Table 2 Top-1 accuracy (%) of chrysanthemum test set
From: Metric learning for image-based flower cultivars identification
Model | Acc. |
|---|---|
ResNet18 (P=5, K=10) | 89.50 |
ResNet18 (P=18, K=5) | 91.88 |
ResNet50 (P=5, K=10) | 66.21 |
ResNet50 (P=18, K=5) | 90.54 |
DenseNet121 (P=5, K=10) | 89.33 |