facebookresearch / dino

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
Apache License 2.0
6.05k stars 885 forks source link

How to get the feature map by using pretrained model. #239

Open JiuqingDong opened 1 year ago

JiuqingDong commented 1 year ago

Hi, recently I try to use the DINO and DINOv2 pre-train model to get the feature map. I use the pre-trained model to get the feature, but only got a vector. It seems like the output of the last average pooling layer. Could you give me some suggestions to get the pyramid feature maps?

image