CatDogVision is a project focused on recognizing images of dogs and cats using a neural network. This project was created for fun and educational purposes.
The goal of this project is to develop a deep learning model that can classify images as either "dog" or "cat" with high accuracy. It serves as a great opportunity to learn about neural networks and image classification.
Note: For relatively good results, it is recommended to train the model for around 100 epochs.
- Python Min. 3.9 - Max. 3.11 (
⚠️ Hardlimit)
-
Clone this repository to your local machine.
-
Ensure you have Python 3.11 or lower installed.
-
Install the necessary dependencies by running the following command:
pip install -r requirements.txt
- Install all required libraries.python train.py
- Train your model.python test.py
- Test your model.pip freeze > requirements.txt
- generate new requirements.txt (ONLY FOR CONTRIBUTORS)
- You can now start working with the project.
-
Make sure to have your dataset of dog and cat images in the "data/train" directory.
-
Customize the neural network model in the
train.py
file to suit your needs. -
Train the model by running:
-
Once the model is trained, you can use it for image classification.
Any suggestions for changes are welcome, if you would like to know what else we would like to do in this project here is a link to the todo list.
This project is made possible with the help of the following libraries:
- Numpy: numpy.org
- Tensorflow: tensorflow.org
- Flask: flask.palletsprojects.com
Feel free to explore and expand upon this project for your own learning and enjoyment! 😊