More RL and callbacks

[0.4.0] - 2021-09-09

Added

• Added Soft Actor Critic (SAC) Model (#627)
• Added EMNISTDataModule, BinaryEMNISTDataModule, and BinaryEMNIST dataset (#676)
• Added Advantage Actor-Critic (A2C) Model (#598)
• Added Torch ORT Callback (#720)
• Added SparseML Callback (#724)

Changed

• Changed the default values pin_memory=False, shuffle=False and num_workers=16 to pin_memory=True, shuffle=True and num_workers=0 of datamodules (#701)
• Supporting deprecated attribute usage (#699)

Fixed

• Fixed ImageNet val loader to use val transform instead of train transform (#713)
• Fixed the MNIST download giving HTTP 404 with torchvision>=0.9.1 (#674)
• Removed momentum updating from val step and add separate val queue (#631)
• Fixed moving the queue to GPU when resuming checkpoint for SwAV model (#684)
• Fixed FP16 support with vision GPT model (#694)
• Removing bias from linear model regularisation (#669)
• Fixed CPC module issue (#680)