Inoutseg fix

[Hendrik-code]

No description provided.

[Copilot]

Pull request overview

This PR fixes issues with the in/out segmentation region selection logic and adds the mix_prob parameter to transform classes. The fix addresses the incorrect handling of multi-channel segmentation masks and reorders operations in transform application.

Changes:

• Fixed _apply_region_mode function to correctly handle multi-channel segmentation masks by using argmax before applying mode inversion
• Added mix_prob parameter to RandomInverseGPU and RandomHistogramEqualizationGPU classes
• Reordered operations in RandomConvTransformGPU to apply mix_prob mixing before region selection
• Updated configuration values for various transform parameters
• Code formatting improvements (trailing whitespace removal, function signature formatting)

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 4 comments.

File	Description
auglab/transforms/gpu/contrast.py	Fixed segmentation mask handling logic, added mix_prob parameter support, reordered transform operations
auglab/transforms/gpu/transforms.py	Added mix_prob parameter to transform instantiations, formatting improvements
auglab/configs/transform_params_gpu.json	Updated transform configuration parameters including probabilities and in_seg/out_seg values

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

The mix_prob operation is applied per batch element inside the loop, which means each batch item gets a different random alpha value. This differs from the RandomConvTransformGPU where mixing happens once for all batch elements. Consider whether this per-batch randomization is intentional or if consistency across transforms is desired.

[Hendrik-code]

@NathanMolinier that is actually a good question, what behavior do we want. We should be consistent.

[NathanMolinier]

Both are fine, and should have a similar impact onto the training. I would not worry too much on this

[Copilot]

The in_seg and out_seg values are set to 0 (integer) instead of 0.0 (float) for FunctionTransform, while all other transforms use float notation (0.0, 0.1, etc.). For consistency and to avoid potential type issues, use 0.0 for float values throughout the configuration.