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.

Sign up for GitHub

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

Jump to bottom

how to train my own dataset #3

Open
zq1314 opened this issue Aug 2, 2018 · 3 comments
Open

how to train my own dataset #3

zq1314 opened this issue Aug 2, 2018 · 3 comments

Comments

@zq1314
Copy link

zq1314 commented Aug 2, 2018 •
edited
Loading

now ,i want to use your method for the (UC Merced Land Use Dataset) dataset. How to convert my data set into your data form？ @chhwang
@zq1314
Copy link
Author

zq1314 commented Aug 4, 2018

@chhwang

@chhwang
Copy link
Owner

chhwang commented Aug 4, 2018 •
edited
Loading

@zq1314 You can prepare your dataset in torch file format (.t7) and read it using torchfile.load function, refer to cifar.py. It will convert the internal data into numpy arrays.

@zq1314
Copy link
Author

zq1314 commented Sep 2, 2018 •
edited
Loading

2018-09-02 10-35-25
Uploading 2018-09-02 10-35-25屏幕截图.png…
2018-09-02 10-40-38
when i run my own dataset ,i face some problem ,i transform my dataset into numpy array but i still face some pronblem
@chhwang

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@chhwang @zq1314