Repository Issue Activity (beta)

#3063 Discussion: batched GPU data augmentation

#3050 Discussion: optional RankSEG-style decoding support for nnU-Net inference

#2442 Title: KeyError: '1'

#3056 --val --val_best fails when checkpoint_final is missing

#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)

#1956 Mismatched orientation of predicted segmentation

#3055 ignore index included in foreground when calculating dataset fingerprint

#3054 Segmentation with organ information

#3052 predict_from_raw_data.py __main__ block hardcodes Dataset004_Hippocampus (v2.8.1)

#3025 [Feature request] Improve support for custom trainers (to no longer require forking/modifying `nnunetv2`)

#2787 The validation mask in validation and running an inference it's not similar

#3051 Segmentation fault (core dumped)

#2653 questions and issues regarding training with nnUNetPlannerResEncL on BraTS2023

#3044 EOF Error/multiprocessing error?

#3046 foldall 和 fold 0 区别是什么

#310 Segmentation fault (core dumped)

#2988 Parallel fold training crashes on Apple Silicon (M2, MPS backend) but single-fold training works

#2571 Error when using DDP and deep_supervision=False

#1948 RGB png dataset bechmarking

#1804 How to make weights to decrease from 1 to 0 as the epoch increases?

#2005 How can i use pretrained model that was made by fine tunning

#2085 Low GPU Utilization on RTX 4090

#2186 Predicting next stage 3d_cascade_fullres failed for case 0011 because the preprocessed file is missing! Run the preprocessing for this configuration first!

#2263 2D nnUNet predicting only one class

#2323 Validation data stuck halfway through