GhostNet implementation from scratch for classifying images from the Oxford-IIIT Pet Dataset

• ghostnet.py: Contains the model.
• train.py: Script for training the model.
• evaluate.py: Script for evaluating the model.
• ghostnet_pet_model.pth: Pre-trained weights provided for your convenience.

To train the model, run:

python train.py

First specify the location of your desired image in img_path variable in evaluate.py

Then run the evaluate.py script to make predictions using the trained model:

python evaluate.py

The dataset used for training is the Oxford-IIIT Pet Dataset.

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

• The GhostNet model architecture is inspired by the original GhostNet paper.
• The code is based on the official GhostNet repo.