|
|
--- |
|
|
license: mit |
|
|
language: |
|
|
- en |
|
|
--- |
|
|
|
|
|
# AlexNetWildFire for Wildfire Classification |
|
|
|
|
|
## Model Details |
|
|
|
|
|
- **Model Architecture:** AlexNet (Modified) |
|
|
- **Framework:** PyTorch |
|
|
- **Input Shape:** 3-channel RGB images |
|
|
- **Number of Parameters:** ~ (Based on AlexNet) |
|
|
- **Output:** Binary classification (wildfire presence) |
|
|
|
|
|
## Model Description |
|
|
|
|
|
This model is a **fine-tuned AlexNet** for wildfire classification. The pretrained **AlexNet** 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 | 0.2161 | 0.2249 | |
|
|
| 2 | 0.1158 | 0.3618 | |
|
|
| 3 | 0.1004 | 0.3120 | |
|
|
| 4 | 0.0213 | 0.3541 | |
|
|
| 5 | 0.0299 | 0.2749 | |
|
|
| 6 | 0.0326 | 0.2352 | |
|
|
| 7 | 0.0032 | 0.2222 | |
|
|
| 8 | 0.0012 | 0.3360 | |
|
|
| 9 | 0.0001 | 0.3072 | |
|
|
| 10 | 0.0000 | 0.2819 | |
|
|
|
|
|
## License |
|
|
|
|
|
This model is released under the **MIT License**. |
|
|
|
|
|
--- |
