Conversation
ATATC
added
documentation
Open
Deploying mipcandy with
|
| Latest commit: |
9f84c88
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://02090d46.mipcandy.pages.dev |
| Branch Preview URL: | https://201.mipcandy.pages.dev |
…rk script's `frontend` parameter. (#133)
…ize functions to include `frontend` parameter. (#133)
This reverts commit 969ac67.
This reverts commit 67a9d81
… `revert_sliding_window()`, and `slide_dataset()` methods. (#192)
# Conflicts: # mipcandy/sliding_window.py
…rvisedSWDataset` classes, and updated related methods. (#192)
…indow` and new `SupervisedSWDataset`. Removed unused `roi` function. Improved device and dataset initialization logic. (#133)
…` in `benchmark.py`. Cleaned up unused imports and methods in `unet.py`. (#133)
…cessing in `benchmark.py`. (#133)
…sion compatibility. (#192)
…d` and `Pad3d`, enhancing 2D/3D shape handling. (#192)
…d` and `Pad3d`, enhancing 2D/3D shape handling. (#192)
…efactored `forward` method into `_forward` for reusability.
…` into `_SegmentationLoss` hierarchy; improved `validation_mode` handling, clarified `include_background` behavior, and optimized labels conversion logic.
…ed `if_empty` argument.
…Dataset` initialization, and adjusted `trainer.train` to add configurable options.
… removed unused preload code for training dataset.
…average dice score, ensured consistent handling of class-level dice metrics, and corrected loss formula for soft dice integration.
… `load_model`/`save_model`, updated method signatures, and improved logic for loading/compiling models during training and inference. (#133)
…d flexibility in metric comparison. (#133)
…ts` for `num_classes >= 3`, added logging for validation metrics, and removed unused loss override in UNetTrainer.
…2` for `DiceBCELossWithLogits`.
…global_previous_index` and fixed `diff` computation to handle edge cases with insufficient metric history.
…previous_index` handling in `diff` computation.
…ts; removed unused model compilation logic in training setup.
…nose low dice scores.
… to diagnose low dice scores." This reverts commit 8a16a1f.
…ic loading logic in dataset handling.
…w `DeepSupervisionWrapper`, target preparation logic, and updates to forward, backward, and validation workflows.
…nd dtype consistency.
… case handling, refined `convert_idx` logic, and reinstated `oversample_foreground` method. (#133)
…ss.validation_mode` dynamically.
…x_from_indices` and ensuring background classes are safely removed. Improved class selection in ROI sampling with weighted probabilities.
… in derived objects.
…eatmap` computation.
…ine model saving logic.
…emory usage during training.
…e counts and updated annotation generation logic for consistency.
…updated call sites accordingly, and adjusted annotation logic to handle 2D and 3D cases.
…undant logic and using uniform selection for classes.
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
See #133.