前提・実現したいこと

mediapipe公式が提供しているコードを動かしたい

発生している問題・エラーメッセージ

Editor: VSCode, python==3.8.10, mediapipe==0.8.6.2, opencv-python==4.5.3.56, opencv-contrib-python==4.5.3.56, numpy==1.21.1
######Error message on terminal

  File "c:/Users/<username>/Documents/docker-python/HandTrackingMin.py", line 11, in <module>
    with mp_hands.Hands(
  File "C:\Users\<username>\AppData\Roaming\Python\Python38\site-packages\mediapipe\python\solutions\hands.py", line 129, in __init__
    super().__init__(
  File "C:\Users\<username>\AppData\Roaming\Python\Python38\site-packages\mediapipe\python\solution_base.py", line 236, in __init__
    validated_graph.initialize(
FileNotFoundError: The path does not exist.
[ WARN:0] global C:\Users\runneradmin\AppData\Local\Temp\pip-req-build-u4kjpz2z\opencv\modules\videoio\src\cap_msmf.cpp (438) `anonymous-namespace'::SourceReaderCB::~SourceReaderCB terminating async callback

#####on debug mode

例外が発生しました: FileNotFoundError
The path does not exist.
  File "C:\Users\大和\Documents\docker-python\HandTrackingMin.py", line 11, in <module>
    with mp_hands.Hands(

該当のソースコード

python
1import cv2
2import mediapipe as mp
3import time
4import numpy as np
5mp_drawing = mp.solutions.drawing_utils
6mp_hands = mp.solutions.hands
7
8
9# For webcam input:
10cap = cv2.VideoCapture(0)
11with mp_hands.Hands(
12    min_detection_confidence=0.5,
13    min_tracking_confidence=0.5) as hands:
14  while cap.isOpened():
15    time.sleep(1)
16    success, image = cap.read()
17    if not success:
18      print("Ignoring empty camera frame.")
19      # If loading a video, use 'break' instead of 'continue'.
20      continue
21
22    # Flip the image horizontally for a later selfie-view display, and convert
23    # the BGR image to RGB.
24    image = cv2.cvtColor(cv2.flip(image, 1), cv2.COLOR_BGR2RGB)
25    # To improve performance, optionally mark the image as not writeable to
26    # pass by reference.
27    image.flags.writeable = False
28    results = hands.process(image)
29
30    # Draw the hand annotations on the image.
31    image.flags.writeable = True
32    image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
33    if results.multi_hand_landmarks:
34      for hand_landmarks in results.multi_hand_landmarks:
35        mp_drawing.draw_landmarks(
36            image, hand_landmarks, mp_hands.HAND_CONNECTIONS)
37    cv2.imshow('MediaPipe Hands', image)
38    if cv2.waitKey(5) & 0xFF == 27:
39      break
40cap.release()