighting.view((1, 1, kernel_size[0] // df, kernel_size[1] // df, Ly * Lx))

        else:
            raise NotImplementedError

        return fold, unfold, normalization, weighting

    @torch.no_grad()
    def get_input(self, batch, k, return_first_stage_outputs=False, force_c_encode=False,