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.

Sign up for GitHub

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

Jump to bottom

More features for CNN in OMLT #129

Open

zshiqiang opened this issue Oct 25, 2023 · 0 comments

Collaborator

zshiqiang commented Oct 25, 2023 •

edited

Current implementation of convolutional 2D layer assumes (1) no paddings (2) no dilations (3) zero biases.

To add these features, we need:

parameters corresponding to those features in the Layer2D definition: https://github.com/cog-imperial/OMLT/blob/main/src/omlt/neuralnet/layer.py
a bias term in the Layer2D constraints: https://github.com/cog-imperial/OMLT/blob/main/src/omlt/neuralnet/layers/full_space.py

By generalizing function kernel_index_with_input_indexes in line 258 of https://github.com/cog-imperial/OMLT/blob/main/src/omlt/neuralnet/layer.py, it's possible to support more pooling and convolutional layers (e.g., 1D, 3D).

zshiqiang mentioned this issue

add documentations #136

Merged

jezsadler mentioned this issue

Support for explicit padding and dilations in 2D CNN layers #138

Open

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment