Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mkurman/nnunet
No New U-Net — self-configuring framework for medical image segmentation. Automatically adapts to any dataset. Top performer on biomedical segmentation benchmarks (BraTS, KiTS, etc.).
Passed 20 of 22 test cases with the skill, and 19 of 22 without it.
1 fixed19 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
A test case the skill fixed. Same model, same prompt, with and without the skill.
I have a medical dataset (dataset ID 501) prepared for nnUNet v2. Could you share the bash commands required to execute the automatic planning and preprocessing step with the default planner, followed by starting fold 0 training in 3D full resolution?
| Checked | Without skill | With skill |
|---|---|---|
| Includes the -pl nnUNetPlanner parameter in the preprocessing command | Missed | Passed |
| Specifies 3d_fullres and fold 0 in the training command | Passed | Passed |
The instructions your model reads when the skill loads.
nnUNet (No New U-Net) is a self-configuring framework for medical image segmentation that automatically adapts to any dataset. Consistently top-performing on benchmarks like BraTS, KiTS, and AMOS.
uv pip install nnunetv2
nnUNetv2_plan_and_preprocess -d DATASET_ID -pl nnUNetPlanner
nnUNetv2_train DATASET_ID CONFIG 0 # CONFIG: 2d, 3d_fullres, 3d_lowres
nnUNetv2_predict -i INPUT_FOLDER -o OUTPUT_FOLDER -d DATASET_ID -c CONFIG
from nnunetv2.inference.predict_from_raw_data import nnUNetPredictor
predictor = nnUNetPredictor()
predictor.initialize_from_trained_model_folder("nnUNet_results/DatasetXYZ", "3d_fullres")
predictor.predict_from_files("input_images", "output_segmentations")
test cases passed, vs 19 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.