CAR DAMAGE DETECTOR

WHAT IS IT?

MASKED Rcnn based car damage detector. Pipeline is as follows: A) Extracting Regions of Interest(ROI) An: By masked Rcnn B) Classification task: Regions are passed on to a fully connected network which classifies them into different image classes. In our case, it will be scratch(‘damage’) or background(car body without damage). C) Regression task: At last, a bounding box(BB) regression is used to predict the bounding boxes for each identified region for tightening the bounding boxes(getting exact BB defining relative coordinates)

How to use? To run the inference script run command RUN COMMANDS INSIDE CAR DETECTION FOLDER python run.py splash --weights mas k_rcnn_damage_0100.h5 --image 22.jpg

WHAT ARE THE REQUIREMENTS?

To get all the requirements and dependencies installed run the command For GPU - pip install -r gpu_requirements.txt For CPU - pip install -r cpu_requirements.txt