Update TorchIO version (#677)

* Update TorchIO version

Resolves #672.

CHANGELOG.md

@@ -13,7 +13,8 @@ created.
 ## Upcoming
 
 ### Added
--([#671](https://github.com/microsoft/InnerEye-DeepLearning/pull/671)) Remove sequence models and unused variables. Simplify README.
+
+- ([#671](https://github.com/microsoft/InnerEye-DeepLearning/pull/671)) Remove sequence models and unused variables. Simplify README.
 - ([#678](https://github.com/microsoft/InnerEye-DeepLearning/pull/678)) Add function to get log level name and use it for logging.
 - ([#666](https://github.com/microsoft/InnerEye-DeepLearning/pull/666)) Replace RadIO with TorchIO for patch-based inference.
 - ([#643](https://github.com/microsoft/InnerEye-DeepLearning/pull/643)) Test for recovery of SSL job. Tracks learning rate and train
@@ -35,7 +36,7 @@ jobs that run in AzureML.
 - ([#554](https://github.com/microsoft/InnerEye-DeepLearning/pull/554)) Added a parameter `pretraining_dataset_id` to
  `NIH_COVID_BYOL` to specify the name of the SSL training dataset.
 - ([#560](https://github.com/microsoft/InnerEye-DeepLearning/pull/560)) Added pre-commit hooks.
--([#619](https://github.com/microsoft/InnerEye-DeepLearning/pull/619)) Add DeepMIL PANDA
+- ([#619](https://github.com/microsoft/InnerEye-DeepLearning/pull/619)) Add DeepMIL PANDA
 - ([#559](https://github.com/microsoft/InnerEye-DeepLearning/pull/559)) Adding the accompanying code for the ["Active label cleaning: Improving dataset quality under resource constraints"](https://arxiv.org/abs/2109.00574) paper. The code can be found in the [InnerEye-DataQuality](InnerEye-DataQuality/README.md) subfolder. It provides tools for training noise robust models, running label cleaning simulation and loading our label cleaning benchmark datasets.
 - ([#589](https://github.com/microsoft/InnerEye-DeepLearning/pull/589)) Add `LightningContainer.update_azure_config()`
  hook to enable overriding `AzureConfig` parameters from a container (e.g. `experiment_name`, `cluster`, `num_nodes`).
@@ -55,6 +56,9 @@ jobs that run in AzureML.
 - ([#679](https://github.com/microsoft/InnerEye-DeepLearning/pull/679)) Add FP and TN slides/tiles to DeepMIL outputs and extend outputs to multi-class problems.
 
 ### Changed
+
+- ([#677](https://github.com/microsoft/InnerEye-DeepLearning/pull/677)) Update TorchIO version to include the recent bug fix related to patch-based inference.
+- ([#666](https://github.com/microsoft/InnerEye-DeepLearning/pull/666)) Replace RadIO with TorchIO for patch-based inference.
 - ([#659](https://github.com/microsoft/InnerEye-DeepLearning/pull/659)) Update cudatoolkit version from 11.1 to 11.3.
 - ([#588](https://github.com/microsoft/InnerEye-DeepLearning/pull/588)) Replace SciPy with PIL.PngImagePlugin.PngImageFile to load png files.
 - ([#585](https://github.com/microsoft/InnerEye-DeepLearning/pull/585)) Switching to PyTorch 1.10.0 and torchvision 0.11.1

environment.yml

@@ -69,7 +69,7 @@ dependencies:
  - tabulate==0.8.7
  - tensorboard==2.3.0
  - tensorboardX==2.1
- - torchio==0.18.73
+ - torchio==0.18.74
  - torchmetrics==0.6.0
  - umap-learn==0.5.2
  - yacs==0.1.8