Add SwinUNETR notebook and utilities for BraTS 2024 #418
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This commit introduces a new Jupyter Notebook (`SwinUNETR_BraTS2024.ipynb`) and associated utility scripts to adapt the SwinUNETR model for use with the BraTS 2024 dataset. Key components included: - `SwinUNETR/BRATS24/SwinUNETR_BraTS2024.ipynb`: The main notebook containing cells for dataset download (via Kaggle Hub), configuration, data loading, model initialization (SwinUNETR), and the training/validation loop. - `SwinUNETR/BRATS24/utils/data_utils_brats24.py`: Contains data loading and preprocessing functions, adapted from the BraTS 2021 version. Includes `get_loader` and a modified `datafold_read` to handle a flexible JSON structure. - `SwinUNETR/BRATS24/utils/trainer_brats24.py`: Contains the training and validation epoch logic (`run_training`, `train_epoch`, `val_epoch`), adapted from the BraTS 2021 version. - `SwinUNETR/BRATS24/generate_brats24_json.py`: A Python script to help you generate the `brats24_folds.json` file needed for defining dataset splits. This script requires you to modify it based on the actual downloaded BraTS 2024 dataset structure. - `SwinUNETR/BRATS24/jsons/`: Directory to store the `brats24_folds.json` file. What you need to do: 1. Run the initial cells of the notebook to download the dataset and identify its path and structure. 2. Update and run `generate_brats24_json.py` to create the dataset JSON file. 3. Configure `args.data_dir` and other relevant parameters in the notebook. 4. Verify and potentially adapt MONAI transforms in `data_utils_brats24.py` (especially `ConvertToMultiChannelBasedOnBratsClassesd`) for BraTS 2024 labels. 5. Execute the notebook to train the model.
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
for more information, see https://pre-commit.ci
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This commit introduces a new Jupyter Notebook (
SwinUNETR_BraTS2024.ipynb) and associated utility scripts to adapt the SwinUNETR model for use with the BraTS 2024 dataset.Key components included:
SwinUNETR/BRATS24/SwinUNETR_BraTS2024.ipynb: The main notebook containing cells for dataset download (via Kaggle Hub), configuration, data loading, model initialization (SwinUNETR), and the training/validation loop.SwinUNETR/BRATS24/utils/data_utils_brats24.py: Contains data loading and preprocessing functions, adapted from the BraTS 2021 version. Includesget_loaderand a modifieddatafold_readto handle a flexible JSON structure.SwinUNETR/BRATS24/utils/trainer_brats24.py: Contains the training and validation epoch logic (run_training,train_epoch,val_epoch), adapted from the BraTS 2021 version.SwinUNETR/BRATS24/generate_brats24_json.py: A Python script to help you generate thebrats24_folds.jsonfile needed for defining dataset splits. This script requires you to modify it based on the actual downloaded BraTS 2024 dataset structure.SwinUNETR/BRATS24/jsons/: Directory to store thebrats24_folds.jsonfile.What you need to do:
generate_brats24_json.pyto create the dataset JSON file.args.data_dirand other relevant parameters in the notebook.data_utils_brats24.py(especiallyConvertToMultiChannelBasedOnBratsClassesd) for BraTS 2024 labels.