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.

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

ConvexComb Operator #4696

Closed
qingqing01 opened this issue Oct 11, 2017 · 1 comment
Closed

ConvexComb Operator #4696

qingqing01 opened this issue Oct 11, 2017 · 1 comment
Assignees
@mkliegl
Labels
OpPorting
Projects
Port Operators

Comments

@qingqing01
Copy link
Contributor

This is really just a special case of batched matrix multiply: #4683

weight: k x d x 1 (reshaped from k x d)
input: k x n x d
output: k x n x 1 (batched matrix mult of input x weight)

(we can flatten back to k x n)
@qingqing01 qingqing01 created this issue from a note in Port Operators (Base on Tensor) Oct 11, 2017
@qingqing01
Copy link
Contributor Author

qingqing01 commented Oct 11, 2017 •
edited
Loading

related to #4683 . If the issue #4683 is closed, this issue also can be closed.

@qingqing01 qingqing01 moved this from Base on Tensor to Doing in Port Operators Oct 11, 2017
@mkliegl mkliegl mentioned this issue Oct 17, 2017
Merged
@mkliegl mkliegl moved this from Doing to Done in Port Operators Oct 18, 2017
@mkliegl mkliegl closed this as completed Oct 18, 2017
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@mkliegl mkliegl

Labels
OpPorting
Projects
Port Operators
Done
Milestone
No milestone
Development

No branches or pull requests
2 participants
@mkliegl @qingqing01