Table 3 Test results of Swin V236 models trained on complete and quarter of circle radial images.
From: A new benchmark for machine learning applied to powder X-ray diffraction
Data | Pretraining | Accuracy ↑ (%) | Top 5 Accuracy ↑ (%) |
|---|---|---|---|
Complete Circles | False | 42.11 | 81.12 |
True | 45.32 | 82.79 | |
1/4 of Circles | False | 41.98 | 80.96 |
True | 46.70 | 83.82 |
