-
Notifications
You must be signed in to change notification settings - Fork 1k
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
Deconvolutions improve performance of AH-Net #1023
Comments
Hi @yiheng-wang-nv , I remember you fixed some determinism issue about the upsampling in AHNet, is it related to this ticket? Thanks. |
that's noted in the docstring @Nic-Ma MONAI/monai/networks/nets/ahnet.py Lines 353 to 355 in 8fc4f5d
|
FYI, the non-determinism issue is explained in an old PR. Generally speaking,
|
Describe the bug
In the current environment deconvolutions work significantly faster with mixed precision than trilinear interpolation for upsampling. In the current Monai implementation of AH-Net the
upsample_mode
defaults to "trilinear", which is suboptimal.To Reproduce
Run training with
upsample_mode="trilinear"
andupsample_mode="transpose"
.Expected behavior
The default
upsample_mode
is changed totranspose
.Screenshots
![image](https://user-images.githubusercontent.com/43240942/92876049-f75a6180-f409-11ea-9bdf-0851fd7dca40.png)
Throughput measured on V100 and A100 for a 3D workload.
Environment (please complete the following information):
Additional context
In cuDNN 8.0.3 deconvolutions have Tensor Core support which improves their performance significantly.
Currently there are issues being tracked for Pytorch and cuDNN which might improve performance. I'll monitor the status and update if needed.
The text was updated successfully, but these errors were encountered: