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.