TTool-AI v1.0.0
What is it
🤖 TTool-AI automates the integration of new tools into AC (Augmented Carpentry), enhancing efficiency and simplifying the process. It is developed in Python and relies on the FastAPI framework. The project is containerized with Docker and Docker Compose. The Training Service is based on PyTorch. The project is developed and tested on Linux (Ubuntu 20.04) with NVIDIA GPUs.
Features:
In this version, TTool-AI offers a basic range of functionalities that streamline the process of video management and model training:
Video Upload and Management
- /upload_videos: Easily upload video files to your dataset.
- /check_upload_video_status: Check the status of your uploaded videos.
- /delete_video: Delete unwanted video.
Machine Learning Model Training and Retrieval
- /get_classes_available: View a list of available classes in the database.
- /train_model: Train custom machine learning models using selected classes.
- /check_train_status: Monitor the progress of the model training.
- /get_train_model: Retrieve trained models and associated labels.
Caveats
For now the server can be accessed only by EPFL users via VPN. We are planning to make the server accessible from outside the EPFL domaine.