我正在编写一个面部识别程序,但不断出现此错误,我非常困惑,我在网络上没有看到其他示例,其中有人在转换为UMat时包含范围
Traceback (most recent call last):
File "test.py", line 48, in <module>
test_photos()
File "test.py", line 40, in test_photos
face, rect = detect_face(test_photo)
File "test.py", line 15, in detect_face
imgUMat = cv2.UMat(img)
TypeError: UMat() missing required argument 'ranges' (pos 2)
我的代码是
def detect_face(img):
imgUMat = cv2.UMat(img)
gray = cv2.cvtColor(imgUMat, cv2.COLOR_BGR2GRAY)
face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + "haarcascade_frontalface_default.xml")
faces = face_cascade.detectMultiScale(gray, scaleFactor=1.2, minNeighbors=5)
if (len(faces)==0):
return None, None
(x, y, w, h) = faces[0]
gray = gray.get()
return gray[y:y+h,x:x+w], faces[0]
def prepare_training_data():
faces = []
labels = []
for img in photo_name_list: #a collection of file locations as strings
image = cv2.imread(img)
face, rect = detect_face(image)
if face is not None:
faces.append(face)
labels.append(me)
return faces, labels
def test_photos():
face_recognizer = cv2.face.LBPHFaceRecognizer_create()
faces, labels = prepare_training_data()
face_recognizer.train(np.array(faces), np.array(labels))
face, rect = detect_face(test_photo)
label = face_recognizer.predict(face)
if label == me:
print("it's me")
else:
print("it's not me")
test_photos()
如果我不使用UMat(),则会出现此错误:
Traceback (most recent call last):
File "test.py", line 48, in <module>
test_photos()
File "test.py", line 40, in test_photos
face, rect = detect_face(test_photo)
File "test.py", line 16, in detect_face
gray = cv2.cvtColor(imgUMat, cv2.COLOR_BGR2GRAY)
TypeError: Expected cv::UMat for argument 'src'
我使用的是OpenCV 4.0.0,老实说,我非常困惑,因为从我看到的其他人来看,没有其他人必须使用UMat来使用cvtColor(),更不用说在UMat()中使用范围了。任何帮助将不胜感激。
最佳答案
无需使用UMat
转换为cv2.Umat()
,只需将其传递给np.float32()
即可。两者在所有意图和目的上都是相同的。
您的代码如下所示:
def detect_face(img):
imgUMat = np.float32(img)
gray = cv2.cvtColor(imgUMat, cv2.COLOR_BGR2GRAY)