We Keep Coding

Paddlelite inference key errors

I am trying to do real time prediciton inference for an arm64 computer. I am using Mobilenet_V1. Unfortunately, I am getting different key errors everytime I run the prediction. It seems the error is due to some problem with the label index (I am not sure about it).
Here's the code and error I am getting.
from paddlelite.lite import *
import cv2
import numpy as np
import sys
import time
from PIL import Image
from PIL import ImageFont
from PIL import ImageDraw
def create_predictor(model_dir):
config = MobileConfig()
config.set_model_from_file(model_dir)
predictor = create_paddle_predictor(config)
return predictor
def process_img(image, input_image_size):
origin = image
img = origin.resize(input_image_size, Image.BILINEAR)
resized_img = img.copy()
if img.mode != 'RGB':
img = img.convert('RGB')
img = np.array(img).astype('float32').transpose((2, 0, 1)) # HWC to CHW
img -= 127.5
img *= 0.007843
img = img[np.newaxis, :]
return origin,img
def predict(image, predictor, input_image_size):
input_tensor = predictor.get_input(0)
input_tensor.resize([1, 3, input_image_size[0], input_image_size[1]])
image = Image.fromarray(cv2.cvtColor(image, cv2.COLOR_BGRA2RGBA))
origin, img = process_img(image, input_image_size)
image_data = np.array(img).flatten().tolist()
input_tensor.set_float_data(image_data)
predictor.run()
output_tensor = predictor.get_output(0)
print("output_tensor.float_data()[:] : ", output_tensor.float_data()[:])
res = output_tensor.float_data()[:]
return res
def post_res(label_dict, res):
# print(max(res))
target_index = res.index(max(res))
print("predicted result:" + " " + label_dict[target_index], "accuracy：", max(res))
if __name__ == '__main__':
label_dict = {0:"metal", 1:"paper", 2:"plastic", 3:"glass"}
model_dir = "../model/mobilenet_v1_opt.nb"
image_size = (224, 224)
predictor = create_predictor(model_dir)
while True:
ret, frame = cap.read()
print('Prediction Start')
time_start=time.time()
res = predict(frame, predictor, image_size)
post_res(label_dict, res)
print('Time Cost：{}'.format(time.time()-time_start) , "s")
print('Predict End')
cv2.imshow("frame", frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
Error：
Any suggestion/tips would be really helpful.

How to capture video by video from one rtsp Url using Opencv?

The server is sending video by video using the same RTSP URL(rtsp://192.168.0.2:8554/)
I can capture and display video using opencv.
import numpy as np
import cv2 as cv
os.environ["OPENCV_FFMPEG_CAPTURE_OPTIONS"] = "rtsp_transport;udp"
cap = cv.VideoCapture('rtsp://192.168.0.2:8554/')
while cap.isOpened():
ret, frame = cap.read()
# if frame is read correctly ret is True
if not ret:
print("Can't receive frame (stream end?). Exiting ...")
break
cv.imshow('frame', frame)
if cv.waitKey(1) == ord('q'):
break
cap.release()
cv.destroyAllWindows()
This program returns error when going on to the next video.
I tried this, but this didn't work.
import cv2 as cv
import os
import time
os.environ["OPENCV_FFMPEG_CAPTURE_OPTIONS"] = "rtsp_transport;udp"
cap = cv.VideoCapture('rtsp://192.168.0.26:8554/')
if not cap.isOpened():
print("Cannot open camera")
exit()
while True:
try:
time.sleep(2)
# Capture frame-by-frame
ret, frame = cap.read()
# if frame is read correctly ret is True
# Our operations on the frame come here
# Display the resulting frame
cv.imshow('frame',frame)
if cv.waitKey(1) == ord('q'):
break
except:
print("Exception!!")
# When everything done, release the capture
cap.release()
cv.destroyAllWindows()
Can I get some help?
Thanks in advance!

I solved this by using multi-threaded program.
Main file
from datasets import LoadStreams
import threading
import os
import logging
import cv2
import torch
import time
logger = logging.getLogger(__name__)
def select_device(device='', batch_size=None):
# device = 'cpu' or '0' or '0,1,2,3'
cpu_request = device.lower() == 'cpu'
if device and not cpu_request: # if device requested other than 'cpu'
os.environ['CUDA_VISIBLE_DEVICES'] = device # set environment variable
assert torch.cuda.is_available(), f'CUDA unavailable, invalid device {device} requested' # check availablity
cuda = False if cpu_request else torch.cuda.is_available()
if cuda:
c = 1024 ** 2 # bytes to MB
ng = torch.cuda.device_count()
if ng > 1 and batch_size: # check that batch_size is compatible with device_count
assert batch_size % ng == 0, f'batch-size {batch_size} not multiple of GPU count {ng}'
x = [torch.cuda.get_device_properties(i) for i in range(ng)]
s = f'Using torch {torch.__version__} '
for i, d in enumerate((device or '0').split(',')):
if i == 1:
s = ' ' * len(s)
logger.info(f"{s}CUDA:{d} ({x[i].name}, {x[i].total_memory / c}MB)")
else:
logger.info(f'Using torch {torch.__version__} CPU')
logger.info('') # skip a line
return torch.device('cuda:0' if cuda else 'cpu')
def detect(rtsp_url):
dataset = LoadStreams(rtsp_url)
device = select_device('')
count = 0
view_img = True
# img = torch.zeros((1, 3, imgsz, imgsz), device=device) # init img
try:
for frame_idx, (path, img, im0s, vid_cap) in enumerate(dataset): # for every frame
count += 1
im0 = im0s[0].copy()
if view_img:
cv2.imshow(str(path), im0)
# if cv2.waitKey(1) == ord('q'): # q to quit
# raise StopIteration
except:
print("finish execption")
dataset.stop()
return "good"
if __name__ == '__main__':
rtsp_url = "rtsp://192.168.0.26:8554/"
while True:
for thread in threading.enumerate():
print(thread.name)
print(detect(rtsp_url))
dataset class file
import glob
import logging
import math
import os
import random
import shutil
import time
import re
from itertools import repeat
from multiprocessing.pool import ThreadPool
from pathlib import Path
from threading import Thread
import cv2
import numpy as np
import torch
class LoadStreams: # multiple IP or RTSP cameras
def __init__(self, sources='streams.txt', img_size=640):
self.mode = 'stream'
self.img_size = img_size
self.capture = None
self.my_thread = None
self.stopFlag = False
if os.path.isfile(sources):
with open(sources, 'r') as f:
sources = [x.strip() for x in f.read().strip().splitlines() if len(x.strip())]
else:
sources = [sources]
n = len(sources)
self.imgs = [None] * n
self.sources = [clean_str(x) for x in sources] # clean source names for later
s = sources[0]
# for i, s in enumerate(sources):
# Start the thread to read frames from the video stream
# print('%g/%g: %s... ' % (i + 1, n, s), end='')
cap = cv2.VideoCapture(eval(s) if s.isnumeric() else s)
assert cap.isOpened(), 'Failed to open %s' % s
w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
fps = cap.get(cv2.CAP_PROP_FPS) % 100
self.ret, self.imgs[0] = cap.read() # guarantee first frame
thread = Thread(target=self.update, args=([0, cap]), daemon=True)
print(' success (%gx%g at %.2f FPS).' % (w, h, fps))
thread.start()
self.capture = cap
self.my_thread = thread
print('') # newline
# check for common shapes
s = np.stack([letterbox(x, new_shape=self.img_size)[0].shape for x in self.imgs], 0) # inference shapes
self.rect = np.unique(s, axis=0).shape[0] == 1 # rect inference if all shapes equal
if not self.rect:
print('WARNING: Different stream shapes detected. For optimal performance supply similarly-shaped streams.')
def update(self, index, cap):
# Read next stream frame in a daemon thread
n = 0
while cap.isOpened() and not self.stopFlag:
n += 1
# _, self.imgs[index] = cap.read()
cap.grab()
if n == 4: # read every 4th frame
_, self.imgs[index] = cap.retrieve()
n = 0
time.sleep(0.01) # wait time
def stop(self):
self.stopFlag = True
try:
# self.capture.release()
# self.my_thrsead.join()
print("stop thread!!")
except:
print("ERROR stopping thread!!")
def __iter__(self):
self.count = -1
return self
def __next__(self):
self.count += 1
img0 = self.imgs.copy()
if cv2.waitKey(1) == ord('q'): # q to quit
cv2.destroyAllWindows()
raise StopIteration
if not self.ret:
print("error!!!")
self.stop()
# Letterbox
img = [letterbox(x, new_shape=self.img_size, auto=self.rect)[0] for x in img0]
# Stack
img = np.stack(img, 0)
# Convert
img = img[:, :, :, ::-1].transpose(0, 3, 1, 2) # BGR to RGB, to bsx3x416x416
img = np.ascontiguousarray(img)
return self.sources, img, img0, None
def __len__(self):
return 0 # 1E12 frames = 32 streams at 30 FPS for 30 years
# def stop(self):
def clean_str(s):
# Cleans a string by replacing special characters with underscore _
return re.sub(pattern="[|##!¡·$€%&()=?¿^*;:,¨´><+]", repl="_", string=s)
def letterbox(img, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True):
# Resize image to a 32-pixel-multiple rectangle https://github.com/ultralytics/yolov3/issues/232
shape = img.shape[:2] # current shape [height, width]
if isinstance(new_shape, int):
new_shape = (new_shape, new_shape)
# Scale ratio (new / old)
r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
if not scaleup: # only scale down, do not scale up (for better test mAP)
r = min(r, 1.0)
# Compute padding
ratio = r, r # width, height ratios
new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding
if auto: # minimum rectangle
dw, dh = np.mod(dw, 32), np.mod(dh, 32) # wh padding
elif scaleFill: # stretch
dw, dh = 0.0, 0.0
new_unpad = (new_shape[1], new_shape[0])
ratio = new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratios
dw /= 2 # divide padding into 2 sides
dh /= 2
if shape[::-1] != new_unpad: # resize
img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR)
top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border
return img, ratio, (dw, dh)
while cap.isOpened() and not self.stopFlag:
this line is especially important because
without this line the threads will be stacked and will have memory error
as the stack stacks up.

How to integrate barcode scanner with tkinter GUI application in python?

When I run the below code. The camera opens and we can read the barcode. What I need is that the camera window remains at the side of my Tkinter GUI application rather than poping up. Here's the code
from imutils.video import VideoStream
from pyzbar import pyzbar
import argparse
import datetime
from datetime import datetime
import imutils
import time
import cv2
import winsound
frequency = 600 # Set Frequency To 2500 Hertz
duration = 800 # Set Duration To 1000 ms == 1 second
ap = argparse.ArgumentParser()
ap.add_argument("-o", "--output", type=str, default="barcodesData.csv",
help="path to output CSV file ")
args = vars(ap.parse_args())
print("Starting webcam")
vs = VideoStream(src=0).start()
time.sleep(2.0)
csvWrite = open(args["output"], "w")
found = set()
while True:
frameData = vs.read()
frameData = imutils.resize(frameData, width=600)
barcodes = pyzbar.decode(frameData)
for barcode in barcodes:
(x, y, width, height) = barcode.rect
cv2.rectangle(frameData, (x, y), (x + width, y + height), (0, 0, 255), 2)
barcodeData = barcode.data.decode("utf-8")
barcodeType = barcode.type
textData = "{} ({})".format(barcodeData, barcodeType)
cv2.putText(frameData, textData, (x, y - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255), 2)
if barcodeData not in found:
csvWrite.write("{},{}\n".format(datetime.today().strftime('%Y-%m-%d'),
barcodeData))
csvWrite.flush()
found.add(barcodeData)
winsound.Beep(frequency, duration)
cv2.imshow("Barcode Scanner", frameData)
key = cv2.waitKey(1) & 0xFF
if key == ord("e"):
break
# close the output CSV file do a bit of cleanup
print("\nWait while we calculate cost...")
csvWrite.close()
cv2.destroyAllWindows()
vs.stop()
time.sleep(1.0)
TO be specific. I'm making a billing software where I can read the barcodes of the products and make a bill. The camera separate screen is annoying so if the camera is on any side of the canvas all the time. It would be more quick.

I encoded the IDs of each product/item in my database in a QR code. When that particular item is being sought for, I used CV2 to detect and decode the QR code.
Here is the code:
def encode_qr():
import qrcode
import random as r
item_code = r.randint(00000000,99999999)
data = item_code
qrfile = "qr_image_name_for_specified_item.png"
# generate qrcode
qrimage = qrcode.make(data)
# save image
fl = qrimage.save(qrfile)
print("Done generating qrcode")
def decode_qr():
import cv2
filename="qr_image_name_for_specified_item.png"
# alternatively webcam cv2.VideoCapture(0)
# read image
image = cv2.imread(filename)
# initialize qrcode detector
detector = cv2.QRCodeDetector()
# detect and decode
info, v_array, binary_qrcode=detector.detectAndDecode(image)
# if null?
if v_array is None:
print("No qrcode detected or probably some technical issues occurred")
else:
print("QRCODE data")
print(info)
# below i am working with the import sqlite3 as sql3
sqldb = sql3.connect("your_database.db")
cur = sqldb.cursor()
cur.execute("select * from table where ID=?, (info,))
rows = cur.fetchall()
for r in rows:
print(r) # this will loop all the item details with the itemcode
print(r[1]) # a specific detail with the item_code

Detecting water in a plant stem in real time using computer vision (OpenCV and Python)

I am working on an experiment with plants in a pressure chamber. I need to be able to identify with a computer vision algorithm the exact moment when water starts to appear at the cut end of the stem. In the case of this video - taken from a USB microscope, this is the interval between 0:30 and 0:34 seconds, approximately.
I tried to use MOG, MOG2 and GMG as a background subtractor, and compare the histograms of each frame (using chi-squared, bhattacharyya, correlation), looking for changes that could be significant, however still without success. Is there a better alternative for this type of work?
Below, some code (made with the help of a friend)
import numpy as np
import sys
import time
import cv2
from matplotlib import pyplot as plt
video_filename = 'M20201022_004.mov'
capture = cv2.VideoCapture(video_filename)
#fgbg = cv2.bgsegm.createBackgroundSubtractorMOG()
fgbg = cv2.createBackgroundSubtractorMOG2()
#kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE,(3,3))
#fgbg = cv2.bgsegm.createBackgroundSubtractorGMG()
width = int(capture.get(cv2.CAP_PROP_FRAME_WIDTH))
height = int(capture.get(cv2.CAP_PROP_FRAME_HEIGHT))
frames_per_second = capture.get(cv2.CAP_PROP_FPS)
num_frames = int(capture.get(cv2.CAP_PROP_FRAME_COUNT))
print(' height: {}\n width: {}\n fps: {}\n num_frames: {}\n'.format(height, width,frames_per_second, num_frames))
frameCounter = 0
t = time.process_time()
dist_hist = 0 # distance between histograms
frame_hist = 0
time_hist = 0
#write file
file1 = open("resultado.txt","w")
if not capture.isOpened():
print("Could not open video")
print('frameCounter: {}'.format(frameCounter))
sys.exit(1)
while capture.isOpened():
success, frame = capture.read()
frameCounter += 1
# Test for read error
if not success:
print('Failed to read video - Video Capture EOF or Error')
print('frameCounter:{}'.format(frameCounter))
if frameCounter == num_frames + 1:
print('EOF found')
else:
print('error')
break
#sys.exit(1)
else:
if frameCounter % 1000 == 0:
print('type:{} size:{} dtype:{} len(shape):{} contador:{}'.format(type(frame),frame.size,frame.dtype,len(frame.shape),frameCounter))
if len(frame.shape) < 3: # grayscale
h, w = frame.shape
print('h:{} w:{}'.format(h, w))
else: # color image
h, w, ch = frame.shape
print('h:{} w:{} ch:{}'.format(h, w, ch))
fgmask = fgbg.apply(frame)
#fgmask = fgbg.apply(frame)
#fgmask = cv2.morphologyEx(fgmask, cv2.MORPH_OPEN, kernel)
# Initial histogram Test
if frameCounter == 1:
hist_initial = cv2.calcHist([fgmask], [0],None,[16],[0, 256])
# print('hist_initial:{}'.format(hist_initial))
#elapsed_time = time.process_time() - t
elapsed_time = frameCounter / frames_per_second
# Process Histogram
hist_process = cv2.calcHist([fgmask], [0],None,[16],[0, 256])
dist = cv2.compareHist(hist_initial, hist_process,cv2.HISTCMP_CHISQR)
str1 = str(frameCounter) + "," + str(dist) + "," + str(dist_hist) + "," + str(elapsed_time)
file1.write(str1)
file1.write("\n")
if dist > dist_hist: # Depending on compareHist method
dist_hist = dist
time_hist = elapsed_time
frame_hist = frameCounter
# Print line at image
strfmt = 'frame: {} elapsed_time: {:7.2f}'.format(frameCounter, elapsed_time)
cv2.putText(frame, strfmt, (0, 50),cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0,0,255), 1, cv2.LINE_AA)
cv2.imshow('frame', frame)
cv2.imshow('fgmask', fgmask)
if cv2.waitKey(1) & 0xff == 27: # ESC pressed
break
print('---> frame:{} dist:{:10.6f} time:{:7.2f}'.format(frame_hist, dist_hist,time_hist))
capture.release()
cv2.destroyAllWindows()
file1.close()
Any help appreciated!

Opencv python background substraction and motion tracking

I read about opencv on google and found the following sample code online to play with:
import cv2
def diffImg(t0, t1, t2):
d1 = cv2.absdiff(t2, t1)
d2 = cv2.absdiff(t1, t0)
return cv2.bitwise_and(d1, d2)
cam = cv2.VideoCapture('vid1.mp4')
winName = "Movement Indicator"
cv2.namedWindow(winName, cv2.CV_WINDOW_AUTOSIZE)
# Read three images first:
t_minus = cv2.cvtColor(cam.read()[1], cv2.COLOR_RGB2GRAY)
t = cv2.cvtColor(cam.read()[1], cv2.COLOR_RGB2GRAY)
t_plus = cv2.cvtColor(cam.read()[1], cv2.COLOR_RGB2GRAY)
while True:
cv2.imshow( winName, diffImg(t_minus, t, t_plus) )
# Read next image
t_minus = t
t = t_plus
t_plus = cv2.cvtColor(cam.read()[1], cv2.COLOR_RGB2GRAY)
key = cv2.waitKey(10)
if key == 27:
cv2.destroyWindow(winName)
break
print "Goodbye"
It produces the following kind of output for a sample video that I give to it:
So I am getting such results with this script. Now what I am trying to figure out is -
1) Get the bounding rect for the moving object in the video file
2) copy the contents of that bounding rect from original video frame to another and write the finished video to a file
Also, the screenshots on trying Kanishak Katahra's solution below I am getting the following output in the result window in the right side in the screenshot below -

Make the point of interest in the output you are getting as 1s. Make the rest as 0.
Convert it to 3D array of size same as original image.
Multiply original image with the output you are getting.
import cv2
import numpy as np
from numpy import newaxis
import time
def diffimg (a,b,c):
t0 = cv2.absdiff(a,b)
t1 = cv2.absdiff(b,c)
t3 = cv2.bitwise_and(t0,t1)
return t3
cap = cv2.VideoCapture(0)
t = cap.read() [1]
tp = cap.read() [1]
tpp = cap.read() [1]
t = cv2.cvtColor(t,cv2.COLOR_BGR2GRAY)
tp = cv2.cvtColor(tp,cv2.COLOR_BGR2GRAY)
tpp = cv2.cvtColor(tpp,cv2.COLOR_BGR2GRAY)
while True:
img = diffimg(t,tp,tpp)
cv2.imshow("motion detct",img)
key = cv2.waitKey(10)
res,img2 = cap.read()
#print img2.shape
t = tp
tp = tpp
tpp = cv2.cvtColor(img2,cv2.COLOR_BGR2GRAY)
cv2.imshow('image',img)
print img
img[img <= 10] = 0 #Try adjusting this value for better results.
img[img != 0] = 1
img = np.repeat(img[:, :, np.newaxis], 3, axis=2)
img3 = np.multiply( img,img2)
cv2.imshow('result',img3)
if key == 27:
cv2.destroyAllWindows()
break;
print "Goodbye User"