Table 4 Comparison of the performance of different feature extraction networks
From: Material classification method of traditional Chinese painting image based on prototypical network
Model | Accuracy(%) | Precision(%) | Recall(%) | F1(%) |
|---|---|---|---|---|
CNN6 | 33.1 | 32.8 | 33.1 | 31.3 |
ResNet18 | 69.0 | 73.0 | 69.0 | 68.6 |
RestNet34 | 38.6 | 34.8 | 38.6 | 31.6 |
RestNet50 | 40.9 | 42.9 | 40.9 | 38.8 |
