seamseg/algos/fpn.py [165:179]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self.canonical_scale = canonical_scale
        self.canonical_level = canonical_level
        self.roi_size = roi_size
        self.min_level = min_level
        self.levels = levels

    def _target_level(self, boxes):
        scales = (boxes[:, 2:] - boxes[:, :2]).prod(dim=-1).sqrt()
        target_level = torch.floor(self.canonical_level + torch.log2(scales / self.canonical_scale + 1e-6))
        return target_level.clamp(min=self.min_level, max=self.min_level + self.levels - 1)

    def _rois(self, x, proposals, proposals_idx, img_size):
        stride = proposals.new([fs / os for fs, os in zip(x.shape[-2:], img_size)])
        proposals = (proposals - 0.5) * stride.repeat(2) + 0.5
        return roi_sampling(x, proposals, proposals_idx, self.roi_size)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



seamseg/algos/fpn.py [299:313]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self.canonical_scale = canonical_scale
        self.canonical_level = canonical_level
        self.roi_size = roi_size
        self.min_level = min_level
        self.levels = levels

    def _target_level(self, boxes):
        scales = (boxes[:, 2:] - boxes[:, :2]).prod(dim=-1).sqrt()
        target_level = torch.floor(self.canonical_level + torch.log2(scales / self.canonical_scale + 1e-6))
        return target_level.clamp(min=self.min_level, max=self.min_level + self.levels - 1)

    def _rois(self, x, proposals, proposals_idx, img_size):
        stride = proposals.new([fs / os for fs, os in zip(x.shape[-2:], img_size)])
        proposals = (proposals - 0.5) * stride.repeat(2) + 0.5
        return roi_sampling(x, proposals, proposals_idx, self.roi_size)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -