Table 6 Performance comparison of \(\hbox {V}^2\)PlantNet and MobileNet variants on the test dataset.
From: Optimised MobileNet for very lightweight and accurate plant leaf disease detection
Model | Total Params | Memory | Inference Time (sec) | TFLOPs | Activations | Precision | Recall | F1-score | Accuracy |
|---|---|---|---|---|---|---|---|---|---|
\(\hbox {V}^2\)PlantNet | 383,375 | 1.46 MB | 0.676399 | 773,445 | 9,659,663 | 0.99 | 0.99 | 0.99 | 0.99 |
MobileNet V1 | 3,244,239 | 12.38 MB | 0.758443 | 6,488,588 | 16,843,215 | 0.99 | 0.99 | 0.99 | 0.99 |
MobileNet V2 | 2,277,199 | 8.69 MB | 1.361673 | 4,554,633 | 21,814,975 | 1.0 | 1.0 | 1.0 | 1.0 |
MobileNet V3 Large | 3,010,767 | 11.49 MB | 1.343 | 6,011,595 | 19,962,943 | 0.99 | 0.99 | 0.99 | 0.99 |
MobileNet V3 Small | 947,775 | 3.62 MB | 1.812190 | 1,889,937 | 7,755,103 | 1.00 | 1.00 | 1.00 | 1.00 |
