DataPredict Neural [Release 1.5] - PyTorch-like Deep Learning Library Meets Roblox!

[MYOriginsWorkshop]

Release Version 1.0 / Beta Version 0.6.0

Added

• Shape Transformation Blocks:

  • Permute

• Attention Blocks:

  • BaseAttentionBlock

  • ScaledDotProductAttention

• Deep Reinforcement Models:

  • DeepQLearning

  • DeepDoubleQLearningV1

  • DeepDoubleQLearningV2

  • DeepClippedDoubleQLearning

  • DeepStateActionRewardStateAction

  • DeepDoubleStateActionRewardStateActionV1

  • DeepDoubleStateActionRewardStateActionV2

  • DeepExpectedStateActionRewardStateAction

  • DeepDoubleExpectedStateActionRewardStateActionV1

  • DeepDoubleExpectedStateActionRewardStateActionV2

  • ActorCritic

  • AdvantageActorCritic

  • ProximalPolicyOptimization

  • ProximalPolicyOptimizationClip

  • REINFORCE

  • VanillaPolicyGradient

• Value Schedulers:

  • BaseValueScheduler

  • TimeDecay

  • StepDecay

Changes

• setClassesList() function and getClassesList() function are added to Sequential Container.

• Removed “numberOfData” parameter from the BaseCostFunction’s calculateCostValue() function and calculateLossTensor() function.

• setLearningRateScheduler() function and getLearningRateScheduler() function are added to the BaseOptimizer

Side Notes

Please update your TensorL library for bug fixes.

[MYOriginsWorkshop]

Release Version 1.1 / Beta Version 0.7.0

Added

• Expansion Blocks:

  • BaseExpansionBlock

  • ExpandNumberOfDimensions

  • ExpandDimensionSizes

[MYOriginsWorkshop]

(post deleted by author)

[MYOriginsWorkshop]

Release Version 1.2 / Beta Version 0.8.0

Changes

• Moved InputHolder to Holder Blocks

• Changed all the Shape Transformation Blocks settings so that it saves the transformed tensor.

Added

• Holder Blocks:

  • BaseHolderBlock

  • VariableHolder

  • NullaryFunctionHolder

[MYOriginsWorkshop]

Release Version 1.3 / Beta Version 0.9.0

Changes

• If any of the input tensors have its number of dimensions or dimension sizes expanded, it will collapse the partial first derivative tensor to the input tensor’s number of dimensions and dimension sizes.

Added

• Operator Blocks:

  • Clamp

  • Maximum

  • Minimum

[MYOriginsWorkshop]

Release Version 1.4 / Beta Version 1.0.0

Changes

• Everything related to “FirstDerivative” is renamed to “ChainRuleFirstDerivative”.

• Everything related to “SecondStepFirstDerivative” is renamed to “FirstDerivative”.

• Calculations for first derivative tensors inside the FunctionBlocks are now more efficient.

Fixes

• Replaced forgotten TensorL’s getSize() functions to getDimensionSizeArray().

• Fixed a bug where MaxUnpooling FunctionBlocks requires incorrect input tensors dimension sizes.

[MYOriginsWorkshop]

Release Version 1.5 / Beta Version 1.1.0

Added

• Added RandomNetworkDistillation under “Models”.