- hailo infer node subscribes to an
image topic
- preprocess image via PIL to the
desired image parameters (hard-
coded currently for yolov5m)
- processes inference on hailo chip
- post process and prints bounding boxes
into terminal
- hef files for darias yolov5, yolov5m
and yolov5s added to repo
- minimal data example with image and
daria / coco labels
- inference now allows an async call,
which keeps the connection to the hailo
device open, which allows for a higher
fps rate (as shown in the test example)
- ImageMeta struct saves image metadata
- DataHandler takes care of loading dataset
and parsing the label information
- YoloProcessing takes care of image preprocessing
and yolo postprocessing
- HailoHandler connects to Hailo device, pushes
the desired network hef file and runs the dataset
on the hailo chip
- postprocessing for yolov5 included
- loading hef file of custom yolov5 onto hailo chip
- running inference
- saving image and printing fps for inference
and postprocessing
