v0.1.29 - Venezia

• Support dicom images in lesion-predict
• Change logger.warnings to warnings.warn
• Remove deprecation warning for floor divide in torch in patch-based prediction

v0.1.28 - Venezia

• Add commit hash logger function to tag MLFlow runs
• Save configuration files to MLFlow
• Add option to save top K checkpoints

v0.1.27 - Venezia

• Add union and voting aggregation to prediction and other minor bug fixes

v0.1.26 - Venezia

• Reformat with newer version of black (v21.7b0)
• Change to every_n_epochs in ModelCheckpoint since every_n_val_epochs will be deprecated

v0.1.25 - Venezia

• Detect and use tensorboard directory (/opt/ml/output/tensorboard) for logging on SageMaker

v0.1.24 - Venezia

• Add experiment and trial name as options to explicitly specify artifact locations

v0.1.23 - Venezia

• Change AWS option to just MLFlow
• Compliant with mypy
• Other minor bug fixes and fix docs

v0.1.22 - Venezia

• Add AWS extras (MLFlow and train and serve console scripts)
• Add option to resample images within a subject for consistent orientation
• Add optional check of DICOM images to determine if they are uniformly sampled
• Make package compatible with Python 3.6 and 3.9
• Split CLI functions into a subpackage for better organization

v0.1.21 - Venezia

• Add MLFlow logging option
• Add support for reading DICOM images and writing DICOM (Segmentation Objects)
• Fix some type hints and make pos_weight a vector of length 1

v0.1.20 - Venezia

• Make reorientation to canonical optional
• Add option to track best network on validation Dice, PPV, loss, or ISBI15 score
• Unify and simplify the positive weight in focal/bce component of combo loss
• Change flip in spatial augmentation to only do lateral flips
• Fix predict_probability flag in CLI