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

Some questions #7

Open
SoonFa opened this issue Mar 8, 2022 · 6 comments
Open

Some questions #7

SoonFa opened this issue Mar 8, 2022 · 6 comments

Comments

@SoonFa
Copy link

SoonFa commented Mar 8, 2022

  1. The provided dataset does not have the structure demonstrated in the documentation.

image
image

  1. ave_cc is not defined
@surajnagaje
Copy link

When I try to run the main_resnet.py I am getting error of file not found : "MINI_DIR/trainval_list.txt"
Anybody please help if u know the solution.
Thnak you!

@SoonFa
Copy link
Author

SoonFa commented Apr 14, 2022

You can divide the dataset based on your needs

@SoonFa
Copy link
Author

SoonFa commented Apr 14, 2022

When I try to run the main_resnet.py I am getting error of file not found : "MINI_DIR/trainval_list.txt" Anybody please help if u know the solution. Thnak you!

You can divide the dataset based on your needs

@surajnagaje
Copy link

We are trying to implement the code for our project. We have searched for the missing files everywhere possible. We could not find them. Were you able to implement this code so that it helps us in proceeding further. If you are able to run the code, please help us in finding those missing files. Moreover, could you please elaborate on your comment 'You can divide the dataset based on your needs'.

Thanks.

@SoonFa
Copy link
Author

SoonFa commented Apr 15, 2022

you can organize your dataset according to the train.txt

All pictures are in the one folder ,if you download the original miniImageNet you downloaded

so you should split it as train.txt suggested.
train/n03908618/n0390861800024462.png 0
The n0390861800024462.png in the big folder should be copied into the train/n03908618/ folder

The rest part is too long to remember.

@surajnagaje
Copy link

Oh okay....One more question if u could please...
were you able to run the complete code? Did you get the results as mentioned in the paper?

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

2 participants