Python人脸识别慢
Posted
技术标签:
【中文标题】Python人脸识别慢【英文标题】:Python face recognition slow 【发布时间】:2019-01-21 08:58:52 【问题描述】:我正在尝试构建一个使用人脸识别库实时检测人脸的软件。我使用网络摄像头进行了尝试,结果很有希望,帧速率也相当稳定,但是当我切换到 .mp4 视频时,结果在 fps 方面非常差。我正在使用 Python 3.6 和 OpenCV,这是我正在使用的代码:
import face_recognition
import cv2
# Load a sample picture and learn how to recognize it.
totti_image = face_recognition.load_image_file("totti.jpg")
totti_face_encoding = face_recognition.face_encodings(totti_image)[0]
# Create arrays of known face encodings and their names
known_face_encodings = [
totti_face_encoding
]
known_face_names = [
"Francesco Totti"
]
def get_faces(frame):
# 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 enqcodings in the frame of video
face_locations = face_recognition.face_locations(rgb_frame)
face_encodings = face_recognition.face_encodings(rgb_frame, face_locations)
# Loop through each face in this frame of video
for (top, right, bottom, left), face_encoding in zip(face_locations, face_encodings):
# See if the face is a match for the known face(s)
matches = face_recognition.compare_faces(known_face_encodings, face_encoding, tolerance=0.50)
name = "Unknown"
# If a match was found in known_face_encodings, just use the first one.
if True in matches:
first_match_index = matches.index(True)
name = known_face_names[first_match_index]
# Draw a box around the face
cv2.rectangle(frame, (left, top), (right, bottom), (0, 0, 255), 2)
# Draw a label with a name below the face
cv2.rectangle(frame, (left, bottom - 35), (right, bottom), (0, 0, 255), cv2.FILLED)
font = cv2.FONT_HERSHEY_DUPLEX
cv2.putText(frame, name, (left + 6, bottom - 6), font, 1.0, (255, 255, 255), 1)
return frame
函数“get_faces”在每个帧的 while 循环内被调用,我的性能约为 0.5 fps。 如果有人有建议以获得更好的 fps 输出,请告诉我,谢谢。
编辑: 我使用了以下示例(根据我的需要进行调整)并且一切都运行得更好: link
最终代码:
import face_recognition
import cv2
# Load a sample picture and learn how to recognize it.
image = face_recognition.load_image_file("totti.jpg")
encoding = face_recognition.face_encodings(image)[0]
# Create arrays of known face encodings and their names
known_face_encodings = [
encoding
]
known_face_names = [
"Totti",
]
# Initialize some variables
face_locations = []
face_encodings = []
face_names = []
def get_faces(frame):
# Resize frame of video to 1/10 size for faster face recognition processing
small_frame = cv2.resize(frame, (0, 0), fx=0.1, fy=0.1)
# Convert the image from BGR color (which OpenCV uses) to RGB color (which face_recognition uses)
rgb_small_frame = small_frame[:, :, ::-1]
# Find all the faces and face encodings in the current frame of video
face_locations = face_recognition.face_locations(rgb_small_frame)
face_encodings = face_recognition.face_encodings(rgb_small_frame, face_locations)
face_names = []
for face_encoding in face_encodings:
# See if the face is a match for the known face(s)
matches = face_recognition.compare_faces(known_face_encodings, face_encoding)
name = "Person"
# If a match was found in known_face_encodings, just use the first one.
if True in matches:
first_match_index = matches.index(True)
name = known_face_names[first_match_index]
face_names.append(name)
# Display the results
for (top, right, bottom, left), name in zip(face_locations, face_names):
# Scale back up face locations since the frame we detected in was scaled to 1/10 size
top *= 10
right *= 10
bottom *= 10
left *= 10
# Draw a box around the face
cv2.rectangle(frame, (left, top), (right, bottom), (0, 0, 255), 2)
# Draw a label with a name below the face
cv2.rectangle(frame, (left, bottom - 35), (right, bottom), (0, 0, 255), cv2.FILLED)
font = cv2.FONT_HERSHEY_DUPLEX
cv2.putText(frame, name, (left + 6, bottom - 6), font, 1.0, (255, 255, 255), 1)
return frame
【问题讨论】:
【参考方案1】:要确定脚本的哪些部分运行时间最长,请使用分析器。这将输出每个调用的执行时间,因此您可以更好地了解您的函数的哪些部分是次优的。有关如何分析代码的示例,请参阅 The Python Profilers。
来自documentation:
加快人脸识别速度
如果您有一台计算机,则可以并行进行人脸识别 多个 CPU 内核。例如,如果您的系统有 4 个 CPU 内核,您 可以在相同的时间内处理大约 4 倍的图像 并行使用所有 CPU 内核。如果您使用的是 Python 3.4 或 较新,传入 --cpus
参数:
face_recognition --cpus 4 ./pictures_of_people_i_know/ ./unknown_pictures/
您也可以传入 --cpus -1 以使用系统中的所有 CPU 内核。
在您的计算机上使用一个然后使用最大数量的核心来测试操作。如果这显着缩短了执行时间,您最好的做法是在您自己的脚本中实现多处理。
2020-08-05 更新
对此进行更多研究,因为它仍然受到一些关注。如果我们看一下repository,看起来 CLI 只是进行了一些您可以自己编写脚本的调用,以便将 --cpus
参数放入您自己的代码中。具体来说,您可以以编程方式使用代码here,而不是从命令行使用。使用多处理以类似方式调用 API,或调用 def process_images_in_process_pool(images_to_check, number_of_cpus, model):
。
【讨论】:
感谢您的回答,但我已经知道问题出在以下几行: face_locations = face_recognition.face_locations(rgb_frame) face_encodings = face_recognition.face_encodings(rgb_frame, face_locations) 但我无法更改它们因为这些是我需要的库函数。这是我在网上找到的最好的继续方法,但速度很慢,所以我的问题不在于找出哪些部分运行时间最长,而是是否有办法使用此代码或我没有使用的其他代码t find 以获得更快的分析。 @J.Blackadar,我可以用我的python代码添加face_recognition --cpus 4
吗?我正在使用 pi 2 进行人脸识别,但速度很慢。 :(
@M.D.P 只有通过单独使用 face_recognition 的示例,才能增加 CPU。在您的实际代码中,您需要实现多处理以将计算负载分配到多个内核。
您能否解释一下我们如何在代码中使用 --cpus 4 或者这只适用于命令行?以上是关于Python人脸识别慢的主要内容,如果未能解决你的问题,请参考以下文章