Table 4 Overall model performance.

From: Deep learning-based disease detection in potato and mango leaves: a comparative study of CNN, AlexNet, ResNet, and EfficientNet

Model

Training Accuracy (%)

Validation Accuracy (%)

Test Accuracy (%)

Precision (%)

Recall (%)

F1-score (%)

Baseline CNN

93.67 ± 0.24

93.5 ± 0.31

92.61 ± 0.28

92.5 ± 0.22

92.5 ± 0.25

92.5 ± 0.24

AlexNet

91.3 ± 0.27

90.8 ± 0.33

90.2 ± 0.29

90.6 ± 0.26

90.4 ± 0.23

90.9 ± 0.25

ResNet

97.1 ± 0.18

96.9 ± 0.21

96.7 ± 0.20

95.9 ± 0.17

95.7 ± 0.18

95.8 ± 0.19

EfficientNet

98.2 ± 0.16

97.9 ± 0.18

97.8 ± 0.17

97.6 ± 0.15

97.5 ± 0.14

97.6 ± 0.15

Back to article page