-
Thanks for your great project! Now I want to make a dataset like OCID-VLG using my data. I want to know what should I do ?
-
In order to output probabilistic segmentation masks (as opposed to binary masks), we could implement uncertainty techniques.
Possible avenues include:
- Monte Carlo dropout (cons: will require 10…
-
Hey @xuebinqin,
I recently played a bit with your model architecture with a goal to improve the segmentation performance on the supervisely dataset and just wanted to share some of my findings open…
-
Hi,
https://github.com/deep-voxel/automatic_pulmonary_lobe_segmentation_using_deep_learning talks about only the masks data. could please share the source for image data.
Thanks
-
## 🚀 Feature
Modify `kornia.contrib.ExtractTensorPatches` to apply the same operation to masks in `AugmentationSequential`.
## Motivation
In remote sensing it's common to work with imagery wh…
-
I have retrained the model to fit my dataset. However, when testing, the model seems to predict the segmentation mask well, but some of the boxes were not included in the txt file output, thus not inc…
-
I want to use dense3DCRF for post processing segmentation masks format PNG, is it possible to change the format from niftii to one or co avert the png images into niftii?
Thanks for your help
-
### 🚀 The feature
Development a function torchvision.utils.draw_segmentation_instances to draw just the external contour of a mask.
### Motivation, pitch
For torchvision.utils we have draw_bo…
-
Current tutorial notebook about test-time augmentation (TTA) simply shows how to apply it for brain MRI segmentation in 2D planes. However, it is unclear the if the TTA method would improve the segmen…
-
Labeling images is a big part of @Home (witness: [this Homer blog post](https://userpages.uni-koblenz.de/~robbie/news/new-year-new-labels/)).
Now that we're starting to see detections out of off-th…