Table 5.
Number of parameters and trainable parameters in transfer learning models and the proposed model
Model Name | Input Image Dimensions | Total number of parameters | Number of trainable parameters |
---|---|---|---|
VGG16 | 224 × 224 × 3 | 134,276,932 | 16,388 |
VGG19 | 224 × 224 × 3 | 139,586,628 | 16,388 |
MobileNetV2 | 224 × 224 × 3 | 2,263,108 | 5124 |
EfficientNet B0 | 224 × 224 × 3 | 4,054,688 | 5124 |
EfficientNet B2 | 260 × 260 × 3 | 7,774,198 | 5636 |
InceptionV3 | 299 × 299 × 3 | 21,810,980 | 8196 |
ResNetV2_152 | 224 × 224 × 3 | 58,339,844 | 8196 |
InceptionResNetV2 | 299 × 299 × 3 | 54,342,884 | 6148 |
NASNetMobile | 224 × 224 × 3 | 4,273,944 | 4228 |
The proposed model | 224 × 224 × 3 | 1,043,558 | 1,043,558 |