File size: 542 Bytes
c2634fd 2c670e9 c2634fd 2c670e9 c2634fd 2c670e9 |
1 2 3 4 5 6 7 8 9 10 |
---
library_name: keras
---
This model is a TensorFlow port of DINO ViT B-16 [1]. The backbone of this model was pre-trained using the DINO pretext task. After that its head layer was trained
by keeping the backbone frozen. ImageNet-1k was used for training purposes. You can refer to [this notebook](https://github.com/sayakpaul/probing-vits/blob/main/notebooks/load-dino-weights-vitb16.ipynb) to know how the porting was done.
## References
[1] Emerging Properties in Self-Supervised Vision Transformers: https://arxiv.org/abs/2104.14294 |