Metadata-Version: 2.4
Name: Intraoralphoto-classifier
Version: 0.1.0
Summary: Intraoral photo classification with ResNet18
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: torch
Requires-Dist: torchvision
Requires-Dist: pillow
Requires-Dist: pandas
Requires-Dist: numpy
Requires-Dist: tqdm
Requires-Dist: opencv-python-headless
Requires-Dist: scikit-learn
Requires-Dist: wandb
Requires-Dist: seaborn
Requires-Dist: matplotlib

# Intraoral-photo-classification

This repository provides a deep learning system for classifying intraoral dental photographs into five standard orthodontic viewpoints:

- center
- up (upper occlusal)
- down (lower occlusal)
- left
- right

The project evaluates preprocessing, data augmentation strategies, multiple image resolutions, and two versions of ResNet-18 (pretrained and trained from scratch).

## 1. Installation

Install from source:

```bash
git clone https://github.com/AImageLab-zip/Intraoral-photo-classification
cd Intraoral-photo-classification
pip install -e .
```

The framework automatically uses GPU if available; otherwise CPU is used.


## 2. Inference

```python
from intraoral_classifier.config import get_device
from intraoral_classifier.infer import run_inference

run_inference(
    patient_dir="<path_to_patient_folder>",
    model_path="<best_model.pth>",
    output_dir="<results_folder>",
    device=get_device(),
)
```

## 3. Model Weights or Checkpoints
Download the model Here: https://drive.google.com/drive/u/0/folders/1LM9fIciXma-2ak9nyRqOzRrinzIH7K0S
