Metadata-Version: 2.3
Name: nude-classifier-2d-3d
Version: 1.0.3
Summary: A Python package for classifying nude images as real (3D) or drawn (2D) using a pre-trained EfficientNet-B0 model.
License: MIT
Keywords: image-classification,deep-learning,pytorch,efficientnet,nudes
Author: FINWAX
Author-email: waxbid@gmail.com
Requires-Python: >=3.10,<4.0
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Requires-Dist: pillow (>=11.0.0,<12.0.0)
Requires-Dist: torch (>=2.7.0,<3.0.0)
Requires-Dist: torchvision (>=0.22.0,<0.23.0)
Project-URL: Homepage, https://github.com/FINWAX/img-nude-as-3d-or-2d.py
Project-URL: Repository, https://github.com/FINWAX/img-nude-as-3d-or-2d.py
Description-Content-Type: text/markdown

# Nude Classifier

A Python package for binary classification of images to determine if they are real (3D) or drawn (2D) nude images using a pre-trained EfficientNet-B0 model.

## Installation

### Using pip

```bash
pip install nude-classifier-2d-3d
```

### Using Poetry

```bash
poetry add nude-classifier-2d-3d
```

## Requirements
- Python 3.8+
- PyTorch
- torchvision
- PIL (Pillow)

See `requirements.txt` or `pyproject.toml` for a full list of dependencies.

## Usage

```python
from nude_classifier_2d_3d import ClassifyNudeAs2dOr3d

# Initialize the classifier
classifier = ClassifyNudeAs2dOr3d()

# Classify an image
image_path = "path/to/your/image.jpg"
prob_3d = classifier.is_3d_nude_prob(image_path)
prob_2d = classifier.is_2d_nude_prob(image_path)

print(f"Probability of 3D (real) nude: {prob_3d:.2f}")
print(f"Probability of 2D (drawn) nude: {prob_2d:.2f}")
```

## Model Details

- Architecture: EfficientNet-B0
- Input: RGB images (will be resized to 224x224 pixels)
- Output: Probability score for 3D (real) nude images
- Pre-trained Model: Included in the package (models/best_efficientnet_b0.pth)

## License

This project is licensed under the MIT License. See the `LICENSE` file for details.

## Disclaimer

This package is intended for research purposes only. Use responsibly and in compliance with applicable laws and regulations.



