 | 1 | initial version |
I'd like to see the output of every layer of DNN under OpenCV Python. So, I am asking you here to help me. If anyone knows a blog or something else explain how to show us outputs of layers, please, put its link in an answer.
I need to see the outputs like this, this
Full code:
import sys
ros_path2 = '/usr/local/lib/python2.7/site-packages'
ros_path3 = '/usr/lib/python2.7/dist-packages'
if ros_path2 and ros_path3 in sys.path:
sys.path.remove(ros_path2)
sys.path.remove(ros_path3)
from imutils.video import VideoStream
from imutils.video import FPS
import numpy as np
# import cupy as np
import argparse
import imutils
import time
import cv2
global out
out = cv2.VideoWriter('outpy.avi',cv2.VideoWriter_fourcc('M','J','P','G'), 3, (640, 480))
# load our serialized model from disk
print("[INFO] loading model...")
net = cv2.dnn.readNetFromCaffe('prototxt.txt', 'caffemodel') #deep neural network ( dnn )
print("[INFO] starting video stream...")
vs = cv2.VideoCapture(0)
fps = FPS().start()
# loop over the frames from the video stream
while True:
ret , frame = vs.read() #add ret,
(h, w) = frame.shape[:2]
blob = cv2.dnn.blobFromImage(cv2.resize(frame, (300, 300)),
0.007843, (300, 300), 127.5)
net.setInput(blob)
# detections = net.forward()
detections = np.array(net.forward())
big_area = 0
big_center = 320
detected = 0
fps.update()
fps.stop()
for i in np.arange(0, detections.shape[2]):
confidence = detections[0, 0, i, 2]
object_type = int(detections[0, 0, i, 1])
if object_type == 15 and confidence > 0.2: # it was if confidence > args["confidence"]:
box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
(startX, startY, endX, endY) = box.astype("int")
label = "{}: {:.2f}%".format('person', float(confidence) * 100)
text1 = " ssd_CPU: ({:.2f} FPS, {:.2f} sec.)".format(fps.fps(), fps.elapsed())
cv2.rectangle(frame, (startX, startY), (endX, endY),[0,0,255], 2)
y = startY - 15 if startY - 15 > 15 else startY + 15
cv2.putText(frame, label, (startX, y),cv2.FONT_HERSHEY_SIMPLEX, 0.5, [0,0,255], 2)
cv2.putText(frame, text1, (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, [0, 0, 255], 3)
y0 = startY+ ((endX- startX)/3.2)
# print 'yo0', y0
y0 = int(y0)
rect_area = (endX-startX)*(endY-startY)
detected = 1
if rect_area > big_area: # big_area and big_center are used so that the TurtleBot always tracks the closest person
big_area = rect_area
out.write(frame)
cv2.imshow("Frame", frame)
key = cv2.waitKey(1) & 0xFF
if key == ord("q"):
break
fps.update()
fps.stop()
print("[INFO] elapsed time: {:.2f}".format(fps.elapsed()))
print("[INFO] approx. FPS: {:.2f}".format(fps.fps()))
# do a bit of cleanup
vs.release()
cv2.destroyAllWindows()