Class-conditional image synthesis on COCO-Animals 50k synthetic evaluation 128x128 (train test)
13.73FIDU-Net GAN
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| U-Net GANFramework=PyTorch, Resolution=128x128, Training Iterations=400k2020.02 | 13.73 | — | — | — | — | 12.29 | |
| U-Net GANFramework=TensorFlow, Resolution=128x128, Training Iterations=400k2020.02 | 13.96 | — | — | — | — | 11.77 | |
| BigGANFramework=PyTorch, Resolution=128x128, Training Iterations=400k2020.02 | 16.37 | — | — | — | — | 11.77 | |
| BigGANFramework=TensorFlow, Resolution=128x128, Training Iterations=400k2020.02 | 16.42 | — | — | — | — | 11.34 | |
| BigGANruns=Best/Median of 5 runs, training_iterations=400k2020.02 | — | 16.37 | 11.77 | 16.55 | 11.78 | — | |
| U-Net GANruns=Best/Median of 5 runs, training_iterations=400k2020.02 | — | 13.73 | 12.29 | 13.87 | 12.31 | — |