InnerEye-DeepLearning/InnerEye
Eran 03b4cc3f2a
BUG: Rename pretraining_run_checkpoints (#841)
"Parameter `extra_downloaded_run_id` has been renamed to
`pretraining_run_checkpoints`" (According to CHANGELOG.md) but is still
in used in SSLClassifierContainer class (in
InnerEye/ML/SSL/lightning_containers/ssl_image_classifier.py).
It will raise an AttributeError: 'SSLClassifierCIFAR' object has no
attribute 'extra_downloaded_run_id' when trying to run python
InnerEyeML/runner.py --model=CXRImageClassifier
--pretraining_run_recovery_id={THE_ID_TO_YOUR_SSL_TRAINING_JOB}.
So renamed it to `pretraining_run_checkpoints` there too.
<!--
## Guidelines

Please follow the guidelines for pull requests (PRs) in
[CONTRIBUTING](/docs/contributing.md). Checklist:

- Ensure that your PR is small, and implements one change
- Give your PR title one of the prefixes ENH, BUG, STYLE, DOC, DEL to
indicate what type of change that is (see
[CONTRIBUTING](/docs/contributing.md))
- Link the correct GitHub issue for tracking
- Add unit tests for all functions that you introduced or modified
- Run automatic code formatting / linting on all files ("Format
Document" Shift-Alt-F in VSCode)

## Change the default merge message

When completing your PR, you will be asked for a title and an optional
extended description. By default, the extended description will be a
concatenation of the individual
commit messages. Please DELETE/REPLACE that with a human readable
extended description for non-trivial PRs.
-->
2023-02-16 12:09:45 +00:00
..
Azure BUG: Dont update multi-node env vars for single node training (#796) 2022-09-02 16:22:14 +00:00
Common ENH: Fix logging + model registration for Amulet runs (#804) 2022-09-30 11:42:38 +01:00
ML BUG: Rename pretraining_run_checkpoints (#841) 2023-02-16 12:09:45 +00:00
Scripts BUG: Patch imports for `move_model.py` (#831) 2022-11-11 10:17:25 +00:00
README.md Replace RadIO with TorchIO for patch-based inference (#666) 2022-02-23 10:28:11 +00:00
settings.yml Remove more dead arguments (#333) 2020-12-04 11:31:37 +00:00

README.md

Microsoft Research Cambridge InnerEyeDeepLearning for Medical Image Analysis

Consuming the InnerEye package

  • You need to have a Conda installation on your machine.
  • Create a Conda environment file environment.yml in your source code with this contents:
name: MyEnv
channels:
  - defaults
  - pytorch
dependencies:
  - pip=20.0.2
  - python=3.7.3
  - pytorch=1.3.0
  - pip:
      - innereye
  • Create a conda environment: conda env create --file environment.yml
  • Activate the environment: conda activate MyEnv