Release Notes

0.3.5.2

• Unsupervised Pre-training guide for semi-supervised learning included.

• Larger datasets run faster due to optimized dataset cardinality calculation.

• Autofit runs with the same early stopping callback but epochs set to 1000000, not 2**31, to make console output more interpretable.

• Distillation report includes number of weights in source and target (teacher and student) models.

• Logging includes both val and test sets (if test is available). Note that the metalearning algorithm never sees test - evaluations on test are purely for diagnostics.

• Log directories named by run number (e.g. ~/.masterful/run-00001) instead of datetime (e.g. ~/.masterful/UTC_2021-08-18__17-34-29.037488)

• Detailed logs originally (sent to ~/.masterful) can now also be sent to console via env variable MASTERFUL_LOG_TO_CONSOLE=1.

• In some cases, fit was broken due to a bug in keras: model.trainable on a cloned model has undocumented behavior. Solution was implemented which ensures autofit and masterful.core.fit will run successfully.

• Warmup implemented.

• Batchnorm warmup implemented to ensure val metrics are based on stable batch norm moving metrics. This is particularly helpful on image data that is not prenormalized to zero-mean, unit-variance (ZMUV).

Known Issues:

• “Gradient Not Found” warning is sent to console during autofit and masterful.core.fit. This warning is innocuous.

0.3.5.1

• Noisy Student Training reintroduced.

• Robust but slower settings for optimizer policy.

• Unsupervised pretraining supports larger model sizes.

• Distillation API.

• Removed warmup due to overfitting bug, will slow down training speeds but not affect final accuracy.

• Documentation for graphical front end, ensembling, and distillation.

0.3.5

• Revised API for autofit and advanced “core” api.

• find_optimizer_policy searches for optimal policy for optimizer settings.

• find_batch_size searches for largest batch size that fits in memory to speedup training.

• General API for data and model specifications.

• Unsupervised pretraining in the advanced API.

• Added reflection on spatial transformations.

0.3.4

• Added quickstart tutorial documentation.

• Separated console output from logging to disk.

• Support for several data formats.

• Anchor box conversion for Fizyr Keras Retinanet model.

• Localization/detection support for spatial transforms.

• Protobuf logging on intermediate search phases.

• Layerization of losses with serialization.

• Native support for loss_weights.

• Native support for multiple losses.

(codename victor)

0.3.3

• Mixup transformation.

• Eliminated all showstopper bugs from previous release.

• Careful control of LR during metalearning algorithm.

(codename uniform)

0.3.2

• Cutmix transformation.

• Removed epochs and lr callbacks, now user responsibility.

• Eliminated some showstopper bugs from previous version.

Known Issues:

• Unstable release, do not use.

(codename tango)

0.3.1

• Added saving and loading of policies.

• Noisy Student Training functionality.

Known Issues:

• Unstable release, do not use.

(codename sierra)

0.3

• Layerization of transforms for high speed augmentation.

• Groundup implementation of transforms.

• Distance analysis to cluster transforms.

• Metalearner is now beam search.

(codename bravo)

0.2.1

• Multiple bug fixes and performance improvements

• Adds supports for TPU training in GCP using Tensorflow 1.15

• Package name has been renamed masterful from masterful_lite

• Corresponding API’s now reside under masterful.api rather than masterful.api.lite

(fka 0.1.5)

0.2

• Support for multiple instance segmentation masks and bounding boxes has been added.

Breaking Changes:

• This add an API breaking change in the way that labels and masks are packed. See the updated documentation for details.

(fka 0.1.2)

0.1

• Episilon greedy based meta learning algorithm.

Known Issues:

• Slow as it requires frequent shuffling between CPU and GPU via py_function.