-
Notifications
You must be signed in to change notification settings - Fork 46
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
ESCNN SO(3) 3D CNN example #23
Comments
Hi @Ale9806 Thanks for the question! Regarding the second question, R3Conv is made precisely to work on tensors of shape (batch, channels, width, length, depth). I will keep this issue open until I add an example for R3Conv. Hope this helps, |
Thanks Gabriele! |
Similarly is there an example of a 3D gcnn net with the icosahedral group? If so could you share the example? |
Hi @Gabri95 et al I tried to implement a 3D ESCNN these days (not done yet).
Bottom line from my side: for a beginner it is super helpful to have a tested and working example (classification, regression). I am happy to help. |
Sorry for the delay on this, but I am a bit busy in this month so I have not finished preparing these examples yet. I will try to complete this next week! @psteinb , regarding the notebook, feel free to open another issue here about it or share a pull-request with your proposed solution. We can upload a corrected version of the notebook in this repository. I will notify the people maintaining the https://uvadlc-notebooks.readthedocs.io/ website about the changes (and, of course, acknowledge your contribution there as well). Thanks, |
Digging a bit deeper, I feel a bit lost now. So I can't resist asking here. Note, I still consider myself a newbie in this field. So feel free to correct me where possible. Where I am coming from:
So I was putting my bets on using these induced representations of the group obtained from a Fourier Transform (as eluded to here, bottom of the slide) as the output of the first conv layer. I was hoping that this would reduce the memory overhead of my 3D CNN. But bouncing back and forth between the lecture and the My question: Does |
In principle my confusion stems from the fact, what the lecture calls a steerable equivariant convolutional NN and how the lecture tutorial quoted above implements it using |
hi @psteinb , Sorry for the confusion but, unfortunately, the term induced representation is used in two contexts in practice. Given two groups
Now, we can use In my library, when you see layers mentioning Hope this clarifies your doubts a bit! Let me know if you have more doubts, |
I keep this issue open in case you want to discuss induced representations further. I have finally included an example of 3D equivariant CNN, I'm sorry for the delay but I wanted to train the model and check it still works well on ModelNeto10 (the architecture is essentially the same used in our paper). Best, |
Thanks, Gabriele |
Hi, when trying to run the code I get the following error:
---> 69 ftelu = FourierELU(self.gspace, _channels, irreps=so3.bl_irreps(L), inplace=True, *grid) AttributeError: 'SO3' object has no attribute 'bl_irreps' |
I also tried clonning the repo and running it (instead of running the code with the pypl package) but if fails the asserations of several files! |
Hello!
I was wondering if there is an example of a 3D Steerable CNN (using R3Conv). Furthermore, Is it possible to use this library to train a model using a tensor of shape (batch, channels, width, length, depth)?
Thanks!
The text was updated successfully, but these errors were encountered: