This Streamlit application allows users to upload images and get predictions from the CLIP model developed by OpenAI. The CLIP model, which stands for "Contrastive Language-Image Pre-training," is a state-of-the-art artificial intelligence model capable of understanding both images and text.
- Upload images: Users can upload images directly to the app interface.
- Get predictions: The app uses the CLIP model to predict the class or content depicted in the uploaded image based on its visual features and any accompanying text description.
- Clone this repository to your local machine.
- Install the required dependencies using
pip install -r requirements.txt. - Run the Streamlit app using
streamlit run app.py. - Once the app is running, upload an image using the provided file uploader.
- Wait for the app to process the image and display the predictions.
The CLIP model is a powerful AI model developed by OpenAI that can understand both images and text. It achieves this by training on a large dataset of image-text pairs using a technique called contrastive learning. This enables the model to learn a joint representation space where images and text are semantically similar if they describe the same concept.
This app was created by Isaac Bravo & Katharina Prasse. It uses the CLIP model developed by OpenAI.