Table 7.
Time complexity.
| No of Epoch | Total Samples | Batch Size | No. of Layers | Input Size | Operations per Batch (approximate) | Batches per Epoch | Operations per Epoch (approximate) | Total Operations (approximate) | |
|---|---|---|---|---|---|---|---|---|---|
| Alexnet | 17 | 6900 | 3 | 8 | 224 × 224 | 1984 | 2300 | 4,571,200 | 77,609,600 |
| MobileNetV2 | 9 | 6900 | 32 | 53 | 224 × 224 | 216 | 11,872 | 2,564,352 | 23,079,168 |
| VGG16 | 4 | 6900 | 32 | 16 | 224 × 224 | 3584 | 216 | 772,864 | 3,091,456 |
| VGG19 | 5 | 6900 | 32 | 19 | 224 × 224 | 4256 | 216 | 919,296 | 4,596,480 |
| ResNet50 | 10 | 6900 | 32 | 50 | 224 × 224 | 32,768 | 216 | 7,083,648 | 7,083,680 |
An in-depth analysis of the computational complexity of the models is provided in Table 7. Understanding these complexities is vital for optimizing training and inference processes and making informed model selection decisions in diverse computational environments. In order to calculate the complexity, the important factors to take into consideration are the following: Number of Epochs, Total Samples, Batch Size, Number of Layers, Input Size, Operations per Batch (approximate), Batches per Epoch, Operations per Epoch (approximate) and Total Operations (approximate). Eq. (9), (10), (11), and (12) represent Operations per Batch, Batches per Epoch, Operations per Epoch and Total Operations sequentially.