Enna
Is there any update on how to create a ScanNet dataset using RGB and point cloud images? Any help would be appreciated.
Did you fix this? I'm also getting the same error while virtualizing the annotated images.
Any updates on if you could resolve this?
Creating a new virtual env with the following packages worked for me. absl-py==0.12.0 aiocontextvars==0.2.2 array2gif==1.0.4 astroid==2.4.2 attrs==19.3.0 backcall==0.2.0 bleach==3.1.5 cachetools==4.2.2 certifi==2020.6.20 chardet==3.0.4 contextvars==2.4 cycler==0.10.0 Cython==0.29.21 dataclasses==0.8 decorator==4.4.2 defusedxml==0.6.0 entrypoints==0.3 future==0.18.2...
Is there any update on this issue?
> > 1. The training might not use the whole dataset after interaction type filtering, hence the early stopping. > > 2. Low accuracy of label 2, which means no...
Hi, Is there any update on this? Are the rendered images available for download? Thanks!!
Hi, How to identify which scenario in tf_example corresponds to which scenario in scenario protos? I noticed that the 'scenario/id' of tf_example doesn't match the 'scenario_id' of Scenario protos data...
I want to extract specific scenarios from the datasets (for instance- car following). This extraction requires lane information, which is not present in the tf example data, that's why I...
Any timeline on when you plan the next release? Also, what do you mean by **"The only way to match tf.Example data to Scenario protos is to find the records...