Image Generation on Steering Angle (test)
1.546Intra-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 | 1.546 | 1.13 | 1.156 | 10.933 | 4.439 | 0.331 | |
| CcGANHyper-parameter selection strategy=HVDL, Label input mechanism=ILI, Image resolution=64x64, Training iterations=30,000, Batch size=2562020.11 | 1.635 | 1.152 | 1.153 | 10.868 | 4.592 | 0.327 | |
| CcGANHyper-parameter selection strategy=SVDL, Label input mechanism=NLI, Image resolution=64x64, Training iterations=30,000, Batch size=2562020.11 | 1.866 | 1.098 | 1.007 | 19.678 | 3.968 | 0.212 | |
| CcGANHyper-parameter selection strategy=HVDL, Label input mechanism=NLI, Image resolution=64x64, Training iterations=30,000, Batch size=2562020.11 | 1.969 | 1.093 | 0.991 | 22.322 | 3.587 | 0.316 | |
| cGANLabel input mechanism=concat, Image resolution=64x64, Training iterations=30,000, Batch size=2562020.11 | 2.446 | 1.717 | 1.255 | 41.686 | 3.251 | 0.255 | |
| cGANNumber of classes (binning)=210 classes, Image resolution=64x64, Training iterations=30,000, Batch size=2562020.11 | 3.285 | 1.296 | 0.603 | 14.596 | 2.572 | 0.976 |