def forward()

in sam2/modeling/position_encoding.py [0:0]

• 31 lines of code
• 3 McCabe index (conditional complexity)

    def forward(self, x: torch.Tensor):
        cache_key = (x.shape[-2], x.shape[-1])
        if cache_key in self.cache:
            return self.cache[cache_key][None].repeat(x.shape[0], 1, 1, 1)
        y_embed = (
            torch.arange(1, x.shape[-2] + 1, dtype=torch.float32, device=x.device)
            .view(1, -1, 1)
            .repeat(x.shape[0], 1, x.shape[-1])
        )
        x_embed = (
            torch.arange(1, x.shape[-1] + 1, dtype=torch.float32, device=x.device)
            .view(1, 1, -1)
            .repeat(x.shape[0], x.shape[-2], 1)
        )

        if self.normalize:
            eps = 1e-6
            y_embed = y_embed / (y_embed[:, -1:, :] + eps) * self.scale
            x_embed = x_embed / (x_embed[:, :, -1:] + eps) * self.scale

        dim_t = torch.arange(self.num_pos_feats, dtype=torch.float32, device=x.device)
        dim_t = self.temperature ** (2 * (dim_t // 2) / self.num_pos_feats)

        pos_x = x_embed[:, :, :, None] / dim_t
        pos_y = y_embed[:, :, :, None] / dim_t
        pos_x = torch.stack(
            (pos_x[:, :, :, 0::2].sin(), pos_x[:, :, :, 1::2].cos()), dim=4
        ).flatten(3)
        pos_y = torch.stack(
            (pos_y[:, :, :, 0::2].sin(), pos_y[:, :, :, 1::2].cos()), dim=4
        ).flatten(3)
        pos = torch.cat((pos_y, pos_x), dim=3).permute(0, 3, 1, 2)
        self.cache[cache_key] = pos[0]
        return pos