search

mrnabati / RRPN

Code for 'RRPN: Radar Region Proposal Network for Object Detection in Autonomous Vehicles' (ICIP 2019)
MIT License
97 stars 35 forks source link

Wrong lable in the infer result #7

Closed punknownq closed 4 years ago

punknownq commented 4 years ago

Hi.Thank you for your work. I have got the output of the RRPN which is right. However, I got wrong lables after ran inference on the validation set images. Can you help me? For example, the person in the image is labeled "car" and the car in the image is labeled "person".

mrnabati commented 4 years ago

This is because of a mismatch between the category IDs in COCO and nuCOCO. A quick fix is to modify the "get_coco_dataset()" function in "detectron/datasets/dummy_datasets.py" and change "classes" from

classes = [ '__background__', 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', 'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush' ]

to

classes = [ '__background__', 'car', 'truck', 'person', 'motorcycle', '_', 'bicycle', '_', 'bus' ]

punknownq commented 4 years ago

Thank you for your reply!