Jakob Wasserthal
Jakob Wasserthal
This is a good point. I will try to add this in the future.
I added some instructions on how to train a nnunet from the public dataset and how to perform evaluation on it. This should help to make evaluation standardized between people....
We are currently working on these structures. But it will take a bit more time before they are finished.
Thanks for your reply. Unfortunately these suggestions did not solve the problem. It seems that a software rooting might help: https://dazeb.dev/root-your-woox-ip-camera-for-rtsp-home-assistant/ I will try this.
This should be fixed in the latest master branch: ``` pip install git+https://github.com/wasserth/TotalSegmentator.git ```
Thanks for pointing this out.
TotalSegmentator is doing some pre and postprocessing. These steps are implemented for binary masks but not for float softmax images. Implementing this would be possible but currently does not have...
Theoretically you could do that, but this will result in missing a lot true positives. The default threshold of 0.5 typically works best and adjusting it does not help in...
Thanks for the suggestion. Huggingface is doing a great job with hosting machine learning models. However, I think this model is a bit different from your typical pytorch model. Just...
The error message you encountered indicates that there is a problem with your system's OpenGL installation. Specifically, it seems that the software rendering library `swrast` is either missing or cannot...