Paul Willot

Glad you're interested in tackling panoptic segmentation too! First an apology, my code is unpolished and not self explanatory, improving it is in my backlog and will be tackled as...

Thanks! I'm quite busy atm but it's added to my backlog, I'll fix it along with other TODOs

That's odd, I don't see this issue on my side sorry 🤔 (just tried with: python 3..10.6, numpy 1.23.2, scipy 1.9.1, imageio 2.22.0) I'm not sure what's happening, maybe there...

I'm curious about this, do you already have use-cases in mind or is that to broaden the capabilities of Chainer? I see your related [ongoing PR](https://github.com/chainer/chainer/pull/4241), does that target the...

Understood. Thanks for the papers, I didn't know about the last two, seems very interesting! Looking forward to use it in Chainer 👍

You can find some in the author's repo, in JAX though: https://github.com/deepmind/deepmind-research/tree/master/perceiver#colabs

Same as #34 you can find some pre-trained weights in the author's repo: https://github.com/deepmind/deepmind-research/tree/master/perceiver#colabs

@KalraA here is what I used: ```Dockerfile FROM nvidia/cudagl:11.0-runtime-ubuntu18.04 ENV NVIDIA_VISIBLE_DEVICES all ENV NVIDIA_DRIVER_CAPABILITIES compute,graphics,utility,video ENV LANG C.UTF-8 ENV LC_ALL C.UTF-8 RUN apt-get update && apt-get install -qq \ curl...

I'm going to close this, but feel free to re-open if it's still relevant

Thanks for the suggestion. Note that what you're committing is a stand-alone jupyter notebook, do you want to actually make a colab notebook? If yes please do so and I'll...