YOLOv8 get predicted class name

Question

I just want to get class data in my python script like: person, car, truck, dog but my output more than this. Also I can not use results as a string.

Python script:

from ultralytics import YOLO

model = YOLO("yolov8n.pt") 
results = model.predict(source="0")

Output:

0: 480x640 1 person, 1 car, 7.1ms
0: 480x640 1 person, 1 car, 7.2ms
0: 480x640 1 person, 1 car, 7.1ms
0: 480x640 1 person, 1 car, 7.1ms
0: 480x640 1 person, 1 car, 7.1ms
0: 480x640 1 person, 7.9ms
0: 480x640 1 person, 7.1ms
0: 480x640 1 person, 1 car, 7.1ms
0: 480x640 1 person, 1 car, 7.1ms

Asked By: gurselturkeri

||

Source

Answer 1

You can pass each class to the model’s name dict like this:

from ultralytics.yolo.engine.model import YOLO
  
model = YOLO("yolov8n.pt")
results = model.predict(stream=True, imgsz=512) # source already setup
names = model.names

for r in results:
    for c in r.boxes.cls:
        print(names[int(c)])

output:

YOLOv8n summary (fused): 168 layers, 3151904 parameters, 0 gradients, 8.7 GFLOPs
bus
person
person
person
person
image 1/2 /home/xyz/ultralytics/ultralytics/assets/bus.jpg: 512x384 4 persons, 1 bus, 35.7ms
person
person
person
tie
tie
image 2/2 /home/xyz/ultralytics/ultralytics/assets/zidane.jpg: 288x512 3 persons, 2 ties, 199.0ms
Speed: 3.9ms pre-process, 117.4ms inference, 27.9ms postprocess per image at shape (1, 3, 512, 512)

Answered By: Mike B

Answer 2

code with a single loop

clist= res[0].boxes.cls
cls = set()
for cno in clist:
    cls.add(model.names[int(cno)])

print(cls)

Answered By: Shreyas

YOLOv8 get predicted class name

Question:

Answers: