Yolov5-face inference ’camera input’ FPS is lower than normal yolov5?

[NoNounknow]

English is not my native language; please excuse typing errors.
“我在使用摄像头输入的数据用以推理的时候发现帧数只有5FPS左右，而使用原版的YOLOV5却有20FPS”
"When I used the data input from the camera for inference, I found that the frame rate was only about 5FPS, while the original YOLOV5 had 20FPS."
以下是我的代码：
Here's my code:

model = torch.hub.load('D:/dl/code/yolov5-face',
                       'custom',
                       'face.pt',
                       source='local')
cap = cv2.VideoCapture(0)
while True:
    ret,frame = cap.read()
    img_cvt = cv2.cvtColor(frame,cv2.COLOR_BGR2RGB)
    results = model(img_cvt)
    results_ = results.xyxy[0].numpy()
    for box in results_:
        l,t,r,b = box[:4].astype('int')
        imgd = cv2.cvtColor(frame, cv2.COLOR_RGB2BGR)
        cv2.rectangle(imgd,(r,b),(l,t),(0,255,0),2)
    cv2.imshow("result",imgd)

I understand now that the default inference device for YOLOv5 Face is the CPU.
Now, I'm trying to perform GPU inference with YOLOv5 Face.

[zryzds]

我也想加入摄像头，方便留下联系方式交流一下吗。打扰了

[NoNounknow]

1015889548，加这个qq吧。 发自我的iPhone

…

------------------ Original ------------------ From: zryzds ***@***.***> Date: Sat,Jul 22,2023 4:15 PM To: deepcam-cn/yolov5-face ***@***.***> Cc: NoNounknow ***@***.***>, Author ***@***.***> Subject: Re: [deepcam-cn/yolov5-face] Yolov5-face inference ’camera input’ FPS is lower than normal yolov5? (Issue #258) 我也想加入摄像头，方便留下联系方式交流一下吗。打扰了 — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: ***@***.***>