Python 更新：从视频结果形状捕获[：2]错误

更新：现在工作后，我检查视频正在加载，但现在我有以下内容

      File "real_time_object_detection.py", line 69, in <module>
    inpWidth = args.width if args.width else frameWidth
AttributeError: 'dict' object has no attribute 'width'

这里是通过命令行运行的

$python real\u time\u object\u detection.py--prototxt mobilenetsdsd\u deploy.prototxt.txt--model mobilenetsd\u deploy.caffemodel--video ped.mp4

这是全部代码

from imutils.video import VideoStream
from imutils.video import FPS
import numpy as np
import argparse
import imutils
import time
import cv2

ap = argparse.ArgumentParser()
ap.add_argument("-p", "--prototxt", required=True,
    help="path to Caffe 'deploy' prototxt file")
ap.add_argument("-m", "--model", required=True,
    help="path to Caffe pre-trained model")
ap.add_argument("-c", "--confidence", type=float, default=0.2,
    help="minimum probability to filter weak detections")
ap.add_argument("-v", "--video", required=True,
    help="path to input video file")
args = vars(ap.parse_args())

CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
    "bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
    "dog", "horse", "motorbike", "person", "pottedplant", "sheep",
    "sofa", "train", "tvmonitor"]
COLORS = np.random.uniform(0, 255, size=(len(CLASSES), 3))

print("[INFO] loading model...")
net = cv2.dnn.readNetFromCaffe(args["prototxt"], args["model"])

print("[INFO] starting video stream...")
vs = cv2.VideoCapture(args["video"])
time.sleep(2.0)
fps = FPS().start()


while True:


    frame = cv2.VideoCapture(args["video"])
    frame = imutils.resize(frame, width=450)
    frame = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
    frame = np.dstack([frame, frame, frame])


    frameHeight = frame.shape[0]
    frameWidth = frame.shape[1]

    inpWidth = args.width if args.width else frameWidth
    inpHeight = args.height if args.height else frameHeight
    blob = cv2.dnn.blobFromImage(frame, args.scale, (inpWidth, inpHeight), args.mean, args.rgb, crop=False)

    net.setInput(blob)
    if net.getLayer(0).outputNameToIndex('im_info') != -1:  # Faster-RCNN or R-FCN
        frame = cv2.resize(frame, (inpWidth, inpHeight))
        net.setInput(np.array([inpHeight, inpWidth, 1.6], dtype=np.float32), 'im_info');
    outs = net.forward(getOutputsNames(net))

    for i in np.arange(0, detections.shape[2]):

        confidence = detections[0, 0, i, 2]


        if confidence > args["confidence"]:
            idx = int(detections[0, 0, i, 1])
            box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
            (startX, startY, endX, endY) = box.astype("int")

            label = "{}: {:.2f}%".format(CLASSES[idx],
                confidence * 100)
            cv2.rectangle(frame, (startX, startY), (endX, endY),
                COLORS[idx], 2)
            y = startY - 15 if startY - 15 > 15 else startY + 15
            cv2.putText(frame, label, (startX, y),
                cv2.FONT_HERSHEY_SIMPLEX, 0.5, COLORS[idx], 2)

    cv2.imshow("Frame", frame)
    key = cv2.waitKey(1) & 0xFF

    if key == ord("q"):
        break

    fps.update()

fps.stop()
print("[INFO] elapsed time: {:.2f}".format(fps.elapsed()))
print("[INFO] approx. FPS: {:.2f}".format(fps.fps()))

cv2.destroyAllWindows()
vs.stop()

---

在行

frame=cv2.VideoCapture（args[“video”]）

之后，检查

frame

是否为空not@JeruLuke我添加了几行代码来检查视频捕获，它返回空帧，但视频存在于同一目录中，然后我认为渲染可能有问题，所以我安装了ffmpeg包，仍然没有解决问题。我将args参数改为绝对路径仍然不起作用。Mp4 ext可能有问题吗？检查。@zindarod谢谢，我检查了帖子上的所有步骤，一切正常，问题出在其他地方

from imutils.video import VideoStream
from imutils.video import FPS
import numpy as np
import argparse
import imutils
import time
import cv2

ap = argparse.ArgumentParser()
ap.add_argument("-p", "--prototxt", required=True,
    help="path to Caffe 'deploy' prototxt file")
ap.add_argument("-m", "--model", required=True,
    help="path to Caffe pre-trained model")
ap.add_argument("-c", "--confidence", type=float, default=0.2,
    help="minimum probability to filter weak detections")
ap.add_argument("-v", "--video", required=True,
    help="path to input video file")
args = vars(ap.parse_args())

CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
    "bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
    "dog", "horse", "motorbike", "person", "pottedplant", "sheep",
    "sofa", "train", "tvmonitor"]
COLORS = np.random.uniform(0, 255, size=(len(CLASSES), 3))

print("[INFO] loading model...")
net = cv2.dnn.readNetFromCaffe(args["prototxt"], args["model"])

print("[INFO] starting video stream...")
vs = cv2.VideoCapture(args["video"])
time.sleep(2.0)
fps = FPS().start()


while True:


    frame = cv2.VideoCapture(args["video"])
    frame = imutils.resize(frame, width=450)
    frame = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
    frame = np.dstack([frame, frame, frame])


    frameHeight = frame.shape[0]
    frameWidth = frame.shape[1]

    inpWidth = args.width if args.width else frameWidth
    inpHeight = args.height if args.height else frameHeight
    blob = cv2.dnn.blobFromImage(frame, args.scale, (inpWidth, inpHeight), args.mean, args.rgb, crop=False)

    net.setInput(blob)
    if net.getLayer(0).outputNameToIndex('im_info') != -1:  # Faster-RCNN or R-FCN
        frame = cv2.resize(frame, (inpWidth, inpHeight))
        net.setInput(np.array([inpHeight, inpWidth, 1.6], dtype=np.float32), 'im_info');
    outs = net.forward(getOutputsNames(net))

    for i in np.arange(0, detections.shape[2]):

        confidence = detections[0, 0, i, 2]


        if confidence > args["confidence"]:
            idx = int(detections[0, 0, i, 1])
            box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
            (startX, startY, endX, endY) = box.astype("int")

            label = "{}: {:.2f}%".format(CLASSES[idx],
                confidence * 100)
            cv2.rectangle(frame, (startX, startY), (endX, endY),
                COLORS[idx], 2)
            y = startY - 15 if startY - 15 > 15 else startY + 15
            cv2.putText(frame, label, (startX, y),
                cv2.FONT_HERSHEY_SIMPLEX, 0.5, COLORS[idx], 2)

    cv2.imshow("Frame", frame)
    key = cv2.waitKey(1) & 0xFF

    if key == ord("q"):
        break

    fps.update()

fps.stop()
print("[INFO] elapsed time: {:.2f}".format(fps.elapsed()))
print("[INFO] approx. FPS: {:.2f}".format(fps.fps()))

cv2.destroyAllWindows()
vs.stop()