search

facebookresearch / dinov2

PyTorch code and models for the DINOv2 self-supervised learning method.
Apache License 2.0
9.19k stars 818 forks source link

Training pipeline of linear probing for semantic segmentation and depth estimation #361

Open ywyue opened 10 months ago

ywyue commented 10 months ago

Dear DINOv2 team, thank you for this amazing work! If I am correct, I only found the whole pipeline of linear probing for classification on ImageNet in https://github.com/facebookresearch/dinov2/blob/main/dinov2/eval/linear.py.

Is it possible for you to also release the training pipeline of linear probing for semantic segmentation (ADE20k, Cityscapes, Pascal VOC 2012) and depth estimation (NYU-Depth V2, KITTI, SUN-RGBD), including dataloader, data augmentation used, training schedule, etc? I believe this will serve as a standard testbed for follow-up works to compare with DINOv2 in a fair setup (i.e. excluding the effect of data augmentation, training schedule, etc). Thank you very much!

zshn25 commented 9 months ago

Hi, here's an unofficial training and testing pipeline of segmentation using mmsegmentation, based on the configs provided by the authors. The example implements Cityscapes but can be adopted to other datasets

https://github.com/zshn25/DINOv2_mmseg