This program is detecting the things from web cam but it's slow so how can i make it fast for better FPS and how can i use GPU for the faster detection and with better performance. And i how can i make it perfect .In this Program i have used the Yolo configuration and weights with coco dataset .
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), (0,0,0), 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, y, w, 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, (x, y+20), font, 2, (255,255,255), 2)
cv2.imshow('Image', img)
key = cv2.waitKey(1)
if key==27:
break
cap.release()
cv2.destroyAllWindows()
To use Gpu we have to compile opencv and this can be done as follows in blog : https://haroonshakeel.medium.com/build-opencv-4-4-0-with-cuda-gpu-support-on-windows-10-without-tears-aa85d470bcd0
and after doing it add the two lines that will that will detect the Gpu and program will run on GPU.
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), (0,0,0), 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, y, w, 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, (x, y+20), font, 2, (255,255,255), 2)
cv2.imshow('Image', img)
key = cv2.waitKey(1)
if key==27:
break
cap.release()
cv2.destroyAllWindows()