Luca Wiehe
Luca Wiehe
**Bug Description** When using `ns-viewer` in Google Colab, Viser fails to establish a connection to the visualized training instance. I was hoping to solve this issue by setting the `--viewer.make-share-url...
Hey, nice project! I wanted to use only the second stage of this approach, i.e. zero-shot prediction with masks that I have trained myself. Is it possible to perform inference...
I've been trying to run your `demo.py` script. Unfortunately, I am encountering the following error message: ``` (deop) ~//deop$ python3 demo.py --input dataset/test/000000000285.jpg --output ./output --class-names bear other Traceback (most...
First of all, awesome project! We are working on a project where we have our own mask extraction procedure. I am pretty new to working with detectron2 for running models....
In your paper, you have adapted your scale hyperparameter to demonstrate the effect of different granularities. What needs to be adjusted to achieve this?
I was playing around with the initial scene configuration. I have set fixed positions for the objects to be placed. Now, I am adjusting some values in the `qpos` array...
If I use the postprocessing from this repo to run the Libero benchmark, the performance is much worse. I get that visuals are much more realistic here compared to Libero...
# Proposed Changes - redesigned calendar entries to be represented as "rings" instead of indication dots at the bottom - details about a given day are shown in a slide-up...
# Proposed Changes - redesigned screen when workout does not exist - made widget collapsible to keep things clean (in particular for longer workout routines) - redesigned workout for current...
# Proposed Changes - refinement of colors for a more modern UI - redesign of progress bar to arcs/semicircle - better distinction between calories and macro-nutrients I know that this...