Confusion in The Loss Function Implementation.

[bibhabasumohapatra]

    def forward_loss(self, imgs, pred, mask):
        """
        imgs: [N, 3, H, W]
        pred: [N, L, p*p*3]
        mask: [N, L], 0 is keep, 1 is remove, 
        """
        target = self.patchify(imgs)
        if self.norm_pix_loss:
            mean = target.mean(dim=-1, keepdim=True)
            var = target.var(dim=-1, keepdim=True)
            target = (target - mean) / (var + 1.e-6)**.5

        loss = (pred - target) ** 2
        loss = loss.mean(dim=-1)  # [N, L], mean loss per patch

        loss = (loss * mask).sum() / mask.sum()  # mean loss on removed patches
        return loss

    def forward(self, imgs, mask_ratio=0.75):
        latent, mask, ids_restore = self.forward_encoder(imgs, mask_ratio)
        pred = self.forward_decoder(latent, ids_restore)  # [N, L, p*p*3]
        loss = self.forward_loss(imgs, pred, mask)
        return loss, pred, mask

Why is the Loss being computed with the Prediction and the "Patchified" Image instead of Prediction and Original Input image.
By intuition Model can only learn from original Image