Method forward

models/birefnet.py:212–305

(self, features)

        return torch.cat(patches_batch, dim=0)

    def forward(self, features):
        if self.training and self.config.out_ref:
            outs_gdt_pred = []
            outs_gdt_label = []
            x, x1, x2, x3, x4, gdt_gt = features
        else:
            x, x1, x2, x3, x4 = features
        outs = []

        if self.config.dec_ipt:
            patches_batch = self.get_patches_batch(x, x4) if self.split else x
            x4 = torch.cat((x4, self.ipt_blk5(F.interpolate(patches_batch, size=x4.shape[2:], mode='bilinear', align_corners=True))), 1)
        p4 = self.decoder_block4(x4)
        m4 = self.conv_ms_spvn_4(p4) if self.config.ms_supervision else None
        if self.config.out_ref:
            p4_gdt = self.gdt_convs_4(p4)
            if self.training:
                # >> GT:
                m4_dia = m4
                gdt_label_main_4 = gdt_gt * F.interpolate(m4_dia, size=gdt_gt.shape[2:], mode='bilinear', align_corners=True)
                outs_gdt_label.append(gdt_label_main_4)
                # >> Pred:
                gdt_pred_4 = self.gdt_convs_pred_4(p4_gdt)
                outs_gdt_pred.append(gdt_pred_4)
            gdt_attn_4 = self.gdt_convs_attn_4(p4_gdt).sigmoid()
            # >> Finally:
            p4 = p4 * gdt_attn_4
        _p4 = F.interpolate(p4, size=x3.shape[2:], mode='bilinear', align_corners=True)
        _p3 = _p4 + self.lateral_block4(x3)

        if self.config.dec_ipt:
            patches_batch = self.get_patches_batch(x, _p3) if self.split else x
            _p3 = torch.cat((_p3, self.ipt_blk4(F.interpolate(patches_batch, size=x3.shape[2:], mode='bilinear', align_corners=True))), 1)
        p3 = self.decoder_block3(_p3)
        m3 = self.conv_ms_spvn_3(p3) if self.config.ms_supervision else None
        if self.config.out_ref:
            p3_gdt = self.gdt_convs_3(p3)
            if self.training:
                # >> GT:
                # m3 --dilation--> m3_dia
                # G_3^gt * m3_dia --> G_3^m, which is the label of gradient
                m3_dia = m3
                gdt_label_main_3 = gdt_gt * F.interpolate(m3_dia, size=gdt_gt.shape[2:], mode='bilinear', align_corners=True)
                outs_gdt_label.append(gdt_label_main_3)
                # >> Pred:
                # p3 --conv--BN--> F_3^G, where F_3^G predicts the \hat{G_3} with xx
                # F_3^G --sigmoid--> A_3^G
                gdt_pred_3 = self.gdt_convs_pred_3(p3_gdt)
                outs_gdt_pred.append(gdt_pred_3)
            gdt_attn_3 = self.gdt_convs_attn_3(p3_gdt).sigmoid()
            # >> Finally:
            # p3 = p3 * A_3^G
            p3 = p3 * gdt_attn_3
        _p3 = F.interpolate(p3, size=x2.shape[2:], mode='bilinear', align_corners=True)
        _p2 = _p3 + self.lateral_block3(x2)

        if self.config.dec_ipt:
            patches_batch = self.get_patches_batch(x, _p2) if self.split else x