Skip to content
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

Missing Conv2D and AveragePooling2D modules in export/import to NIR #304

Open
SirineArfa opened this issue Mar 20, 2024 · 0 comments · May be fixed by #305
Open

Missing Conv2D and AveragePooling2D modules in export/import to NIR #304

SirineArfa opened this issue Mar 20, 2024 · 0 comments · May be fixed by #305

Comments

@SirineArfa
Copy link

Description

The currently supported modules in the snntorch's export_nir.py are [Leaky, Linear, Synaptic, RLeaky, RSynaptic]. In my case I need to convert an SNN model with Conv2D, Leaky, Linear and AveragePooling2D layers to NIR.

What could be done

Two possible options to solve this:

  1. Naively add these two torch.nn layer operations to the snntorch/export_nir.py function
  2. Centralizing NIRTorch functions from_nir.py and to_nir.py to support the NIR conversion of torch.nn layers regardless of the used framework (snntorch,norse,sinabs...)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging a pull request may close this issue.

1 participant