Version 0.3 - Performance Improvements

Changes:

• Performance improvements of block mask computation (#21)
• Performance improvements of bernoulli mask computation (#22)

Bug Fixes:

• Fixed bug where too big block sizes lead to wrong block mask size (#20)

Notes:

• Should be now compatible with PyTorch v1.0

Version 0.2.1 - minor fix

Fixes a minor issue with the DropBlock2D block mask generation.

Version 0.2

Breaking changes:

• DropBlock is now DropBlock2D
• feat_size argument no longer exists, now dinamically computed

New Features:

• DropBlock3D
• LinearScheduler
• ResNet9 on CIFAR10 example script

Bug Fixes:

• Refactored forward pass of DropBlock
• FIxed gamma computation
• Fixed CUDA compatibility

First Release

Index based DropBlock implementation