python torch opencv调用摄像头识别物体

一环境配置:
1,python安装
2,matplotlib
3,torch
4,torchvision
python 3.10 或3.9 版本,pip直接安装
二 代码,

# Load libraries

from PIL import Image
import matplotlib.pyplot as plt
import torch
import torchvision.transforms as T
import torchvision
import numpy as np
import cv2
import threading

model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True)
model.eval()

COCO_INSTANCE_CATEGORY_NAMES = [
    '__background__', 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus',
    'train', 'truck', 'boat', 'traffic light', 'fire hydrant', 'N/A', 'stop sign',
    'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
    'elephant', 'bear', 'zebra', 'giraffe', 'N/A', 'backpack', 'umbrella', 'N/A', 'N/A',
    'handbag', 'tie', 'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball',
    'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 'tennis racket',
    'bottle', 'N/A', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl',
    'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza',
    'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed', 'N/A', 'dining table',
    'N/A', 'N/A', 'toilet', 'N/A', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
    'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'N/A', 'book',
    'clock', 'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush'
]

def get_prediction(img_path, threshold,img):
    #img = Image.open(img_path)
    transform = T.Compose([T.ToTensor()]) 
    img = transform(img) 
    pred = model([img]) 
    pred_class = [COCO_INSTANCE_CATEGORY_NAMES[i] for i in list(pred[0]['labels'].numpy())] 
    pred_boxes = [[(i[0], i[1]), (i[2], i[3])] for i in list(pred[0]['boxes'].detach().numpy())]
    pred_score = list(pred[0]['scores'].detach().numpy())
    pred_t = [pred_score.index(x) for x in pred_score if x > threshold][-1] 
    pred_boxes = pred_boxes[:pred_t+1]
    pred_class = pred_class[:pred_t+1]
    #print("pred_class:",pred_class)
    #print("pred_boxes:",pred_boxes)
    return pred_boxes, pred_class,pred_score

def object_detection_api(img_path, threshold=0.5, rect_th=3, text_size=1, text_th=1):
    #boxes, pred_cls = get_prediction(img_path, threshold) 
    addr = "rtsp://admin:admin@192.168.31.109:554/stream2";
    cap=cv2.VideoCapture(addr)
    if cap.isOpened():
        ret, frame = cap.read()
        if ret:
            img = frame
            img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
            boxes, pred_cls,score = get_prediction(img_path, threshold,frame)
            for i in range(len(boxes)):
                if (score[i]>0.85):
                    cv2.rectangle(img,(int( boxes[i][0][0]),int( boxes[i][0][1])),(int( boxes[i][1][0]),int( boxes[i][1][1])),color=(0, 255, 0), thickness=rect_th)
                    cv2.putText(img,pred_cls[i], (int( boxes[i][0][0]),int( boxes[i][0][1])),  cv2.FONT_HERSHEY_SIMPLEX, text_size, (0,255,0),thickness=text_th)
    cap.release()
    #cv2.destroyAllWindows()
    return img
    #plt.imshow(img)
   # plt.show()
def cammera():
    addr = "rtsp://admin:admin@192.168.31.109:554/stream2";
    cap=cv2.VideoCapture(addr)
    while cap.isOpened():
        ret, frame = cap.read()
        if ret:
            img = frame
            cv2.imshow('fr', img)
            cv2.waitKey(1)
    

def imgthread ():
    while True:
        image=object_detection_api(img_path="1234.jpg")
        cv2.imshow('frame', image)
        cv2.waitKey(1)
    

if __name__ == '__main__':
   # imgth=threading.Thread(target=cammera ,name='cammerath')
   # imgth.start()
    th=threading.Thread(target=imgthread,name='aa')
    th.start()
    
    

三 代码解析
model 函数原型
def fasterrcnn_resnet50_fpn(pretrained=False, progress=True,
num_classes=91, pretrained_backbone=True, trainable_backbone_layers=3, **kwargs):
参数：
pretrianed（bool）：如果为真，返回一个在 COCO train2017 上的预训练模型。
progress（bool）：如果为真，将下载进度条展示在屏幕。
pretrained_backbone（bool）：如果为真，返回一个在 Imagenet 上的主干网络预训练模型。
num_classes（int）：模型输出的种类数量（包括背景）。
trainable_backbone_layers（int）：从最后一个块开始可训练 ResNet 层的数量（未被冻结）。合法的值在 0~5 之间，5 意味着所有主干网络的层都是可训练的。