Henric Andrew

When I try to train om my own images and segmentation maps I get this: .../mmsegmentation/mmseg/datasets/transforms/formatting.py:81: UserWarning: Please pay attention your ground truth segmentation map, usually the segmentation map is...

When changing patch_size from 256 to 512 and step size from 256 to 512 I get this error: "Error: AssertionError: ground truth has different shape (torch.Size([2, 1, 512, 512])) from...

In this notebook, why are bounding boxes used even though masks are provided?

This does not work. I want to use the code on my own model. The function freeze sessions returns an object - the "frozen_graph" that only contains emty lists and...

I have images of object with segmentation masks created manually by myself. I modify the jupyter notebook "Personalize SAM with one shot (with fine-tuning)", but the resulting segmentation is not...

Setting class_weight causes CUDA error

2

I have searched related issues but cannot get the expected help. I follow this tutorial: https://github.com/open-mmlab/mmsegmentation/blob/main/demo/MMSegmentation_Tutorial.ipynb I train on my own four classes and it works until I try to...