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

Train with own dataset. #37

Open
AmberrrLiu opened this issue May 31, 2020 · 3 comments
Open

Train with own dataset. #37

AmberrrLiu opened this issue May 31, 2020 · 3 comments

Comments

@AmberrrLiu
Copy link

How to train with your own dataset?
I converted the data to coco format; Some file configuration changes were made following mmdetection.
But the training result label is still coco's.

@xieenze
Copy link
Owner

xieenze commented Jun 1, 2020

Hi,
I cannot understand your meanings, please provide more details.

@AmberrrLiu
Copy link
Author

Hi,
I cannot understand your meanings, please provide more details.

There is no training record(eg. loss) during training my own data set. During visualization, the picture is not well recognized, and the label is still the data label of coco, instead of self-labeling.

@kaiyux
Copy link

kaiyux commented Dec 15, 2020

Hi,
I cannot understand your meanings, please provide more details.

There is no training record(eg. loss) during training my own data set. During visualization, the picture is not well recognized, and the label is still the data label of coco, instead of self-labeling.

Make sure you set correct num_classes in config & CLASSES in mmdet/datasets/coco_seg.py.
It seems that the num_classes should have background included.
Hope this helps : )

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

3 participants