This project retrieves thousands of photos of different labels such as "Eastern Bluebird", "Moutains" or "Forest". Then, a Convolutional Neural Network is trained to determine the category of a photo.
This was made as an introduction to CNNs, deep learning, the PyTorch library, and data gathering.
- PyTorch for the CNN model and training
- Flickr API for the pictures scraping
Open the main file of the repo, CNN - Photos Recognotion, and click on "Open in Colab" at the top of the file. To avoid downloading the pictures, you'll have to import the dataset in your GDrive (send me a message for the links).