Replies: 1 comment
-
I have a similar question as well. I am planning to test TIMM Models for keypoint regression and I don't know how the input folder structure looks like and how to specify the annotations/labels. I am annotating my keypoints in CVAT and it supports various export formats for the annotations. Some explanation here would be nice !!!😃 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I am researching an image regression problem. I have training data with all images and a *.txt file (has image name and label) in one folder. The *.txt file format is as follows:
0.png 0.12
1.png 0.23
2.png 0.34
.....
In Timm, it scans the folder name as its label. How to create a dataset as I want? Or can I define a custom create_dataset function?
Thanks
Beta Was this translation helpful? Give feedback.
All reactions