| | --- |
| | license: mit |
| | --- |
| | |
| | # VGGWildFireModel for Wildfire Classification |
| |
|
| | ## Model Details |
| |
|
| | - **Model Architecture:** VGG-16 (Modified) |
| | - **Framework:** PyTorch |
| | - **Input Shape:** 3-channel RGB images |
| | - **Number of Parameters:** ~ (Based on VGG-16) |
| | - **Output:** Binary classification (wildfire presence) |
| |
|
| | ## Model Description |
| |
|
| | This model is a **fine-tuned VGG-16** for wildfire classification. The pretrained **VGG-16** backbone is used with its feature extractor **frozen**, while only the **final classification layer** is trained. The last fully connected layer has been replaced with a **single output neuron** for binary classification. |
| |
|
| | ## Training Details |
| |
|
| | - **Optimizer:** Adam |
| | - **Batch Size:** 32 |
| | - **Loss Function:** Binary Cross-Entropy |
| | - **Number of Epochs:** 10 |
| | - **Dataset:** [Wildfire Detection Image Data](https://www.kaggle.com/datasets/brsdincer/wildfire-detection-image-data) |
| |
|
| | ### Losses Per Epoch |
| |
|
| | | Epoch | Training Loss | Validation Loss | |
| | |-------|--------------|----------------| |
| | | 1 | 0.2571 | 0.3858 | |
| | | 2 | 0.0846 | 0.1935 | |
| | | 3 | 0.0165 | 0.1573 | |
| | | 4 | 0.0013 | 0.1204 | |
| | | 5 | 0.0001 | 0.1243 | |
| | | 6 | 0.0000 | 0.1247 | |
| | | 7 | 0.0000 | 0.1244 | |
| | | 8 | 0.0000 | 0.1242 | |
| | | 9 | 0.0000 | 0.1240 | |
| | | 10 | 0.0000 | 0.1236 | |
| |
|
| | ## License |
| |
|
| | This model is released under the **MIT License**. |
| |
|
| | --- |
| |
|
