Table 3.
Parameters for training a deep learing model.
| Name | Parameters |
|---|---|
| Development Environment | Anaconda, Jupyter Notebook, Tensorflow, Keras, OpenCV |
| Processor | Intel Xenon Gold 5218 CPU @ 2.30 GHz, 2.29 GHz |
| Installed RAM | 64 GB |
| Operating System | Windows 10, 64 bit |
| Graphics | NVIDIA, Quadro P600 |
| Graphics Memory | 24 GB |
| Programming Language | Python |
| Input | Image Dataset |
| Input dimension | 416 × 416 |
| Batch Size | 16 |
| Decay | 0.0001 |
| Initial Learning Rate | 0.001 (will reduced to 10−2 times after every 50,000 steps) |
| Momentum | 0.9 |
| Epochs | 250 |
| Optimisation algorithm | Stochastic Gradient Descent (SGD) |