Table 3 DLVTNet model recognition accuracy comparison under different batch sizes.
From: Lightweight grape leaf disease recognition method based on transformer framework
Methods | Accuracy | Precision | Recall | F1 score | Top Accuracy | Batch Size |
|---|---|---|---|---|---|---|
DLVTNet | 98.33 | 98.36 | 98.33 | 98.33 | 99.41 | 8 |
DLVTNet | 98.48 | 98.48 | 98.47 | 98.46 | 99.79 | 16 |
DLVTNet | 98.44 | 98.46 | 98.45 | 98.45 | 99.42 | 32 |
Best DLVTNet | 98.58 | 98.61 | 98.62 | 98.60 | 99.62 | 16 |
Bad DLVTNet | 98.27 | 98.32 | 98.32 | 98.29 | 99.49 | 16 |
