This project intend to train the Yolo Model for detect and recognize different type of component in document. This object detection output can use for advance Document Automation Application
-
Yolo Computer Vision Realtime Object Detection Model
- this project used State-of-Art Pre-trained Yolo model for fine tuning the document layout detection
-
Train Dataset
- the project used open source documment layout dataset for training model
-
custom label image
- use requirements.txt for installation package dependencies
-
dev folder : for testing tdifferent YOLO model with sample document/image
-
yoloTraing: for training custom model for document layout detection