-
Notifications
You must be signed in to change notification settings - Fork 47
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
training problem #3
Comments
@nebuladream Actually I train the neural network with the code that is published, using mini_mask, if you use utils.minimize_mask_2 to cut and resize the keypoints, these should not "disappear", when a point is not present (missing) because is not in the picture the code assign (0, 0) = 1 image, image_meta, gt_bbox, gt_mask = modellib.load_image_gt(dataset_val, config, image_id, if m.sum() == 0: actually I dont know way the performance is not as the paper |
@minizon @nebuladream Do you finally fix this issue? My loss can't converge too. It confused me a lot. |
@minizon @minizon You can refer to my repository https://github.com/Superlee506/Mask_RCNN. I refereed to the original detectron project and modified the code with detailed comments. The loss converges quickly, but there is still much room for improvement. |
@Superlee506 Thank you for sharing your code. I've realized that I've made a mistake on the horizontal flip augmentation. I did not change the kp left/right labels when I mirrored the persons. Since I remove this augmentation, both the training and val losses converge, though there's still a larger margin to the theoretical value compared to other branches' losses. By the way, your space encoding is more efficient in GPU memory use. |
@nebuladream Yes, I also notice this problem. Can your model distinguish the symmetrical lef/right keypoint? My model often predict these points together. |
@Superlee506 , @minizon this can be an interesting read for this problem: http://blog.dlib.net/2018/01/correctly-mirroring-datasets.html |
I run your inference phrase success, but when I try to finetune your model by AIChallenger data, it seems not right, after some epoch the keypoints disappear…… in your main.py, train heads layers which may not include mask_class_loss_graph, is this cause the issue? can you provide how to train the net?
The text was updated successfully, but these errors were encountered: