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

Support Conv1D and MaxPooling1D #22

Open
fthielke opened this issue May 21, 2024 · 0 comments
Open

Support Conv1D and MaxPooling1D #22

fthielke opened this issue May 21, 2024 · 0 comments

Comments

@fthielke
Copy link
Collaborator

Models for sequence data need 1D variants of the convolutional and pooling layers.

AC: WhistleNetMk16 can be run in CompiledNN

ahasselbring added a commit that referenced this issue May 21, 2024
They can at least be read and handled by SimpleNN (by much code
duplication). However, there are no kernels, and there is no fusion of
layers (e.g. Conv1D + BatchNorm + Activation) yet. The SimpleNN
implementation is not tested.
fthielke added a commit that referenced this issue May 23, 2024
This layer is not used directly by targeted models, but since the CompiledNN implementation of Conv1D will require zero padding anyways we might as well support it all the way.
fthielke added a commit that referenced this issue May 24, 2024
fthielke added a commit that referenced this issue May 24, 2024
Laurendus added a commit that referenced this issue Jun 12, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Development

No branches or pull requests

1 participant