-
Notifications
You must be signed in to change notification settings - Fork 1
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
GNN & MLP linking plug-in #26
base: ticlv5_14_0_0_pre0
Are you sure you want to change the base?
GNN & MLP linking plug-in #26
Conversation
for (const auto &point_i : lcs_i){ | ||
for (const auto &point_j : lcs_j){ | ||
// Calculate Euclidean distance between point_i and point_j and push it to dists | ||
dists.push_back(std::sqrt(std::pow((point_i[0] - point_j[0]), 2) + std::pow((point_i[1] - point_j[1]), 2) + std::pow((point_i[2] - point_j[2]), 2))); |
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.
if we can avoid the std::sqrt and work with everything squared would be better
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 fixed the function to output the second power of the distance, then max and min squared distances are selected. But the network is currently trained with the distance, so I still have to use sqrt for min and max distance calculation...
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.
ok, let's remember this then :)
Added plug-in for GNN and MLP networks for trackster linking.