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
Nodes #106
Nodes #106
Conversation
end | ||
return Hyperrectangle(center, gamma) | ||
end | ||
output = approximate_affine_map(L, input) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
output = overapproximate(AffineMap(L.weights, input, L.bias))
is another option for this line. Any preference on which is clearer for the paper @changliuliu?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I like approximate_affine_map
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This new implementation is very neat!
end | ||
return Hyperrectangle(center, gamma) | ||
end | ||
output = approximate_affine_map(L, input) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I like approximate_affine_map
Noticed in #105 that
Node
really isn't required for maxsens.It also should be quite possible to write it using our own
approximate_affine_map
or LazySet'soverapproximate
(probably). For example, we can write it as