Retrieve confidence value Yolov5

Question

I'm using this code to load the yolov5 model model = torch.hub.load('ultralytics/yolov5', 'custom', 'C:\Object Detection\yolov5_object_detection\last.pt') and how can I retrieve the confidence value after the model detected on an image?

Answer 1

Load the model, feed an image to it, loop through the predictions and extract their contents.

model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True)
model.eval()
det = model(img)  # feed image

for *xyxy, conf, cls in det:  # loop through results and extract contents
    print(*xyxy)
    print(conf)   # what you are looking for
    print(cls)