|
|
--- |
|
|
license: mit |
|
|
language: |
|
|
- en |
|
|
--- |
|
|
|
|
|
# LeNet for Wildfire Classification |
|
|
|
|
|
## Model Details |
|
|
|
|
|
- **Model Architecture:** LeNet (Modified) |
|
|
- **Framework:** PyTorch |
|
|
- **Input Shape:** 3-channel RGB images |
|
|
- **Number of Parameters:** ~ (Calculated based on input size) |
|
|
- **Output:** Binary classification (wildfire presence) |
|
|
|
|
|
## Model Description |
|
|
|
|
|
This model is a modified version of the classic **LeNet** architecture, adapted for **wildfire classification**. It consists of two convolutional layers followed by three fully connected layers. The model was trained using **ReLU activations**, **max pooling**, and a **final linear layer** for binary classification. |
|
|
|
|
|
## Training Details |
|
|
|
|
|
- **Optimizer:** Adam |
|
|
- **Loss Function:** Binary Cross-Entropy |
|
|
- **Batch Size:** 32 |
|
|
- **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 | 0.8609 | 0.3632 | |
|
|
| 2 | 0.3368 | 0.3023 | |
|
|
| 3 | 0.2723 | 0.2852 | |
|
|
| 4 | 0.1966 | 0.1914 | |
|
|
| 5 | 0.2889 | 0.2610 | |
|
|
| 6 | 0.1914 | 0.2747 | |
|
|
| 7 | 0.2148 | 0.2520 | |
|
|
| 8 | 0.1643 | 0.1751 | |
|
|
| 9 | 0.1938 | 0.1929 | |
|
|
| 10 | 0.1130 | 0.2095 | |
|
|
|
|
|
## License |
|
|
|
|
|
This model is released under the **MIT License**. |
|
|
|
|
|
--- |
