Running yolov8 pre-trained model on a free GPU on a CPU for detection for a single class

Question

As a newbie trying object detection for a single class i will be using a free GPU. Can the yolov8 trained model on a free GPU to detect a single class after i have downloaded it on a CPU?

Answer 1

The model will load on GPU if available. Hence, just have to force the inference on CPU by using the device argument in predict.

from ultralytics.yolo.engine.model import YOLO


model = YOLO("yolov8n.pt")

# force to run on CPU by using device flag
results = model.predict(source="0", show=True, stream=True, classes=0, device='cpu')
for i, result in enumerate(results):
    boxes = result.boxes
    for box in boxes:
        xyxy = box.xyxy[0] 

You can double check that you are actually running on CPU by checking your GPU usage with nvtop