AbdelkadirSellahi/VQA-Using-YOLO-BERT-LSTM

VQA Flood Detection is a deep learning project that combines object detection (YOLOv8) and text understanding (BERT + LSTM) to analyze UAV flood imagery. The system answers user questions by integrating visual and textual features, providing actionable insights for disaster management and emergency response.

语言：Jupyter Notebook · GitHub 星标：4 · Fork：0

在 GitHub 上查看原仓库