- 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.
- Build the container.
docker build -t fashion .
- 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