Classification of Simpsons characters
This is a simple demo for classifying Simpsons characters with fast.ai and optimizing the neural network by monitoring and comparing runs with Weights & Biases.
Hyper-parameters are defined pseudo-randomly and every run is automatically logged onto Weighs & Biases for easier analysis/interpretation of results and how to optimize the architecture.
Install dependencies through
Pipfileor manually (Pytorch, Fast.ai & Wandb)
Log in or sign up for an account ->
Visualize and compare your runs through generated link
After running the script a few times, you will be able to compare quickly a large combination of hyperparameters. As an example, you can refer to my runs.
Feel free to modify the script and define your own hyperparameters.