Samuele Ruffino

Yes this is Nuscenes dataset. From the image I sent, you can see that actually the lines have correct direction (parallel to actual lanes in image), but seems to have...

Ok, using the inverse augmentation works better but still I am getting some fov issue or similar. Here you can see the precition (left) and gt (right). The line in...

But under MixViT-ConvMAE I can download online models only (already with SPM integrated).

Ok, but then at stage 2 SPM only has been trained ? No more training on backbone and box head ?

But in this way the SPM would be already pretrained or everything is already implemented in the proper way?

I have seen you have a ```multiobj_mode``` param in ```external/AR/pytracker/tracker```, is that referring to this mode or it is something different? Thank you!

I have the same issue!

When encountering this issue, I have run: ```bash pip install scikit-image==0.18.3 pip install matplotlib==3.5.3 pip install cachetools descartes fire black flake8 pandas plotly pytest ``` and it was at least...

I am having the same issue for now

That would be reallyappreciated also by my side :)