Git Product home page Git Product logo

yolo-annotation-tool's Introduction

YOLO-Annotation-Tool

This is for creating the training set of images for YOLO

Commands on terminal:
git clone https://github.com/ManivannanMurugavel/YOLO-Annotation-Tool.git

cd YOLO-Annotation-Tool

Create 001 folder in Images folder and put your class one images

Convert to .JPEG from any type of images. Use this command(Ubuntu)

mogrify -format jpg *.JPEG or mogrify -format jpg *.jpeg or mogrify -format jpg *.png

Run Main python script

python main.py

Run convert python file for create final text file for yolo images

python convert.py

-------Progress-------

yolo-annotation-tool's People

Contributors

manivannanmurugavel avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

yolo-annotation-tool's Issues

main.py line 138

Help please...

$ python main.py
File "main.py", line 138
print 'No .jpg images found in the specified dir!'
^
SyntaxError: Missing parentheses in call to 'print'. Did you mean print('No .jpg images found in the specified dir!')?

Average loss less than 0.06 but not detecting properly

Hi,
I am trying to detect number plate region given a car. The detailed problem has been described here**(as it is too lengthy)**. Please look into it and any help is very much appreciated.

I have followed https://medium.com/@manivannan_data/how-to-train-yolov2-to-detect-custom-objects-9010df784f36 to train data

Between my images are around 100*32(different images, different sizes) having only number plates and I didn't do any resizing. I think YOLO will resize that. Is it true??

Link attached here for detailed description

https://medium.com/@namburisrinath/hey-hi-80660945331b

If any further clarifications/doubts are there, please do ask.

Thanks in advance
Srinath

Error while running convert.py

Hi, I am facing these errors while running convert.py , I have 1100 images and their corresponding .txt files, but it only convert just one picture.

(yolo) asad@asad-Z370P-D3:~/YOLO-Annotation-Tool$ python convert.py
Input:./Labels/001/00923.txt
Output:./Labels/output/00923.txt
1
370 131 553 270

['1\n370', '131', '553', '270\n']
1
370
(1024, 576)
Traceback (most recent call last):
File "convert.py", line 89, in
print(float(xmin), float(xmax), float(ymin), float(ymax))
ValueError: invalid literal for float(): 1
370

No Module named IPL

I still clone this repository. When i want to run "python main.py".
But, i have some issues like that :

Traceback (most recent call last):
File "main.py", line 12, in
from PIL import Image, ImageTk
ImportError: No module named PIL

anyone can help me about this problem? thank you

invalid literal for float()

I'm trying to train my own data on the Yolo network, but before that I have to convert the bounding boxes co-ordinates to the form it wants.
and i get the error: first it prints out all the file names and the content of the data then

1
29 45 615 251

['1\n29', '45', '615', '251\n']
1
29
(803, 624)
Traceback (most recent call last):
File "convert.py", line 96, in
print(float(xmin), float(xmax), float(ymin), float(ymax))
ValueError: invalid literal for float(): 1
29
I need help please. I don't know what to do

Problem with converting jpg to text

I tried to convert jpg images to path text, but percentage value did not match correct value.
I get 263 image path in test.txt , that should be 163 because i have 2639 (images) * 10 /100 =163
What goes wrong in this code?

import glob, os current_dir = os.path.dirname(os.path.abspath(__file__)) print(current_dir) current_dir = r'C:\Users\Abdou\darknet\build\darknet\x64\data\obj' percentage_test = 10; file_train = open('train.txt', 'w') file_test = open('test.txt', 'w') counter = 1 index_test = round(100 / percentage_test) for pathAndFilename in glob.iglob(os.path.join(current_dir, "*.jpg")): title, ext = os.path.splitext(os.path.basename(pathAndFilename)) if counter == index_test: counter = 1 file_test.write(current_dir + "/" + title + '.jpg' + "\n") else: file_train.write(current_dir + "/" + title + '.jpg' + "\n") counter = counter + 1

IndexError: list index out of range

When I am trying to convert, I get an error:

['152', '59', '220', '155']
152
(449, 334)
(152.0, 220.0, 59.0, 155.0)
(0.4142538975501113, 0.3203592814371258, 0.1514476614699332, 0.28742514970059885)
Input:./Labels/002/img_38.txt
Output:./Labels/output/img_38.txt
12

['12']
Traceback (most recent call last):
  File "convert.py", line 70, in <module>
    xmax = elems[2]
IndexError: list index out of range

File img_38.txt content:

12
8 119 74 211
85 43 125 96
148 63 199 118
280 107 383 238
235 59 263 96
375 82 430 159
285 61 309 92
329 24 355 59
311 29 327 50
277 26 303 52
392 34 413 53
364 9 386 36

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.