An application to assist the visual impaired.

Visual US Team at Accessibility Design Competition 2023.

1. Clone repository.

git clone https://github.com/ngthtinh99/VisualAssistant.git

2. Install Python (Python 3.7 - 3.9 is required for supporting Pytorch).
3. Install necessary libraries.

pip install requests torch torchvision gradio timm fairscale transformers

4. Run the deploy, the first time downloading the model would take about 5-10 minutes, the next time would not need to reload.

python app.py

5. Browse the deploy on Localhost via the link http://localhost:7860, or the Public link generated in Command prompt.
6. Enjoy 🙂

[1] BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation.

[2] Junnan Li, Dongxu Li, Caiming Xiong, Steven Hoi, BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation.

[3] Gradio: Build Machine Learning Web Apps — in Python.