-
Thanks for the nice repo.
Maybe you applied the Focal Loss in **mrcnn_class_loss_graph**, but what about **rpn_bbox_loss_graph and rpn_class_loss_graph** ?
Why did you not apply here?
Thanks
-
I have 30 classes & my dataset is totally imbalanced, so I'm planning to train only the top 10 classes,
But i don't want to remove other class ids from text file, is there any way to do this?? @Alexe…
-
Hi, thank you for your great work. I am currently exploring the semi-supervised semantic segmentation works, and find your work very interesting.
I want to ask a general question, that is, how to u…
-
Thank you for the really great tool!
I was trying to rerun the tutorial, but I got several errors. I would appreciate any help on what could have gone wrong.
Two of them were while running ir.pl.clo…
-
-
With severely imbalanced classes, people often undersample the more frequent class or oversample the less frequent class (see https://www3.nd.edu/~dial/publications/hoens2013imbalanced.pdf). There are…
-
I have CT dataset with high class imbalance for binary classification, where only 1% of my 3D CT scan is to be segmented. How do i choose learning rate, loss and epochs?
-
I have a matrix of 4000*1400, can I use it for classification problems using random forest?
-
Approach I'd take :- 1. Utilizing 5 models such as DenseNet121 , Xception, VGG16, ResNet50, and InceptionV3 for image classification.
2. Applying data augmentation (rotation, zooming, flipping,…
-
- [x] Implement custom dataloader for YOLOv8
- [x] create a baseline / reference from vanilla yolov8
- [ ] Data augmentation
- [x] Incorporate other countries in training
- [ ] Freeze layers befo…