hi-ml

hi-ml copied to clipboard

In this PR: - `transformer_dropout` parameter is added to TransformerPooling` and `TransformerPoolingBenchmark` pooling layers. - Tests are updated with the `transformer_dropout` parameter.

harshita-s

ENH: Upgrade hi-ml-cpath to Python 3.9

1

ant0nsc

FIX: Update env var settings for multi node

4

Changes in the way that Azure ML set the environment variable `ENV_AZ_BATCHAI_MPI_MASTER_NODE` mean that the logic for setting environment variables for multi-node jobs needs updating

mebristo

Bump numpy from 1.21.6 to 1.22.0 in /hi-ml-cpath

8

Bumps [numpy](https://github.com/numpy/numpy) from 1.21.6 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...

dependabot[bot]

ENH: Switch to new AzureML runtime

1

ant0nsc

Bump pypa/gh-action-pypi-publish from 1.5.0 to 1.5.1

7

Bumps [pypa/gh-action-pypi-publish](https://github.com/pypa/gh-action-pypi-publish) from 1.5.0 to 1.5.1. Release notes Sourced from pypa/gh-action-pypi-publish's releases. v1.5.1 What's Changed Fixed printing out the dist hashes when packages_dir is a wildcard value. — by @​meowmeowmeowcat...

dependabot[bot]

ENH: Enable heatmaps when tiling on the fly

1

In this PR we enable heatmap outputs when tiling on the fly. Specifically: * we changed the MONAI transform used for tiling to be GridPatch. The main advantage is that...

vale-salvatelli

Models that use pre-trained SSL currently rely on hardocded path in `run_ids.py`, but these runs are only available in one Workspace. The user should be able to provide their own...

mebristo

In PL 1.5, supplying the checkpoint path to the trainer has been deprecated. Instead, it should be supplied as an argument to `trainer.fit`.

ant0nsc

Re-activate #523 . Troublemaker: Checkpoints from existing SSL runs will not be able to load in the new codebase. We need to decide how to handle legacy runs

ant0nsc