---
library_name: keras
pipeline_tag: image-classification
tags:
  - keras
  - tensorflow
  - computer-vision
  - image-classification
  - fire-detection
  - wildfire-detection
  - binary-classification
  - transfer-learning
---

# Fire Detection Models

A collection of trained deep learning models for binary fire detection.

These models classify an input image into one of two classes:

- **Fire**
- **No Fire**

The repository contains multiple CNN architectures trained as part of a broader deep learning project focused on fire detection and wildfire-related computer vision.

## Models

| Model | Architecture | Task |
|---|---|---|
| `Custom_CNN_binary_classification.keras` | Custom CNN | Fire / No Fire |
| `efficientnetb0_binary_classification.keras` | EfficientNetB0 | Fire / No Fire |
| `resnet50_binary_classification.keras` | ResNet50 | Fire / No Fire |
| `vgg16_binary_classification_finalized.keras` | VGG16 | Fire / No Fire |

## Model Format

All models are saved using the Keras `.keras` format.

```python
import tensorflow as tf

model = tf.keras.models.load_model(
    "efficientnetb0_binary_classification.keras"
)

model.summary()
```

Replace the filename with the model you want to load.

## Intended Use

These models are intended for:

- research
- experimentation
- educational purposes
- model comparison
- further fine-tuning
- development of fire-detection applications

## Limitations

Model performance depends on the dataset, preprocessing pipeline, image quality, and deployment environment.

The models should be independently evaluated on an appropriate test dataset before being used in real-world or safety-critical applications.

## Project Context

These models are part of a larger deep learning project containing:

- fire detection
- fire severity classification
- feature extraction
- dimensionality reduction
- clustering
- recommendation generation
- supporting datasets and notebooks

## License

No standardized open-source license has been specified for this repository.

Please refer to the original project and dataset terms before redistribution or commercial use.