+1
Daily
9,043
stars
2,516
forks
83
watchers
290
prs
2,439
issues
4
releases
Top issues
#2115torch._dynamo.exc.BackendCompilerFailed: backend='inductor' raised: RuntimeError: Cannot find a working triton installation. More information on installing Triton can be found at https://github.com/openai/triton18 comments · 2024-04-20#2912[Bug] Validation fails with OOM on GPU and ArrayMemoryError on CPU fallback (nnU-Net v2, Windows 10, RTX 3060, 16GB RAM)12 comments · 2025-09-29#1942*RuntimeError: More than one of your folds has a prediction for case PETCT_PETCT_113_TP0.nii.gz**11 comments · 2024-02-08#2410Inconsistent Axis Order in `median_image_size_in_voxels` After Running `nnUNet_plan_and_preprocess` on Different Datasets8 comments · 2024-07-30#2361Training slows down when increasing batch size8 comments · 2024-07-10#2671Pickling issue- Can't pickle local object 'nnUNetTrainerV2.initialize_network.<locals>.<lambda>'6 comments · 2025-01-19#2986Advice on integrating custom intensity augmentation into nnU-Net5 comments · 2026-02-06#2735Training fails with TypeError: full() received an invalid combination of arguments5 comments · 2025-03-13
Discussions
#3070Question re multi-gpu training and torch seeding1 comments · 2026-09-21#3061Converting clinical DICOM into an nnU-Net-ready dataset (Med-ImageNet)0 comments · 2026-08-26#2987Custom epoch num AND L-R mirroring off1 comments · 2026-02-08#2978loss functıon0 comments · 2026-01-21#2977LOSS FUNC.0 comments · 2026-01-21#2946Dimension mismatch during validation between ground truth data and predictions0 comments · 2025-11-22#2915Question about (to me) weird line used when exporting segmentation w `LabelManager`1 comments · 2025-10-02#2907Fingerprinting with ignore label1 comments · 2025-09-16
Latest release
Residual Encoder UNets released! v2.4.1 2024-04-21See documentation :-)