Add webcam livetracking.

main.py

+import torch
+import cv2
+import time
+import matplotlib.pyplot as plt
+
+# Model
+model = torch.hub.load('ultralytics/yolov5', 'yolov5l')  # or yolov5m, yolov5l, yolov5x, cu
+# model = torch.hub.load('ultralytics/yolov3', 'yolov3')
+
+
+def show(img):
+    plt.imshow(img)
+    plt.show()
+
+classes = ["person", "bicycle", "car", "motorbike", "aeroplane", "bus",
+           "train", "truck", "boat", "traffic light", "fire hydrant",
+           "stop sign", "parking meter", "bench", "bird", "cat", "dog",
+           "horse", "sheep", "cow", "elephant", "bear", "zebra", "giraffe",
+           "backpack", "umbrella", "handbag", "tie", "suitcase", "frisbee",
+           "skis", "snowboard", "sports ball", "kite", "baseball bat",
+           "baseball glove", "skateboard", "surfboard", "tennis racket",
+           "bottle", "wine glass", "cup", "fork", "knife", "spoon", "bowl",
+           "banana", "apple", "sandwich", "orange", "broccoli", "carrot",
+           "hot dog", "pizza", "donut", "cake", "chair", "sofa", "pottedplant",
+           "bed", "diningtable", "toilet", "tvmonitor", "laptop", "mouse", "remote",
+           "keyboard", "cell phone", "microwave", "oven", "toaster", "sink", "refrigerator",
+           "book", "clock", "vase", "scissors", "teddy bear", "hair drier", "toothbrush"]
+
+
+def debug_preds():
+    detected_classes = [int(results.pred[0][i][-1]) for i in range(0, len(results.pred[0]))]
+    print(detected_classes)
+    for det in results.pred[0]:
+        if int(det[-1]) == 0:  # person
+            print("Person ({}):".format(float(det[-2])))
+            print("x1:y1 : {}:{}".format(float(det[0]), float(det[1])))
+            print("x2:y2 : {}:{}".format(float(det[2]), float(det[3])))
+
+
+if __name__=="__main__":
+
+    # set start time to current time
+    start_time = time.time()
+
+    # displays the frame rate every 2 second
+    display_time = 2
+
+    # Set primary FPS to 0
+    fps = 0
+
+    # we create the video capture object cap
+    cap = cv2.VideoCapture(0)
+    if not cap.isOpened():
+        raise IOError("We cannot open webcam")
+
+    while True:
+        ret, frame = cap.read()
+        # resize our captured frame if we need
+        frame = cv2.resize(frame, None, fx=1.0, fy=1.0, interpolation=cv2.INTER_AREA)
+
+        # detect object on our frame
+        results = model(frame.copy())
+        # debug_preds()
+
+
+        # show us frame with detection
+        # cv2.imshow("Web cam input", frame)
+        cv2.imshow("img", results.render()[0])
+        if cv2.waitKey(25) & 0xFF == ord("q"):
+            cv2.destroyAllWindows()
+            break
+
+        # calculate FPS
+        fps += 1
+        TIME = time.time() - start_time
+        if TIME > display_time:
+            print("FPS:", fps / TIME)
+            fps = 0
+            start_time = time.time()
+
+    cap.release()
+    cv2.destroyAllWindows()