Skip to content

muddukrishna96/Realtime-data-labeling-for-creating-custom-datadets-for-object-detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 

Repository files navigation

Realtime-data-labeling-for-creating-custom-datadets-for-object-detection

It is recomended to create a folder called Data and two sub folders called images and labels where real time captured images are stored in images folders and their corresponding labels are stored in labels folder .

labels=['class1','class2'] # u can mention diffrent types of classed for example happy, sad etc number of classes can be added or reduced in this line of code for example for a code like emotions detector we can add classes like 'happy','sad','angry' etc and collect images accordingly

number_imgs = 20 #mention no of images to be collected per class as the no of images increased the accuracy of prediction increases. so the number of images to be captured can be changed from here

About

this code can be used to create custom labelled data sets

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published