This repo contains a PyTorch implementation of a CNN model for multi-label Image classification.Here we predict various facial attributes such as finding people with brown hair, are smiling, or wearing glasses. This type of problem comes under multi label image classification where an instance can be classified into multiple classes among the predefined classes.
Dataset can be obtained from kaggle CelebFaces-Attributes.
Dataset consist of 202,599 number of face images of various celebrities with 40 binary attribute annotations per image.
- Install Python3
- Clone repository
git clone https://github.com/kartikbatra056/CelebFaces-Attributes-Prediction.git
- Enter cloned directory
cd CelebFaces-Attributes-Prediction
- Install dependencies
pip3 install -r requirements.txt
- Deploy the app
python3 app.py
- Open a web browser and go to
http://localhost:5000