Python 索引器错误：尝试使用face_Recognition自动识别人脸时，列表索引超出范围

我试图将未知人脸保存在视频中，并根据它们出现的第一帧识别它们。例如，如果未知人脸出现在第14帧上，则应将其识别为“新14”，但当出现新人脸时，我不断收到错误“Indexer:list index out range”（索引器：列表索引超出范围）。 这是我的代码和回溯

import face_recognition
import cv2

input_movie = cv2.VideoCapture("video.mp4")
length = int(input_movie.get(cv2.CAP_PROP_FRAME_COUNT))

# Create an output movie file (make sure resolution/frame rate matches input video!)
fourcc = cv2.VideoWriter_fourcc(*'XVID')
output_movie = cv2.VideoWriter('output.avi', fourcc, 29.97, (640, 360))


newimage = face_recognition.load_image_file("anchor.png")
new_face_encoding = face_recognition.face_encodings(newimage)[0]

known_faces = [
    new_face_encoding,

]

# Initialize some variables
face_locations = []
face_encodings = []
face_names = []
frame_number = 0


def recog(frame_number, known_faces, face_names):
    toenc = []

    torec = face_recognition.load_image_file(r"New\Unknown%s.jpg" %str(frame_number))

    #if not len(torec):
     #   print("cannot find image")
    #torec = face_recognition.load_image_file(r"New\Unknown%s.jpg" %str(frame_number))
    toenc.append((face_recognition.face_encodings(torec))[0])
    if not len(toenc):
        print("can't be encoded")
    known_faces.append(toenc.pop())
    face_names.append("new %s" %str(frame_number))      

# Load some sample pictures and learn how to recognize them.

while True:
    # Grab a single frame of video
    ret, frame = input_movie.read()
    frame_number += 1

    # Quit when the input video file ends
    if not ret:
        break

    # Convert the image from BGR color (which OpenCV uses) to RGB color (which face_recognition uses)
    rgb_frame = frame[:, :, ::-1]

    # Find all the faces and face encodings in the current frame of video
    face_locations = face_recognition.face_locations(rgb_frame)
    face_encodings = face_recognition.face_encodings(rgb_frame, face_locations)

    #face_names = []
    for face_encoding in face_encodings:
        # See if the face is a match for the known face(s)
        match = face_recognition.compare_faces(known_faces, face_encoding)


        # If you had more than 2 faces, you could make this logic a lot prettier
        # but I kept it simple for the demo
        name = "Unknown"

        face_names.append(name)

    # Label the results
    for (top, right, bottom, left), name in zip(face_locations, face_names):
        if not name:
            continue

        # Draw a box around the face
        unface = cv2.rectangle(frame, (left, top), (right, bottom), (0, 0, 255), 2)
        if name == "Unknown":
            res = frame[top:bottom, left:right]
            cv2.imwrite(r"New\Unknown%s.jpg" %str(frame_number), res)
            recog(frame_number, known_faces, face_names)

        cv2.rectangle(frame, (left, bottom - 25), (right, bottom), (0, 0, 255), cv2.FILLED)
        font = cv2.FONT_HERSHEY_DUPLEX
        cv2.putText(frame, name, (left + 6, bottom - 6), font, 0.5, (255, 255, 255), 1)

    # Write the resulting image to the output video file
    print("Processing frame {} / {}".format(frame_number, length))
    #output_movie.write(frame)
    cv2.imshow("frame", frame)
    if( cv2.waitKey(27) & 0xFF == ord('q')):
        break

# All done!
input_movie.release()
cv2.destroyAllWindows()

输出

In [1]: runfile('D:/project_new/facerec_from_video_file.py', wdir='D:/project_new')
Processing frame 1 / 3291
Processing frame 2 / 3291
Processing frame 3 / 3291
Processing frame 4 / 3291
Processing frame 5 / 3291
Processing frame 6 / 3291
Processing frame 7 / 3291
Processing frame 8 / 3291
Processing frame 9 / 3291
Processing frame 10 / 3291
Processing frame 11 / 3291
Processing frame 12 / 3291
Traceback (most recent call last):

  File "<ipython-input-1-4b2c69ca71f8>", line 1, in <module>
    runfile('D:/project_new/facerec_from_video_file.py', wdir='D:/project_new')

  File "C:\Users\saber\Anaconda3\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 827, in runfile
    execfile(filename, namespace)

  File "C:\Users\saber\Anaconda3\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 110, in execfile
    exec(compile(f.read(), filename, 'exec'), namespace)

  File "D:/project_new/facerec_from_video_file.py", line 81, in <module>
    recog(frame_number, known_faces, face_names)

  File "D:/project_new/facerec_from_video_file.py", line 35, in recog
    toenc.append((face_recognition.face_encodings(torec))[0])

IndexError: list index out of range

[1]中的

runfile（'D:/project\u new/facerec\u from\u video\u file.py'，wdir='D:/project\u new'）
处理帧1/3291
处理帧2/3291
处理帧3/3291
处理帧4/3291
处理帧5/3291
处理帧6/3291
处理帧7/3291
处理帧8/3291
处理帧9/3291
处理帧10/3291
处理帧11/3291
处理帧12/3291
回溯（最近一次呼叫最后一次）：
文件“”，第1行，在
runfile（'D:/project\u new/facerec\u from\u video\u file.py'，wdir='D:/project\u new'）
文件“C:\Users\saber\Anaconda3\lib\site packages\spyder\u kernels\customize\spyderrcustomize.py”，第827行，在runfile中
execfile（文件名、命名空间）
文件“C:\Users\saber\Anaconda3\lib\site packages\spyder\u kernels\customize\spyderrcustomize.py”，第110行，在execfile中
exec（编译（f.read（），文件名，'exec'），命名空间）
文件“D:/project\u new/facerec\u from\u video\u File.py”，第81行，in
记录（帧编号、已知面、面名称）
文件“D:/project\u new/facerec\u from\u video\u File.py”，第35行，记录
toenc.append（（人脸识别.人脸编码（torec））[0]）
索引器：列表索引超出范围

我不能百分之百肯定这反映了您的情况，但我对

人脸识别库的经验是，它不能总是对某些人脸进行编码。这通常发生在侧面，或者如果他们的视角太扭曲，或者即使有太多的头发覆盖在脸上

就我个人而言

我们可能需要看看您在哪里定义
face\u recognition.face\u encodings（）
。我很好奇它的回报是什么。这是人脸识别库中的一个预定义方法。嗯……请查看您的文档，了解
人脸识别。人脸编码（）
。我想知道如果没有匹配项，它是否会返回一个空集合，因为您的代码似乎假设返回的集合中有项。
encodings = face_recognition.face_encodings(known_image)
if len(encodings) > 0:
    biden_encoding = encodings[0]
else:
   print("No faces found in the image!")
   quit()