RETINA NET FOR OBJECT DETECTION

WHAT IS IT?

Retina Net is a two stage object detector with accuracy more than mobilent and little FLOPS. Here first FPN (Feature Pyramid Network) are used to get the features from image then the image is passed to 2 different network for boundary boxes detection and object detection,to reduce the class imbalance focal loss is used.

HOW TO USE?

To run The Inference Script run this command python run.py --image

SAMPLE COMMAND

python run.py examples/ctyp-lyndale-ave-pedestrian-protest.jpeg

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