A deep neural network model with zero shot learning based on cifar100 data set.
The target of this Project is to create a model to classify images, even images not included in the training data set.
This Project was created with Python(3.8.7), tensorflow, keras, pandas, numpy and more libraries.
In order to understand the steps and what we did you are welcome to look at the research jupyter notebook.
- Clone this repository.
- Open cmd/shell/terminal and go to project folder:
cd Image-classification-zero-shot-learning
- Install project dependencies:
pip install -r requirements.txt
- Run the python script with input image:
python ./src/image_classification.py python "path_to_img"
- Enjoy the application.
Prediction: chimpanzee, chimp, monkey, baboon, orangutan |
Prediction: telephone, phone, telephon, telephones, land-line |
Prediction: rose, flower, tulip, carnation, marigold |
Prediction: elephant, tiger, lion, tusker, leopard |
Prediction: woodlouse, snake, crab, leatherjacket, blobfish |
Prediction: orange, purple, yellow, pink, red |
Please let me know if you find bugs or something that needs to be fixed.
Hope you enjoy.
@inproceedings{mikolov2018advances,
title={Advances in Pre-Training Distributed Word Representations},
author={Mikolov, Tomas and Grave, Edouard and Bojanowski, Piotr and Puhrsch, Christian and Joulin, Armand},
booktitle={Proceedings of the International Conference on Language Resources and Evaluation (LREC 2018)},
year={2018}
}