nnUNet · Issues· 94 open
Open on GitHubLocally synced open issues (discussions stay on GitHub)
- #3069
[Feature Request]: tiff compression of saved predictions
enhancementUpdated Sep 16, 2026 - #3066
TypeError: nnUNetTrainer.__init__() takes from 5 to 6 positional arguments but 7 were given
questionUpdated Sep 11, 2026 - #3064
Race condition in nnUNetTrainer.do_split(): concurrent trainings can read a partially written splits_final.json
bugneeds-maintainerUpdated Sep 9, 2026 - #3063
Discussion: batched GPU data augmentation
Updated Sep 7, 2026 - #3050
Discussion: optional RankSEG-style decoding support for nnU-Net inference
Updated Aug 18, 2026 - #3056
--val --val_best fails when checkpoint_final is missing
bugneeds-maintainerUpdated Aug 4, 2026 - #3048
All classes climb to EMA pseudo-Dice ~0.06 by epoch ~55, then collapse back to ~0 by epoch 1000 (extremely sparse multi-class MRI)
Updated Jul 29, 2026 - #3055
ignore index included in foreground when calculating dataset fingerprint
bugneeds-maintainerUpdated Jul 19, 2026 - #3052
predict_from_raw_data.py __main__ block hardcodes Dataset004_Hippocampus (v2.8.1)
bugneeds-maintainerUpdated Jul 13, 2026 - #2787
The validation mask in validation and running an inference it's not similar
Updated Jul 13, 2026 - #3051
Segmentation fault (core dumped)
bugneeds-maintainerneeds-reproUpdated Jul 7, 2026 - #2571
Error when using DDP and deep_supervision=False
Updated Jun 22, 2026 - #2072
long time writing to disk
Updated Jun 15, 2026 - #3022
MedNeXt-v2 Resources
questionUpdated May 27, 2026 - #2963
CUDA Out of Memory during 3d_fullres inference on RTX 5090 (32 GB VRAM, Windows/WDDM)
Updated May 18, 2026