Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

how to use it for train the openalpr? #2

Open
abangrephol opened this issue Apr 14, 2017 · 13 comments
Open

how to use it for train the openalpr? #2

abangrephol opened this issue Apr 14, 2017 · 13 comments

Comments

@abangrephol
Copy link

how to use it for train the openalpr?

@linxzhang
Copy link

I'm using this utility to train Chinese plates, and got some *.yaml files, are there any tutorial documents?

@matthill
Copy link
Contributor

This Python script can be used to create the crop images for the detector training: https://github.com/openalpr/train-detector/blob/master/crop_plates.py

@KhuranaPuneet
Copy link

I am using it on windows platform and trying to train ALPR for Indian plates. Got some yaml files in the same directory. Now when i run below command, i have an incorrect output. I am very new to this and am finding hard to get it done.

C:\Users\epukhur\Desktop\openalpr_32>ALPR -c eu c:\temp\7.jpg
plate0: 4 results
- DL8C872 confidence: 93.9432
- DL8C87Z confidence: 79.7399
- 0L8C872 confidence: 72.9129
- 0L8C87Z confidence: 58.7096

7

@KhuranaPuneet
Copy link

KhuranaPuneet commented Jul 14, 2017 via email

@zhouhao27
Copy link

Got the same error. Any solution?

@wiemrachman
Copy link

Hai Linxzhang,

Could you give detail how to use utility "Plate_Tagger" to got some *.yaml files?
do you have *.yaml file for example?

Many Thanx

@zhouhao27
Copy link

@wiemrachman Just tag the image, it will generate the .yaml file. For example, a sample yaml file:

image_file: 1.jpg
image_width: 640
image_height: 375
plate_corners_gt: 272 211 405 205 404 267 273 275
region_code_gt: sg2
plate_number_gt: SGH9456J
plate_inverted_gt: true

@wiemrachman
Copy link

Thanx @zhouhao27

Really?
Actually we have 2 problem with plat_tagger utility.

  1. Button Save still disable (grey)
  2. After i fixed the bug, i got the log (bellow) without error but there is not yaml file

wiem@t430:~/plate_tagger/build$ ./openalpr_tagger
11:42:13.110 D Open directory
11:42:13.110 D Configuration file: /home/wiem/.config/OpenALPR/openalpr_tagger.ini
11:42:18.097 D Loading directory '/home/wiem/Downloads/vid2img'
11:42:19.329 D Loaded files: 2120
11:42:19.329 D Next
11:42:19.330 D Loading image '/home/wiem/Downloads/vid2img/out1556.png'
11:42:27.891 D Starting selection QRect(214,149 1x1)
11:42:30.002 D Actual selection: QRect(529,361 203x77)
11:42:30.002 D Image selection: QRect(529,361 203x77)
11:42:42.515 D Tombol save di klik ya
11:42:42.515 D Selected polygon: QPolygon()

any suggestion?

@wiemrachman
Copy link

to resolve the bug (save button = false)

I changed plateselector.cpp , at void PlateSelector::slotSave()
from :
ui->buttonBox->button(QDialogButtonBox::Save)->setEnabled( !plateNumber().isEmpty() &&
!ui->imageViewerPlateSelector->selectedPolygon().isEmpty()
into :
ui->buttonBox->button(QDialogButtonBox::Save)->setEnabled(true);

just tricky to force save button "true"

but after tag the image , i did not found yaml file

please help me

@zhouhao27
Copy link

I built the openalpr_tagger in my Mac osx without modifying anything in source code. It works well and the yaml files are saved in the same folder as your original image files.

@wiemrachman
Copy link

I think no problem betwwen Max OSX or Ubuntu.

I Suspect there are something wrong on plateselector.cpp
Will you show me plateselector.cpp , are there difference with https://github.com/openalpr/plate_tagger/blob/master/plateselector.cpp?

@wiemrachman
Copy link

@zhouhao27
Ups you right Just tag the image
Many Thanx @zhouhao27

@nabeeltahir12
Copy link

I have installed this tagger on windows but the Save button does not appear to be active (i-e unable to save ) Is there any bug in the code? I installed using exe file.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

7 participants