Skip to content

Issues: facebookresearch/Mask2Former

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

153 Open 80 Closed
153 Open 80 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

attn_mask[torch.where(attn_mask.sum(-1) == attn_mask.shape[-1])] = False
#249 opened Nov 11, 2024 by dawang-11
Does anyone know how to adjust the class_weight to a list for training on a dataset with extremely imbalanced label pixels?
#248 opened Sep 20, 2024 by jason60904yee
1
Custom Dataset structure guide on setting Class IDs and num_classes
#247 opened Sep 6, 2024 by niqbal996
how to understand predicting mask_embed using only query_feat
#246 opened Aug 7, 2024 by gaosanyuan
AP/AR result from the inference results.json in video instance segmentation
#245 opened Jul 30, 2024 by ZZzz-jh
Division by zero caused by mask operation
#243 opened Jul 28, 2024 by Chenyang-1024
Setup up for fine-tuning of mask2former for binary segmentation using low-rank adaptation
#242 opened Jul 25, 2024 by beschmitt
RuntimeError: d.is_cuda() INTERNAL ASSERT FAILED
#241 opened Jul 22, 2024 by wenboweiwb
How to train only the semantic segmentation weights of ade20k?
#240 opened Jun 18, 2024 by tms2003
Could you please let me know if anyone has successfully trained using the YouTube VIS 2021 dataset? How should the dataset be formatted?
#239 opened May 23, 2024 by Xinge-Zhou
How should I fix the input size during testing?
#238 opened May 20, 2024 by klkl2164
3
Custom dataset registration to use a model trained on Cityscapes for semantic segmentation.
#237 opened May 15, 2024 by arslanduygu
Mask loss with soft labels
#236 opened Apr 23, 2024 by antopost
Poor Output image quality
#235 opened Apr 11, 2024 by xuyuxiu83
Run in colab seems that there's a ModuleNotFoundError related to the MultiScaleDeformableAttention module.
#234 opened Mar 15, 2024 by henry7213
Using COCO for the dataset, what is the appropriate adjustment for learning rate if using a single GPU
#233 opened Mar 12, 2024 by KuKKiK9811
Prebuilt wheels provided via 3rd party repository
#232 opened Mar 11, 2024 by MiroPsota
1
difference among different mode
#231 opened Feb 17, 2024 by BuRr-Lee
loading swintransformer
#228 opened Feb 8, 2024 by BuRr-Lee
how use custom pre-trained backbone in mask2former
#226 opened Jan 18, 2024 by sleepat-11
1
batch_size doesn't affect evaluation
#225 opened Jan 14, 2024 by SuroshAhmadZobair
HAVE ANYONE MEET SUCH ERROR WHEN TRAINING ON OWN DATASET
#224 opened Dec 19, 2023 by lonelyqian
1
As for training, how long does it take?
#223 opened Dec 5, 2023 by zckcola
No module named 'MultiScaleDeformableAttention', Please compile MultiScaleDeformableAttention CUDA op
#222 opened Nov 16, 2023 by kanishkanarch
2
Using ground truth masks instead of the predicted ones
#221 opened Nov 9, 2023 by goncayilmaz
ProTip! What’s not been updated in a month: updated:<2024-10-17.