如何解决如何在 GPU 上运行对象检测?
该程序正在从网络摄像头检测事物,但速度很慢,所以我如何使其更快以获得更好的 FPS,以及我如何使用 GPU 进行更快的检测和更好的性能。我如何才能使它完美。在这个程序中,我使用了 Yolo 配置和带有 coco 数据集的权重。
import cv2
import numpy as np
net = cv2.dnn.readNet('yolov4-custom.cfg','yolov4.weights')
classes = []
with open("coco.names","r") as f:
classes = f.read().splitlines()
cap = cv2.VideoCapture(0)
#cap = cv2.VideoCapture('videoplayback.mp4')
font = cv2.FONT_HERShey_PLAIN
colors = np.random.uniform(0,255,size=(100,3))
while True:
_,img = cap.read()
height,width,_ = img.shape
blob = cv2.dnn.blobFromImage(img,1/255,(416,416),(0,0),swapRB=True,crop=False)
net.setInput(blob)
output_layers_names = net.getUnconnectedOutLayersNames()
layerOutputs = net.forward(output_layers_names)
Boxes = []
confidences = []
class_ids = []
for output in layerOutputs:
for detection in output:
scores = detection[5:]
class_id = np.argmax(scores)
confidence = scores[class_id]
if confidence > 0.2:
center_x = int(detection[0]*width)
center_y = int(detection[1]*height)
w = int(detection[2]*width)
h = int(detection[3]*height)
x = int(center_x - w/2)
y = int(center_y - h/2)
Boxes.append([x,y,w,h])
confidences.append((float(confidence)))
class_ids.append(class_id)
indexes = cv2.dnn.NMSBoxes(Boxes,confidences,0.2,0.4)
if len(indexes)>0:
for i in indexes.flatten():
x,h = Boxes[i]
label = str(classes[class_ids[i]])
confidence = str(round(confidences[i],2))
color = colors[i]
cv2.rectangle(img,(x,y),(x+w,y+h),color,2)
cv2.putText(img,label + " " + confidence,y+20),font,2,(255,255),2)
cv2.imshow('Image',img)
key = cv2.waitKey(1)
if key==27:
break
cap.release()
cv2.destroyAllWindows()
解决方法
要使用 Gpu,我们必须编译 opencv,这可以在博客中按如下方式完成:https://haroonshakeel.medium.com/build-opencv-4-4-0-with-cuda-gpu-support-on-windows-10-without-tears-aa85d470bcd0
然后添加两行,这将检测 Gpu 并且程序将在 GPU 上运行。
import cv2
import numpy as np
net = cv2.dnn.readNet('yolov4-custom.cfg','yolov4.weights')
classes = []
with open("coco.names","r") as f:
classes = f.read().splitlines()
# this below two line will help to run the detetection.
net.setPreferableBackend(cv2.dnn.DNN_BACKEND_CUDA)
net.setPreferableTarget(cv2.dnn.DNN_TARGET_CUDA)
cap = cv2.VideoCapture(0)
#cap = cv2.VideoCapture('videoplayback.mp4')
font = cv2.FONT_HERSHEY_PLAIN
colors = np.random.uniform(0,255,size=(100,3))
while True:
_,img = cap.read()
height,width,_ = img.shape
blob = cv2.dnn.blobFromImage(img,1/255,(416,416),(0,0),swapRB=True,crop=False)
net.setInput(blob)
output_layers_names = net.getUnconnectedOutLayersNames()
layerOutputs = net.forward(output_layers_names)
boxes = []
confidences = []
class_ids = []
for output in layerOutputs:
for detection in output:
scores = detection[5:]
class_id = np.argmax(scores)
confidence = scores[class_id]
if confidence > 0.2:
center_x = int(detection[0]*width)
center_y = int(detection[1]*height)
w = int(detection[2]*width)
h = int(detection[3]*height)
x = int(center_x - w/2)
y = int(center_y - h/2)
boxes.append([x,y,w,h])
confidences.append((float(confidence)))
class_ids.append(class_id)
indexes = cv2.dnn.NMSBoxes(boxes,confidences,0.2,0.4)
if len(indexes)>0:
for i in indexes.flatten():
x,h = boxes[i]
label = str(classes[class_ids[i]])
confidence = str(round(confidences[i],2))
color = colors[i]
cv2.rectangle(img,(x,y),(x+w,y+h),color,2)
cv2.putText(img,label + " " + confidence,y+20),font,2,(255,255),2)
cv2.imshow('Image',img)
key = cv2.waitKey(1)
if key==27:
break
cap.release()
cv2.destroyAllWindows()
版权声明:本文内容由互联网用户自发贡献,该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 dio@foxmail.com 举报,一经查实,本站将立刻删除。