Image Generation on RC-49 (test)
0.389Intra-FIDCcGAN
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| CcGANHyper-parameter selection strategy=SVDL, Label input mechanism=ILI, Image resolution=64x64, Training iterations=30,000, Batch size=2562020.11 | 0.389 | 1.783 | 2.949 | 1.94 | 20.173 | 0.197 | |
| CcGANHyper-parameter selection strategy=HVDL, Label input mechanism=ILI, Image resolution=64x64, Training iterations=30,000, Batch size=2562020.11 | 0.424 | 1.805 | 2.814 | 1.816 | 17.992 | 0.213 | |
| CcGANHyper-parameter selection strategy=SVDL, Label input mechanism=NLI, Image resolution=64x64, Training iterations=30,000, Batch size=2562020.11 | 0.515 | 1.853 | 2.61 | 4.982 | 19.425 | 0.207 | |
| CcGANHyper-parameter selection strategy=HVDL, Label input mechanism=NLI, Image resolution=64x64, Training iterations=30,000, Batch size=2562020.11 | 0.612 | 1.869 | 2.353 | 5.617 | 14.73 | 0.285 | |
| cGANLabel input mechanism=concat, Image resolution=64x64, Training iterations=30,000, Batch size=2562020.11 | 1.141 | 1.819 | 2.459 | 30.212 | 11.44 | 0.295 | |
| cGANNumber of classes (binning)=150 classes, Image resolution=64x64, Training iterations=30,000, Batch size=2562020.11 | 1.72 | 2.731 | 0.779 | 4.815 | 2.382 | 1.066 |