Skip to content

Issues: facebookresearch/dino

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

97 Open 150 Closed
97 Open 150 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Changing number of classes
#282 opened Jul 31, 2024 by vikashg
Reproducing results on segmentation using training from scratch
#281 opened Jul 22, 2024 by sonamsingh19
Cannot reproduce KNN performance for vanilla ViT-S training
#280 opened Jun 28, 2024 by wangh09
1
Can I use dino model to match images with pixels? Just like with the clip model you can match pixels with text.
#278 opened May 21, 2024 by dajiebi
1
How to convert to onnx
#276 opened May 2, 2024 by Ochre-amber
2
Why Teacher network perform bettert than Student one during training?
#274 opened Apr 9, 2024 by Hongbo-Z
1
Loss is not decresing
#273 opened Mar 7, 2024 by risingClouds
4
Best features for image similarity
#272 opened Mar 6, 2024 by fbliman
1
a solution to solve memory issues (but slows down training a bit)
#269 opened Dec 27, 2023 by fawazsammani
Why do we skip cases where the student and teacher operate on the same view? If they are operating on different views, why should they produce similar results to calculate the cross-entropy loss?
#267 opened Dec 12, 2023 by jinghere11
1
For large batches (256), there is a problem of loss non convergence
#265 opened Dec 6, 2023 by Elijah-Yi
Difference between DINO and DINOv2
#264 opened Nov 21, 2023 by Tulsishah
Loss Nan Error
#263 opened Nov 15, 2023 by Elijah-Yi
Why the patchembedding defaut img size is not equal to the image size in visualize attention?
#261 opened Nov 9, 2023 by LWShowTime
1
Facing Accuracy Drop while running in QDQ onnx runtime
#260 opened Nov 8, 2023 by akarshit15092000
Intermediate checkpoints?
#259 opened Nov 6, 2023 by ghost
Hyperparameters for ViT-B/16 + ImageNet pretraining
#255 opened Oct 2, 2023 by kalyani7195
The averaged learning rate in log.txt
#254 opened Sep 22, 2023 by haohang96
Image resolution at intermediate layers?
#252 opened Sep 12, 2023 by yousafe007
3
problem when trying to finetune a model, using resnet50 backbone
#251 opened Sep 8, 2023 by saeidrazavi
1
Linear Evaluation LR Sweep Values
#249 opened Aug 1, 2023 by ferreirafabio
2
dinohead weight normalized
#248 opened Jul 6, 2023 by kffeng
Faster training
#247 opened Jun 9, 2023 by rbareja25
2
Loss doesn't decrease
#246 opened Jun 1, 2023 by AwayFromKeyboardwarrior
6
How to use teacher weights?
#245 opened May 24, 2023 by zahrasa
ProTip! Type g i on any issue or pull request to go back to the issue listing page.