Hello everyone! I updated the concrete dropout implementation from the original authors to work with tensorflow 2.0, tweaked the code a bit and turned it into a pip package! If you are interested, you can find the github page here.
Concrete dropout is a technique which allows for the training of the dropout probability in a layer, which may save a lot of time since it removes the need to grid search for the best dropout parameters.
For more information, see the original paper arXiv:1705.07832 and the readme on github!
If you have any questions or suggestions, please feel free to contact me!