keras-team/keras-io

Pre-trained ResNet50 as backbone of YOLOv8

SaraDadjouy opened this issue · 3 comments

SaraDadjouy commented

Hello! I want to do an object detection task and read this Efficient Object Detection with YOLOV8 and KerasCV.

I have a pre-trained ResNet50 model and want to use it as the backbone with YOLOv8Detector. But I'm not sure if it is even possible. Would you please help me with this on how can I do this?

sachinprasadhs commented

I'm not sure if you can use ResNet50 as backbone for YOLOv8Detector.

Probably you can give it a try by providing ResNet backbone in the below code snippet.

 yolo = keras_cv.models.YOLOV8Detector(
    num_classes=len(class_mapping),
    bounding_box_format="xyxy",
    backbone=backbone,
    fpn_depth=1,
)

Refer the YOLOv8 architecture here https://blog.roboflow.com/whats-new-in-yolov8/

github-actions commented

This issue is stale because it has been open for 14 days with no activity. It will be closed if no further activity occurs. Thank you.

github-actions commented

This issue was closed because it has been inactive for 28 days. Please reopen if you'd like to work on this further.