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

Directory structure of the dataset is not clear #1

Open
aashish-chaubey opened this issue Feb 10, 2020 · 0 comments
Open

Directory structure of the dataset is not clear #1

aashish-chaubey opened this issue Feb 10, 2020 · 0 comments

Comments

@aashish-chaubey
Copy link

Issue: Name of the directory in the data set is not clear. Should the names of the directory be a string or should it be number?

My directory structure for the data set (as mentioned in the README.md):

data\
    class1\
        img1.jpg
        img2.jpg
        img3.jpg
        ...
    class1\
        img1.jpg
        img2.jpg
        img3.jpg
        ...
    .
    .
    .

In the utils.py
Method: generate_batches
You use int(files[i].split('/')[1]), does that mean you want to cast the names to int? If so this is throwing an error.

**Error**: invalid literal for int() with base 10: 'class1'
Configurations:

  • Tensorflow Version: 1.13.1
  • Python: 3.7.3
  • OS: Mac OS Catalina 10.15.3
@aashish-chaubey aashish-chaubey changed the title Directory structure of the data is not clear Directory structure of the dataset is not clear Feb 10, 2020
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

1 participant