The Wayback Machine - https://web.archive.org/web/20211104044938/https://github.com/open-mmlab/mmsegmentation/issues
Skip to content

Pinned issues

Roadmap of MMSegmentation
#13 opened Jul 13, 2020 by hellock
Open 38
Correct English and Chinese document and add new features!
#679 opened Jul 7, 2021 by MengzhangLI
Open 3
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

80 Open 538 Closed
80 Open 538 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀
File "/mnt/lustre/menghao/anaconda3/envs/py37/lib/python3.7/site-packages/mmcv/image/geometric.py", line 242, in imrescale h, w = img.shape[:2] ValueError: not enough values to unpack (expected 2, got 0)
#1011 opened Nov 2, 2021 by MengHao666
1
How to get the pretrained data like demo
#1010 opened Nov 2, 2021 by Allenzhang97
@MengzhangLI
1
Faster dataloader on server which has IO bottleneck
#1008 opened Nov 2, 2021 by Dawn-bin
@MengzhangLI
1
would you like to add custom_hooks , user_defined hooks
#1001 opened Oct 27, 2021 by 459737087
@Junjun2016
6
Demo Doesn't work on Colab awaiting response
#997 opened Oct 26, 2021 by mavaylon1
1
[TensorRT] Is batching possible ? awaiting response
#976 opened Oct 19, 2021 by timothylimyl
@RunningLeon
12
Error report: Too many values to unpack (expected 2)
#970 opened Oct 16, 2021 by zhongqiu1245
2
Sampling points process in Pointrend awaiting response
#965 opened Oct 14, 2021 by MacavityT
@MengzhangLI
Eval always 'nan' when training on custom dataset awaiting response
#964 opened Oct 14, 2021 by xiangsanliu
@MengzhangLI
3
How to ignore background while calculating miou? awaiting response
#962 opened Oct 14, 2021 by silaopi
@MengzhangLI
TypeError: AdamW: __init__() got an unexpected keyword argument '_delete_' raise type(e)(f'{obj_cls.__name__}: {e}')
#961 opened Oct 14, 2021 by MengHao666
5
How to pass parameters awaiting response
#937 opened Oct 5, 2021 by jianlong-yuan
@MengzhangLI
7
How to print the best miou at each eval iteration during training ?
#924 opened Sep 29, 2021 by wusitong98
@Junjun2016 @xvjiarui
2
TracerWarning while Pytorch2ONNX conversion. 'Converting a tensor to a Python boolean might cause the trace to be incorrect.'. Deployment FAQ ONNX
#903 opened Sep 24, 2021 by pingguoyouzidaxigua
@MengzhangLI @RunningLeon
4
Non-mutually-exclusive Segmentation
#890 opened Sep 21, 2021 by zachcoleman
@MengzhangLI
3
Error in Cross entropy
#886 opened Sep 18, 2021 by jianlong-yuan
@MengzhangLI
1
I can convert ocrnet pytorch's model to onnx(tmp.onnx), however --verify shows that: outputs between tmp.onnx and pytorch model have big difference. Deployment FAQ ONNX
#881 opened Sep 17, 2021 by lyf6
@MengzhangLI @RunningLeon
2
result segmentation map is not showing the ignore_label awaiting response
#857 opened Sep 6, 2021 by MrOCW
@MengzhangLI
3
a question about data_time
#852 opened Sep 3, 2021 by h1063135843
2
How to export the model to a pt file that can be run on cudas? awaiting response
#817 opened Aug 24, 2021 by wj1017090777
@MengzhangLI
2
Multi-gpu training is taking longer than single-gpu training awaiting response
#816 opened Aug 24, 2021 by sprakashdash
@MengzhangLI
2
The Miou output during training is inconsistent with the Miou tested？swin_ base model
#811 opened Aug 23, 2021 by daigang896
@Junjun2016
4
pred_label and label mismatch errors occur when using multi-node multi-gpus bug
#767 opened Aug 9, 2021 by PeizeSun
@Junjun2016
14
With newest mmcv==1.3.10, text log bug bug
#758 opened Aug 6, 2021 by jianlong-yuan
@Junjun2016
4
The difference between the implementation of SETR and the official open source code
#721 opened Jul 25, 2021 by sixiaozheng
@sennnnn
3
ProTip! Add no:assignee to see everything that’s not assigned.