[go: nahoru, domu]
Skip to content

Issues: lucidrains/vit-pytorch

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

121 Open 138 Closed
121 Open 138 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

Fine-tuning without loading position embedding from pre-trained model
#188 opened Jan 2, 2022 by Blosslzy
Vit MAE reconstruction size mismatch
#187 opened Dec 30, 2021 by RhinigtasSalvex
2
where is the train.py? tks
#185 opened Dec 30, 2021 by henbucuoshanghai
2
Training in cifar100
#182 opened Dec 22, 2021 by xinchenduobian
1
Hot to get the features and positional embeddig information
#180 opened Dec 16, 2021 by marcomameli1992
4
mae output normal size images
#179 opened Dec 16, 2021 by yzb1997
1
Vision Transformers for Federated Learning use-cases
#176 opened Dec 2, 2021 by alexey-gruzdev
MAE decoder pos_emb
#175 opened Nov 30, 2021 by dnecho
3
Vit3D for Brain CTscans
#174 opened Nov 26, 2021 by Meddebma
6
MAE image recon
#169 opened Nov 17, 2021 by chokyungjin
9
ViT-Dino for Medical images
#166 opened Nov 2, 2021 by Mushtaqml
2
Recorder - DataParallel issue
#165 opened Oct 28, 2021 by samansarraf
Removing FC layer at the top of the transformer model
#164 opened Oct 9, 2021 by loukasilias
2
when running the example notebook::TypeError: 'encoding' is an invalid keyword argument for this function
#163 opened Oct 8, 2021 by monajalal
Delete Issue
#160 opened Oct 1, 2021 by nsriniva03
Loading pretrained weights from Ross image repository
#158 opened Sep 22, 2021 by DegardinBruno
Training DINO
#154 opened Sep 2, 2021 by cmartin-isla
4
Training vit on Imagenet 1k got bad performance.
#152 opened Aug 31, 2021 by songlei00
2
ViT + ResNet
#149 opened Aug 29, 2021 by khawar-islam
PIT varriant
#148 opened Aug 24, 2021 by abhigoku10
Memory usage
#143 opened Aug 19, 2021 by gerben-b
1
training vit with 12channel image
#137 opened Aug 2, 2021 by sukkyusun1
1
how to deal with the situation when the patch size is not square?
#136 opened Jul 23, 2021 by wangyk55
Train with new datasets
#133 opened Jul 19, 2021 by Jeba-create
1
Ask for help: How to use multi GPUs? All input tensors must be on the same device. Received cuda:3 and cuda:2
#131 opened Jul 8, 2021 by starrywintersky
4
ProTip! Follow long discussions with comments:>50.