Skip to content
This repository has been archived by the owner on Jun 26, 2021. It is now read-only.

Releases: delira-dev/delira

Release v0.6.0

06 Feb 09:33
cd3ad27
Compare
Choose a tag to compare
Release v0.6.0 Pre-release
Pre-release

This is a major release since it changes the license to a dual licensing strategy. This may cause some troubles if you want to use the latest version, so make sure to check the README and the LICENSE.

Release 0.5.0

04 Dec 09:00
e33bdb9
Compare
Choose a tag to compare
Release 0.5.0 Pre-release
Pre-release

Bugfixes

Breaking Changes

  • Logging is now done outside the closure
  • Metrics are now based on numpy and are calculated the same way for train and val
  • Remove trixi dependency [Commit]
  • Remove deprecated codeparts (TorchvisionClassificationDataset , train_test_split , Nii3DLazyDataset , Nii3DCacheDataset , [delira.utils.imageops.py](http://delira.utils.imageops.py) , DefaultOptimWrapperTorch , DebugMode Context Manager and the following requirements: scikit-image, pillow, SimpleITK, psutil [Commit]

New Features

  • Slack Notificator [Commit]
  • Function to seed all backends [Commit]
  • Add Callbacks after and before epoch, after and before training and after and before every step (regardless of train and val) [Commit]
  • New Custom Data Pipeline (completely replaces the batchgenerators pipeline) for more customization and better integration of our sampling [Commit]
  • Register Logger in Callbacks [Commit]
  • Onecycle Scheduler Callback [Commit]
  • Allow creation of config from system args [Commit]

Bugfix Release v0.4.1

27 Jul 07:37
7586390
Compare
Choose a tag to compare
Bugfix Release v0.4.1 Pre-release
Pre-release

Bugfix Release v0.4.1

Bugfixes

  • Several improvements to reduce memory usage (and fixed an actual memory leak)
  • Fix the Search for previous trainings [commit]
  • Convert Metric Values to Numpy [commit]
  • Epochs correctly saved in checkpoints [commit]
  • Refactoring to clean up global namespace [commit]

Improvements

  • Add numba jitting for transforms [commit]
  • Bump TensorFlow to 1.14 [commit]
  • Versioning via versioneer for more detailed versions [commit]

Release v0.4.0

16 Jun 18:00
71368ce
Compare
Choose a tag to compare
Release v0.4.0 Pre-release
Pre-release

Release v0.4.0

New Features

  • Slack: We now have a community chat on slack [commit]
  • Paper: We wrote and submitted a Paper to JOSS [commit]
  • Dataset Integration Guide: New tutorial to switch from old dataset API to new dataset API [commit]
  • Predictor: Introduce new Predictor class to predict from network without having to initialize Trainer with dummy values [commit]
  • PEP-8: Complete Codebase is now PEP-8 compatible and CI/CD now checks for it [commit]
  • Debug Mode: New debug mode disables all multiprocessing (currently multiprocessing is only used during data loading); Might slow down the program but increases debug capabilities [commit]

Breaking Changes

  • Return dicts: Models must now return dicts during prediction and training [commit]
  • Kfold: The old kfold- function has now merged with the new kfold, stratified_kfold and stratified_kfold_predict to a new kfold function supporting all these behaviors. [commit]
  • Rename tf Backend: The tf backend has been renamed to tensorflow during installation. The new command to install delira with TensorFlow backend is now: pip install delira[tensorflow] [commit]

Non-Breaking Changes

  • Unify Trainer: Merging Code from Backend Trainers (TfNetworkTrainer and PyTorchNetworkTrainer) into BaseNetworkTrainer; Will increase maintainability and ease of adding new backends [commit]
  • Unify Experiment: Merging Code from Backend Experiments to BaseExperiment [commit]
  • Sampler StopIteration: Refactor samplers to use a common function to check if StopIteration must be raise (where possible) [commit]

Bugfixes

  • TF Resnet18: ResNet18 in TF now matches the official paper [commit]
  • Parameters: Correct Permutations in Parameters class [commit]
  • Infinite Recursion: Infinite recursion in LookUpConfig due to wrong typechecks is now fixed [commit]
  • DataLoading num_batches: The number of batches is now calculated without any influence of multiprocessing [commit]
  • DataLoading: Instabilities due to inter-process communication [commit]

Release v0.3.2

25 Apr 18:29
5fa9689
Compare
Choose a tag to compare
Release v0.3.2 Pre-release
Pre-release

Release v0.3.2

Added

  • WeightedPrevalenceSampler (433cccb)
  • _DatasetIterator allowing iteration over a dataset with a simple loop without having to iterate over indices explicitly (70d6232)
  • Support for TF1.13 (5e28172)
  • Support for Python 3.5 (5db1a17)

Breaking Changes

  • New Dataset API (#88 )
  • Changed test framework from pytest to unittest (a709809)

Bugfixes

  • Random sampler can now be seeded via numpy for completely determinitic behavior (a7c10ee)

Release v0.3.1

25 Feb 10:29
b3841ca
Compare
Choose a tag to compare
Release v0.3.1 Pre-release
Pre-release

Bugfix-Release 0.3.1

Bugfixes:

  • loading behavior with weights_only=True for torch backend (fff41cf)
  • Behavior of BlankDataset (353648e)
  • Refactoring of backend choosing (01f25de)

Release v0.3.0

07 Feb 11:00
bae606a
Compare
Choose a tag to compare
Release v0.3.0 Pre-release
Pre-release

Release 0.3.0

Added

  • TensorFlow support including

    • AbstractTfNetwork
    • TfNetworkTrainer
    • TfExperiment
    • ClassificationNetworkBaseTf
  • Basic Test-API in Experiment (commit)

  • More Unittests

  • Methods to get a subset of each Dataset

  • Stratified Kfold

Bugfixes

  • dropping last batch in PyTorchNetworkTrainer.predict (commit)
  • Check for installed backends

First Beta Release

15 Jan 14:03
6ab0a1d
Compare
Choose a tag to compare
First Beta Release Pre-release
Pre-release

Based on PyTorch, batchgenerators and trixi it provides a framework for

  • Dataset loading
  • Dataset sampling
  • Augmentation (multi-threaded) including 3D images with any number of channels
  • A generic trainer class that implements the training process
  • Already implemented models used in medical image processing and exemplaric implementations of most used models in general (like Resnet)
  • Web-based monitoring using Visdom
  • Model save and load functions