NudeNet: Neural Nets for Nudity Classification, Detection and selective censoring

Classifier classes:

Detector classes:

Usage

As Python module

Installation:

pip install --upgrade nudenetupdated

Classifier Usage:

# Import module
from nudenet import NudeClassifier

# initialize classifier (downloads the checkpoint file automatically the first time)
classifier = NudeClassifier()

# Classify single image
classifier.classify('path_to_image_1')
# Returns {'path_to_image_1': {'safe': PROBABILITY, 'unsafe': PROBABILITY}}
# Classify multiple images (batch prediction)
# batch_size is optional; defaults to 4
classifier.classify(['path_to_image_1', 'path_to_image_2'], batch_size=BATCH_SIZE)
# Returns {'path_to_image_1': {'safe': PROBABILITY, 'unsafe': PROBABILITY},
#          'path_to_image_2': {'safe': PROBABILITY, 'unsafe': PROBABILITY}}

Detector Usage:

# Import module
from nudenet import NudeDetector

# initialize detector (downloads the checkpoint file automatically the first time)
detector = NudeDetector() # detector = NudeDetector('base') for the "base" version of detector.

# Detect single image
detector.detect('path_to_image')
# fast mode is ~3x faster compared to default mode with slightly lower accuracy.
detector.detect('path_to_image', mode='fast')
# Returns [{'box': LIST_OF_COORDINATES, 'score': PROBABILITY, 'label': LABEL}, ...]

Developpers

To get started, simply clone the repository and install the dependencies:

poetry install

Once the dependencies are installed, you can start developing your project.

Notes

• Current version of NudeDetector is trained on 160,000 entirely auto-labelled (using classification heat maps and various other hybrid techniques) images.
• The entire data for the classifier is available at https://archive.org/details/NudeNet_classifier_dataset_v1
• A part of the auto-labelled data (Images are from the classifier dataset above) used to train the base Detector is available at https://github.com/notAI-tech/NudeNet/releases/download/v0/DETECTOR_AUTO_GENERATED_DATA.zip

Fork notes

• The original project made by notAI-tech is here
• The forked version made by platelminto taken for this project is here

Contributing

If you have any suggestions for improvements, please feel free to open an issue or submit a pull request.

License

This project is licensed under the MIT License.