v0.3.1

What's Changed

hi-ml-azure

• FIX: Stop replacing dashes with underscores in experiment name by @fepegar in #884
• FIX: Fix env variables not passed to AML SDK v2 jobs by @fepegar in #885

Full Changelog: v0.3.0...v0.3.1

v0.3.0

What's Changed

hi-ml-azure

• ENH: Expose v1 dataset overwrite by @peterhessey in #853
• ENH: Better commandline parsing of Enums by @ant0nsc in #861
• BUG: Prevent creating v2 data asset without specifying datastore by @peterhessey in #854
• FIX: Fix empty list of script params not used by @fepegar in #881

hi-ml

• ENH: Enable flexible resolution unit for mock data generator by @kenza-bouzid in #827
• MNT: Upgrade pytorch to 1.11 by @kenza-bouzid in #833
• ENH: Improve handling of metric comparison for regression tests by @ant0nsc in #835
• BUG: Misleading warnings when comparing metrics by @ant0nsc in #838
• ENH: Allow variants of model parameters in the same class by @ant0nsc in #840
• ENH: Add log files to AzureML runs to identify preemption by @ant0nsc in #841
• MNT: Fix incorrect type annotations by @ant0nsc in #846
• ENH: Ability to evaluate model on a new dataset by @ant0nsc in #859
• FIX: Fix typo in makefile for make targets by @jubinmathew1995 in #865
• ENH: Add tests for use of checkpoints in inference_only mode by @ant0nsc in #876

hi-ml-multimodal

• FIX: Fix notebook CI when trying to merge from fork by @fepegar in #829
• ENH: Add BioViL-T image and text encoders by @ozan-oktay in #830
• ENH: Consume BioViL-T Pretrained Models in Inference Engines by @ozan-oktay in #845
• FIX: Fix notebook not working on Binder by @fepegar in #852
• MNT: Bump hi-ml-multimodal version by @fepegar in #849
• ENH: Improve support for choosing image model weights by @markpinnock in #807
• MNT: Bump hi-ml-multimodal version: 0.2.0 → 0.2.1 by @fepegar in #869

hi-ml-cpath

• ENH: Add LoadMaskSubROId transform by @kenza-bouzid in #828
• ENH: Use Latest Monai GridPatch to filter both threshold and count by @kenza-bouzid in #834
• BUG: Convert to tifffile if file doesn't exist or if it's empty by @kenza-bouzid in #836
• ENH: Add non normalized confusion matrix to plot options by @kenza-bouzid in #791
• ENH: Enable activation checkpointing for Resnet and SwinTransformer by @kenza-bouzid in #842
• ENH: Refactor Swin Transformer checkpointing by @kenza-bouzid in #843
• ENH: Add display name to montage script by @kenza-bouzid in #847
• ENH: Add diagnosis for Tiff Conversion by @kenza-bouzid in #862
• ENH: Add normalized confusion matrix key to metrics keys by @maxilse in #868
• ENH: Add a class_weights argument to the data module by @ant0nsc in #871
• BUG: Fix extra validation epoch hook call order by @kenza-bouzid in #873
• ENH: Add account key argument to generate checkpoint URL script by @kenza-bouzid in #874
• ENH: Clean up design of slides dataset by @ant0nsc in #875

Other

• ENH: Autoupdate hooks [pre-commit.ci] by @pre-commit-ci in #831
• Bump pypa/gh-action-pypi-publish from 1.5.0 to 1.8.1 by @dependabot in #844
• STY: Add Black pre-commit hook by @fepegar in #782
• Bump pypa/gh-action-pypi-publish from 1.8.1 to 1.8.3 by @dependabot in #856
• Bump pypa/gh-action-pypi-publish from 1.8.3 to 1.8.5 by @dependabot in #863
• ENH: Autoupdate hooks [pre-commit.ci] by @pre-commit-ci in #864

New Contributors

• @jubinmathew1995 made their first contribution in #865

Full Changelog: v0.2.19...v0.3.0

v0.2.19

What's Changed

• BUG: Doc build fails because of special characters in .md file by @ant0nsc in #826
• ENH: Autoupdate hooks [pre-commit.ci] by @pre-commit-ci in #593
• MNT: Upgrade pytest by @ant0nsc in #813
• MNT: Add make command to publish to PyPI by @fepegar in #816
• DOC: Use symlinks to build docs instead of copying files by @fepegar in #824

hi-ml-azure

• ENH: MONAI Auto3dSeg Updates by @peterhessey in #819

hi-ml-multimodal

• FIX: Copy hi-ml-multimodal README while building documentation by @fepegar in #811
• FIX: Set evaluation mode to compute number of dimensions by @fepegar in #809
• DOC: Replace arXiv links with ECCV links by @fepegar in #812
• FIX: Use different image for multimodal notebook by @fepegar in #808
• MNT: Bump version: 0.1.2 → 0.1.3 by @fepegar in #815
• MNT: Increase verbosity while running notebook by @fepegar in #817

hi-ml-cpath

• ENH: Add Swin Transformer Encoder and Projection layer by @kenza-bouzid in #810
• ENH: Add background normalization transform by @harshita-s in #803
• ENH: Add ipykernel to environment by @ant0nsc in #814
• ENH: WSI Conversion to tiff files by @kenza-bouzid in #820

Full Changelog: v0.2.18...v0.2.19

More pathology workflow tools, fix for identity-based access

What's Changed

hi-ml-azure

• BUG: Add flag for identity-based data access by @peterhessey in #797

hi-ml-cpath

• ENH: Add code to create montages from WSI by @ant0nsc in #787
• ENH: Add ability to choose a folder for upload to DSA by @ant0nsc in #796
• ENH: Add workspace config path to generate checkpoint URL script by @kenza-bouzid in #798
• ENH: Add an argument to specify split for DSA upload by @ant0nsc in #800
• ENH: Add instructions for HistoQC by @ant0nsc in #799

hi-ml-multimodal

• MNT: Run multimodal CI every morning by @fepegar in #790

Full Changelog: v0.2.17...v0.2.18

Enable user identity based data access, plotting improvements

What's Changed

hi-ml-azure

• ENH: Enable User Identity for accessing data by @peterhessey in #775
• BUG: Fix ordering of local_datasets by @peterhessey in #794

hi-ml

• ENH: Enable resubmitting single cross validation runs manually by @kenza-bouzid in #781

hi-ml-cpath

• ENH: Add extra slides to attention heatmaps plots by @kenza-bouzid in #778
• BUG: Fix missing bottom coordinates in outputs csv by @kenza-bouzid in #784
• ENH: Add ROC curve to plot options by @harshita-s in #780
• ENH: Stratify PR and ROC curves by metadata by @harshita-s in #788

Full Changelog: v0.2.16...v0.2.17

Bug fix release for job display names

What's Changed

hi-ml-azure

• BUG: Display name is not respected when using SDK v2 by @ant0nsc in #776

hi-ml-cpath

• ENH: Add intensity threshold scale argument by @kenza-bouzid in #779

Full Changelog: v0.2.15...v0.2.16

Enhancements for SDK v2 jobs

What's Changed

hi-ml-azure

• BUG: Fix and test data asset interactions by @peterhessey in #740
• BUG: ML Client doesn't use workspace config path when specified by @kenza-bouzid in #771
• BUG: Fix create v2 asset bug by @peterhessey in #772
• ENH: Make display names a first class citizen by @ant0nsc in #774

Full Changelog: v0.2.14...v0.2.15

Bug fix release for Kubernetes compute

What's Changed

hi-ml-azure

• BUG: Jobs on Kubernetes compute don't see GPUs by @ant0nsc in #769

hi-ml-cpath

• ENH: Gaussian blur and pre-processing transforms in SSL by @harshita-s in #752
• BUG: Gather results causes OOM for very large bag_size by @kenza-bouzid in #765
• ENH: Enable distributed inference by @kenza-bouzid in #761

Full Changelog: v0.2.13...v0.2.14

Bug fix release for AzureML SDK v2

What's Changed

hi-ml-azure

• BUG: SDK v2 datasets are not passed to AML correctly by @ant0nsc in #758

hi-ml

• MNT: Remove duplicate code by @ant0nsc in #751

hi-ml-cpath

• ENH: Deprecate val_set_is_dist by @kenza-bouzid in #754

hi-ml-multimodal

• MNT: Bump hi-ml-multimodal patch version by @fepegar in #750

General

• BUG: Remove shadow PR files by @peterhessey in #745
• ENH: Output the slowest tests by @ant0nsc in #762

Full Changelog: v0.2.12...v0.2.13

Better AzureML v2 SDK support, low-priority preemption, pathology improvements

What's Changed

hi-ml-azure

• BUG: Fix broken --azureml flag by @peterhessey in #709
• ENH: Allow for distributed jobs in AML SDK v2 by @mebristo in #730
• BUG: Add waiting for job completion for SDK v2 by @ant0nsc in #669
• BUG: Do not remove conda_env argument when submitting with SDK v2 by @ant0nsc in #737
• BUG: Training HelloWorld using AML v2 SDK hangs by @ant0nsc in #741

hi-ml

• ENH: Enable adding additional env variables from container by @kenza-bouzid in #689
• BUG: Retire DATASET_MOUNT_CACHE_SIZE by @kenza-bouzid in #692
• ENH: Add logic to find recovery checkpoints for preempted runs by @ant0nsc in #705
• ENH: Add shadow workflow for hi-ml-pr by @mebristo in #595
• ENH: Reduce logging noise in test suite by @ant0nsc in #718
• ENH: Allow low-priority preemption after training by @ant0nsc in #722
• ENH: Simplify MLRunner Inference by @kenza-bouzid in #734

hi-ml-cpath

• ENH: Upgrade cucim and tiffile by @kenza-bouzid in #691
• ENH: Enable overriding tiling on the fly steps by @kenza-bouzid in #696
• ENH: Add diagnostics tools by @kenza-bouzid in #695
• ENH: Add option to tile a single slide selected by slide id by @maxilse in #707
• Bump wheel from 0.36.2 to 0.38.1 in /hi-ml-cpath by @dependabot in #713
• BUG: Fix slow-path warning in tests that use MockPandaSlidesGenerator by @kenza-bouzid in #717
• ENH: Recreate datamodule for extra validation and inference by @kenza-bouzid in #721
• ENH: Improve Attention Heatmaps plots by @kenza-bouzid in #723
• ENH: Re-enable a test for SSL encoders by @ant0nsc in #726
• ENH: Allow return of intermediate layers from ResNet by @markpinnock in #724
• BUG: Subsample tiles without replacement by @harshita-s in #732
• ENH: Use UnrepeatedDistributedSampler for validation and test by @kenza-bouzid in #743

hi-ml-multimodal

• TEST: Update CI to compute and upload coverage for hi-ml-multimodal by @fepegar in #685
• ENH: Use module-level logger in hi-ml-multimodal by @fepegar in #687

General

• DOC: Refer to CONTRIBUTING for list valid prefixes by @fepegar in #686
• ENH: Improve PR workflows by @ant0nsc in #697
• ENH: Clean up readme file in the template for new projects by @ant0nsc in #702
• Bump setuptools from 59.5.0 to 65.5.1 in /new_project_template by @dependabot in #714
• Bump setuptools from 59.5.0 to 65.5.1 in /hi-ml-multimodal by @dependabot in #715
• Bump wheel from 0.36.2 to 0.38.1 in /new_project_template by @dependabot in #711
• Bump wheel from 0.36.2 to 0.38.1 by @dependabot in #710
• ENH: Simplify makefile targets by @ant0nsc in #728
• ENH: Remove mypy cache folder in make clean by @ant0nsc in #735

New Contributors

• @markpinnock made their first contribution in #724

Full Changelog: v0.2.11...v0.2.12