ancestor-mithril

Labelme.exe is malicious

1

### Provide environment information nope ### What OS are you using? windows ### Describe the Bug   ### Expected Behavior _No response_ ### To Reproduce Download Labelme.exe from the...

Improving performance of batchgenerators

3

Thanks you for your work, this is a nice tool for augmenting 3d images. My changes come to improve the performance speed of various methods, to reduce the cpu time...

Adding tests

1

Some tests against the `sklearn`'s k-means and some performance tests would be helpful when contributing.

Readme example results in `TypeError`

1

The example in documentation results in an error with `TotalSegmentator==2.1.0` ```py import nibabel as nib from totalsegmentator.python_api import totalsegmentator if __name__ == "__main__": # option 2: provide input and output...

* reducing the number of allocations when reading images and writing segmentations * segmentation are casted to np.uint8 only if they are not already np.uint8 * images are stacked directly...

New feature: adding a parameter to control the number of processes used by the validation dataloader

2

## Motivation Many nnUNet users try to run it on systems in which the hardware is lacking (there are many users reporting `Some background worker is 6 feet under`). Currently,...

New feature: adding a parameter to control the number of pseudo-validation cases

2

This feature allows to do fewer iterations of pseudo-validation instead of 50, allowing for faster training or more confident pseudo-validation score, depending on the needs of each experiment. It also...

Does reorientation matter?

2

When training nnUNet on data using 2 different orientations, does it matter if I use `SimpleITKIO` or should I use `NibabelIOWithReorient`? When looking at dataset conversion scripts, https://github.com/MIC-DKFZ/nnUNet/blob/master/nnunetv2/dataset_conversion/Dataset219_Amos2022_task2.py uses NibabelIOWithReorient,...