Episode 2: PyTorch Dropout, Batch size and interactive debugging
In the previous video, we create a PyTorch classification model from scratch and set up training on GPUs: https://youtu.be/OMDn66kM9Qc
In this video we are going over using dropout layers to avoid overfitting, interactive debugging of your models, and choosing the optimal batch size.
Check out our next video to find out how to train your model the Lightning way- write less boilerplate, scale more quickly: https://youtu.be/DbESHcCoWbM
Alfredo Canziani is a Computer Science professor at NYU (check out his deep learning class -https://www.youtube.com/playlist?list=PLLHTzKZzVU9eaEyErdV26ikyolxOsz6mq.)
Willam Falcon is an AI Ph.D. researcher at NYU, and creator and founder of PyTorch Lightning.
00:24 Prevent overfitting with Dropout
08:06 Interactive neural network debugging
28:45 Choosing batch size
Thanks for watching!