Open suyan451 opened 2 months ago
self.layer1, self.layer2, self.layer3, self.layer4 = nn.Sequential(self.dinov2.blocks[:8]), nn.Sequential(self.dinov2.blocks[8:12]), nn.Sequential(self.dinov2.blocks[12:21]), nn.Sequential(self.dinov2.blocks[21:24])
When VRP encoder is DINOv2, how to define mid-level and high-level features?