search

keras-team / keras-cv

Industry-strength Computer Vision workflows with Keras
Other
1.01k stars 330 forks source link

keras_cv.models.YOLOV8Detector.from_preset("efficientnetv2_b2_imagenet") fails #1793

Closed LukeWood closed 1 year ago

LukeWood commented 1 year ago

TypeError: YOLOV8Detector.init() missing required positional argument: 'backbone'

Also, it tries to provide multiple "num_classes" values. Lets add a polish to this flow.

ianstenbit commented 1 year ago

This looks like it's because the init args are in a different order for YOLOV8Detector vs RetinaNet. I'll try to send a fix today. I assume you know how to work around in the meantime @LukeWood

LukeWood commented 1 year ago

Yes sir, just filing bugs as I demo the API a bit :)