• Conditional Generative Adversarial Nets (2014)
• Deep Convolutional Generative Adversarial Networks (2016)

Interactive report: link

Model	Epoch 0	Epoch 12	Epoch 24
CGAN
DCGAN

Model	BCE Loss
CGAN
DCGAN

Overall DCGAN achieved better results, not only in terms of generator loss, but also visually pleasing results. However, the training took twice as much time as CGAN training.

1. Build the container.

docker build -t fashion .

2. Run.

docker run --runtime=nvidia fashion

If you want to use Weights & Biases make sure to assign your key to WANDB_API_KEY env variable and run:

docker run --runtime=nvidia --env-file .env fashion --wandb 1

• Pretraining generator model
• Testing other architectures
• More extensive hyperparameter tuning (more parameters and more optuna trials)
• Writing tests