Mădălina Burlea@Finallyfound

A web application that runs real-time soldering defect detection using a YOLO model, served via a FastAPI backend. Built to run on AMD GPUs using ROCm — no NVIDIA required. Users upload or stream PCB images through a browser UI, and the app returns annotated results with bounding boxes around detected defects. What It Does Accepts image uploads via a web interface Runs inference using a YOLO model (Ultralytics) with AMD GPU acceleration via ROCm Returns annotated images with detected soldering defects highlighted Includes basic authentication (bcrypt-based) and rate limiting to protect the API Serves a Jinja2-templated frontend from static/

To participate in the hackathon, simply click Sign up with AMD. If you are not already a member of the AMD AI Developer Program (ADP), you will need to create an account. ADP members can access AI tutorials, experts, and community support. In addition, new members can claim a free month of DeepLearning.ai pro, $100 in AMD GPU cloud credits, and $50 in Fireworks AI API credits. All hackathon participants will receive on hackathon launch additional compute and API credits for their projects. Ready to build what's next on AMD? Sign up with AMD below to secure your spot.