BestOf 2025 · 2
7.28 FID
A2 · FID, precision, recall and generated images
Ranked by FID · lower is better. Student groups and professor references compete together.
7.28 FID
8.27 FID
49.88 FID
FID over time · lower is better.
Drag to zoom horizontally or vertically; scroll to zoom. Use the toolbar to pan or reset. Dots show evaluations, not GitHub activity. Failed runs leave gaps.
No successful evaluations yet.
FID ↓ · precision ↑ · recall ↑. P and R are fractions between 0 and 1. The generator architecture must stay fixed.
Hover or focus the ! icon to read an error; click to copy it. Open the image link to inspect the generated digits.
| Rank | Status | Samples | Source | |||||
|---|---|---|---|---|---|---|---|---|
| 1 | BestOf 2025 · 2Reference | 7.28 | 0.866 | 0.701 | 135.69A40 | Success | 10 images | Frozen referencec64582d3 |
| 2 | BestOf 2025 · 1Reference | 8.27 | 0.794 | 0.711 | 65.26A40 | Success | 10 images | Frozen reference39f46132 |
| 3 | VanillaGANReference | 49.88 | 0.467 | 0.171 | 65.41A40 | Success | 10 images | Frozen reference4b4d8ba1 |
No matching group.
Random samples from this run, not hand-picked. Click an image to open the PNG.
Random samples from this run, not hand-picked. Click an image to open the PNG.
Run 20261021T160156Z · Generation limit: 1200 s. Student generation: 4 CPU threads / 12 GiB; historical references may use one A40. Metrics use the evaluator GPU. Time excludes dependency installation and metric computation.