sebastiansarasti/EfficientNetWildFireClassifier

EfficientNetWildFireModel for Wildfire Classification

Model Details

• Model Architecture: EfficientNet-B0 (Modified)
• Framework: PyTorch
• Input Shape: 3-channel RGB images
• Number of Parameters: ~5.3M (Based on EfficientNet-B0)
• Output: Binary classification (wildfire presence)

Model Description

This model is a fine-tuned EfficientNet-B0 for wildfire classification. The pretrained EfficientNet-B0 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, predicting the presence of wildfire.

Training Details

• Optimizer: Adam
• Batch Size: 32
• Loss Function: Binary Cross-Entropy (BCE)
• Number of Epochs: 10
• Dataset: Wildfire Detection Image Data

Losses Per Epoch

Epoch	Training Loss	Validation Loss
1	0.1859	0.0699
2	0.0553	0.0580
3	0.0263	0.0576
4	0.0146	0.0553
5	0.0105	0.0555
6	0.0080	0.0554
7	0.0062	0.0554
8	0.0052	0.0559
9	0.0043	0.0550
10	0.0037	0.0563

License

This model is released under the MIT License.

---