I'm a newbie in DL/Real time object detection area and tring to learn some stuff from youtube. I watched a video https://www.youtube.com/watch?v=DLngCtsG3bk on youtube about real time custom object detection on yolov3 and I did all stepts correctly. When I run my object-detection python file on my laptop its running on CPU and I can only receive 2-3 fps. Please can anyone tell me how can I use my GPU for running it. The files I got yolov3_training_last.weights, yolov3_testing.cfg and classes.txt. The python file is included below and when I run it as I said I get low fps. If is there any way to increase it with using GPU, please teach me. Thank you in advance.
Python File:
import cv2
import numpy as np
import time
net = cv2.dnn.readNet('yolov3_training_last.weights', 'yolov3_testing.cfg')
classes = []
with open("classes.txt", "r") as f:
classes = f.read().splitlines()
cap = cv2.VideoCapture(0)
font = cv2.FONT_HERSHEY_PLAIN
colors = np.random.uniform(0, 255, size=(100, 3))
# used to record the time when we processed last frame
prev_frame_time = 0
# used to record the time at which we processed current frame
new_frame_time = 0
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 > 0.95:
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]
crop_img = img[y:y+h, x:x+w]
(B, G, R) = [int(x) for x in cv2.mean(crop_img)[:3]]
roi_face= img[y: y+ h, x:x+w]
roi_face = cv2.blur(roi_face,(20,20))
img[y: y+ h, x: x+ w]=[0,0,0]
img[y: y+ h, x: x+ w]=cv2.add(roi_face, img[y: y+ h, x: x+ w])
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, 1, (255,255,255), 2)
font = cv2.FONT_HERSHEY_SIMPLEX
# time when we finish processing for this frame
new_frame_time = time.time()
# Calculating the fps
# fps will be number of frame processed in given time frame
# since their will be most of time error of 0.001 second
# we will be subtracting it to get more accurate result
fps = 1/(new_frame_time-prev_frame_time)
prev_frame_time = new_frame_time
# converting the fps into integer
fps = int(fps)
# converting the fps to string so that we can display it on frame
# by using putText function
fps = str(fps)
# putting the FPS count on the frame
cv2.putText(img, fps, (7, 70), font, 3, (100, 255, 0), 3, cv2.LINE_AA)
cv2.imshow('Image', img)
key = cv2.waitKey(1)
if key==27:
break
cap.release()
cv2.destroyAllWindows()
