-
Notifications
You must be signed in to change notification settings - Fork 436
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
Learnable Align Attention Implementation #294
Comments
It sounds like voxels that they are talking about are in fact pillars with 1 per bev grid, but I'm not 100% sure. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
In the DeepFusion paper it was said that
So I think this should lead to
V x N
correlations for V voxel cells and if we consider batchesBxVxN
. However in the implementationaffinity = tf.einsum('bnc,bnc->bn', q, k)
producesBxN
shaped tensor. I feel like this should beaffinity = tf.einsum("bij,bkl->bik",q,k)
. I couldnt manage to wrap my head around this, what am I missing?Finally, thanks to the team for this great work.
@LiYingwei
The text was updated successfully, but these errors were encountered: