Skip to content

Issues: milesial/Pytorch-UNet

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

Clear current search query, filters, and sorts
106 Open 344 Closed
106 Open 344 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

Add cpp inference project.(Msnhnet Engine)
#287 opened Aug 20, 2021 by msnh2012 updated Aug 20, 2021
mask preprocessing
#296 opened Sep 14, 2021 by soans1994 updated Sep 14, 2021
Cannot overfit net on a small training set
#165 opened Apr 23, 2020 by sptom updated Sep 29, 2021
35
How to resolve "KeyError: ((1, 1, 6), '|u1')"?
#299 opened Sep 27, 2021 by JenniferYingyiWu2020 updated Oct 27, 2021
3
How to resolve “KeyError: ((1, 1, 512), '|u1')”
#315 opened Nov 10, 2021 by felix2536449596 updated Nov 10, 2021
The predicted result graph cannot be visualized
#323 opened Dec 5, 2021 by heixinbaicaishang updated Dec 14, 2021
1
ValueError: not enough image data
#358 opened Apr 13, 2022 by lsm11111 updated Apr 13, 2022
RuntimeError: number of dims don't match in permute
#366 opened May 23, 2022 by 40618233 updated May 24, 2022
1
The generated mask graph is in the shape of [h, W, 3]. Now, the following data that only supports three-dimensional data appears using celoss. Does it need to convert the three-channel graph into one channel? Finally, do a dimensionality reduction to get the shape of [n, h, w] ?
#313 opened Nov 8, 2021 by gittjob updated Jun 10, 2022
8
File "/disk/sdc/shejiao/Pytorch-UNet-master/evaluate.py", line 19, in evaluate mask_true = F.one_hot(mask_true, net.n_classes).permute(0, 3, 1, 2).float() RuntimeError: number of dims don't match in permute
#367 opened May 29, 2022 by DonMuv updated Jun 17, 2022
1
Weird mask preprocessing side effect even without resizing
#387 opened Aug 27, 2022 by tmprgit updated Aug 28, 2022
训练出错RuntimeError: ACL stream synchronize failed.
#388 opened Aug 31, 2022 by xiaofei624 updated Aug 31, 2022
RuntimeError
#390 opened Sep 15, 2022 by nayenizhenmei updated Sep 15, 2022
how to convert VOC2012 SegmetionClass png file to this project train masks
#386 opened Aug 20, 2022 by futureflsl updated Oct 9, 2022
1
how to get miou and acc?
#302 opened Oct 3, 2021 by henbucuoshanghai updated Oct 30, 2022
2
ABOUT predict.py problem?
#384 opened Aug 3, 2022 by LINFF1023 updated Nov 5, 2022
2
Either no mask or multiple masks found for the ID
#312 opened Nov 5, 2021 by SkevyHoo updated Nov 9, 2022
6
RuntimeError: CUDA error: CUBLAS_STATUS_NOT_INITIALIZED when calling cublasCreate(handle) ？how to solve?---如何解决
#389 opened Sep 7, 2022 by ShakeWeLy updated Nov 24, 2022
2
how to get approximate value as the description Dice coefficient of 0.988423
#404 opened Nov 22, 2022 by sparkssjj updated Dec 6, 2022
1
RuntimeError: only batches of spatial targets supported (3D tensors) but got targets of size: : [1, 215, 245, 3]
#373 opened Jun 15, 2022 by 40618233 updated Dec 6, 2022
4
Training on mac mps instead of cuda
#393 opened Oct 4, 2022 by FlorisCalkoen updated Dec 7, 2022
2
The output image is strange : train.py or predict.py problem?
#407 opened Nov 30, 2022 by t19b205d updated Dec 7, 2022
3
IndexError: Target 255 is out of bounds.
#408 opened Dec 5, 2022 by mmmmyolo updated Dec 7, 2022
4
a problem in predict.py
#410 opened Dec 9, 2022 by Chen-qwer updated Dec 9, 2022
2
After training the model, how to save it into model.pth
#411 opened Dec 12, 2022 by dugurrn updated Dec 12, 2022
1
ProTip! What’s not been updated in a month: updated:<2024-12-30.