Skip to content

Issues: hustvl/SparseInst

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

51 Open 67 Closed
51 Open 67 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

Could you tell me where can I find the code for multiplying the DICE loss with the classification score that you mentioned in your paper?
#128 opened Oct 10, 2024 by Run-19
loss_mask:nan
#126 opened Dec 6, 2023 by Zhounjau
When running train_net.py, an error occurs.
#125 opened Aug 22, 2023 by kirorotarzan
training details
#124 opened Aug 10, 2023 by lsm140
2
I think the performance of your model is not as high as Condinst
#123 opened Jul 4, 2023 by Originlightwkp
Single kernel crossponding to multiple object
#122 opened Jun 26, 2023 by Lincoln12w
Is lightweight backbone like mobilenet available in the future?
#121 opened May 29, 2023 by wooAo
1
RuntimeWarning: invalid value encountered in intersection
#120 opened May 13, 2023 by zyqdragon
Why init weights like that?
#119 opened May 13, 2023 by leftthomas
hyper-parameters not same with paper
#118 opened May 13, 2023 by leftthomas
train on cocodataset ( AP is so low )
#117 opened Apr 10, 2023 by Wooho-Moon
2
error in training by using voc2012
#116 opened Apr 5, 2023 by 116022017144
About experiments on Cityscapes
#115 opened Apr 4, 2023 by cici-999
Please help to get started with COCO-style custom datasets and classes
#114 opened Mar 23, 2023 by thusinh1969
关于样本分配的顺序问题（或者说训练为什么可以收敛？）
#113 opened Mar 22, 2023 by feiyuhuahuo
1
APs is nan
#112 opened Mar 17, 2023 by 18219716332
关于可视化IAM的问题
#111 opened Mar 9, 2023 by GTrui6
5
这个文件/root/anaconda3/envs/sparse/lib/python3.7/site-packages/fvcore/transforms/transform.py对polygon数据的处理是怎么样的
#110 opened Feb 27, 2023 by 116022017144
[Checkpointer] Loading from pretrained_models/resnet50d_ra2-464e36ba.pth fvcore.common.checkpoint WARNING: Some model parameters or buffers are not found in the checkpoint:
#109 opened Feb 20, 2023 by 116022017144
在COCO数据集上使用sparse_inst_r50vd_dcn_giam_aug.yaml重头训练，精度并没有达到37.9，低了十几个点
#108 opened Feb 16, 2023 by 116022017144
2
demo.py error
#105 opened Dec 26, 2022 by Xuying2000
1
在COCOTrain2017数据集训练，Val2017测试的AP是27.00，为什么这么低呢?
#103 opened Dec 8, 2022 by 1032697379
4
Output Resolution
#102 opened Dec 7, 2022 by marcown
1
different results between ONNX model and pt model
#101 opened Dec 7, 2022 by zoey9628
2
Bug of demo.py
#100 opened Dec 4, 2022 by leftthomas
3
ProTip! no:milestone will show everything without a milestone.