Experimentation
Experiment using a different activation function and training for a higher number of epochs.
We'll cover the following
Run your own experiments
If you’ve worked through to this stage you’ve covered enough basics to meaningfully try your own ideas for improving the GAN process.
- You could try different kinds of loss functions, different sizes of the neural network, perhaps even variations of the standard GAN training loop.
- Perhaps you might try to discourage mode collapse by including a measure of diversity over several outputs in the loss function.
- If you’re very confident, you might try to implement your own optimiser, one which is better suited to the adversarial dynamics of a GAN.
Experiment with GELU
activation function
The following is one of my own simple experiments with an activation function called GELU
, which is like a ReLU
but has a softer corner.
📝 Some have suggested that such activation functions are now the state of the art because they provide good gradients, and don’t have a sharp discontinuity around the origin.
Get hands-on with 1400+ tech skills courses.