torchio

torchio copied to clipboard

Fix non-shuffling Queue minibatch pop order

1

Fixes #938. **Description** Fixed mini-batch sampling order when the `shuffle_subjects` is set to `False` for `tio.Queue`. Added a test case to verify this change. **Checklist** - [x] I have read...

alabamagan

Getting mini-batch from queue results in reverse order for non-shuffling queue

4

### Is there an existing issue for this? - [X] I have searched the existing issues ### Problem summary When iterating mini-batches in a queue without shuffling, I expected the...

alabamagan

Unload image

4

**🚀 Feature** Possibility to "unload" an image to save memory **Motivation** When working with huge datasets, it can easily happen that one runs out of memory. To avoid this, it...

justusschock

Repr should not load the image

5

**🚀 Feature** Changing the way `__repr__` gives an representation of the image. **Motivation** Debuggers call `__repr__` to give a preview of the python object. **Pitch** When having torchio Images that...

justusschock

Histogram standardization changes image shape after transformation

4

### Is there an existing issue for this? - [X] I have searched the existing issues ### Bug summary So I am learning landmarks and applyiong for the dataset TCIA...

kondratevakate

Parsing functions should be static

1

**🚀 Feature** Parsing methods like `Image._parse_affine`, `Image._parse_tensor` and `Image._read_and_check` currently don't touch the class state (via `self`). As they only do input validation, they also shouldn't. To prevent this entirely...

justusschock

Allow the ingestion of RSNA Spine Fracture Test Images

4

**🚀 Feature** The RSNA Spine Fracture class is hard-coded to only load the training images: https://github.com/fepegar/torchio/blob/main/src/torchio/datasets/rsna_spine_fracture.py#L71 I propose implementing an argument at initialization to allow this class to ingest test...

dankleeman

[pre-commit.ci] pre-commit autoupdate

1

updates: - [github.com/pycqa/flake8: 4.0.1 → 5.0.4](https://github.com/pycqa/flake8/compare/4.0.1...5.0.4) - [github.com/asottile/pyupgrade: v2.37.2 → v2.37.3](https://github.com/asottile/pyupgrade/compare/v2.37.2...v2.37.3) - [github.com/asottile/setup-cfg-fmt: v1.20.2 → v2.0.0](https://github.com/asottile/setup-cfg-fmt/compare/v1.20.2...v2.0.0) - [github.com/PyCQA/doc8: 0.11.2 → v1.0.0](https://github.com/PyCQA/doc8/compare/0.11.2...v1.0.0)

pre-commit-ci[bot]

Cannot use Patch Queue together with multi-GPU training (via pytorch-lightning)

3

### Is there an existing issue for this? - [X] I have searched the existing issues ### Bug summary I am testing to use Pytorch-lightning to handle model training (easy...

jxchen01

DataLoader is very slow when using SubjectsDataset

7

### Is there an existing issue for this? - [x] I have searched the existing issues ### Problem summary When using SubjectsDataset with PyTorch dataloader, iterating over the dataloader is...

ivezakis