mmr/tkDNN
Archived
1
0
Fork 0
Code Issues 46 Pull Requests 12 Releases 4 Activity

Large GPU memory consumption on Tensorrt8 branch #279

New Issue
Open
opened 2022-02-17 03:28:27 +01:00 by zhou-git · 0 comments
zhou-git commented 2022-02-17 03:28:27 +01:00 (Migrated from github.com)
Copy Link
Copy Source

I was been using tkdnn with tensort6/cuda10.0 for a while and everything works fine.
Recently I upgrade the gpu card from 2070 to A4000, so a upgrade of all related drivers is necessary.
Now the new environment is cuda11.5/tensorrt8.2.2.1/opencv4.5.5.
Now with the new environment, using the same trained model (Yolov4, network size: 530x320), the gpu memory usage increase from roughly 1GB to 2.5GB with fp32, 600MB to 1.9GB with fp16.

Any ideas why this is happening?
Thanks a lot for the great work by the way!

I was been using tkdnn with tensort6/cuda10.0 for a while and everything works fine. Recently I upgrade the gpu card from 2070 to A4000, so a upgrade of all related drivers is necessary. Now the new environment is cuda11.5/tensorrt8.2.2.1/opencv4.5.5. Now with the new environment, using the same trained model (Yolov4, network size: 530x320), the gpu memory usage increase from roughly 1GB to 2.5GB with fp32, 600MB to 1.9GB with fp16. Any ideas why this is happening? Thanks a lot for the great work by the way!
👍 1
This repo is archived. You cannot comment on issues.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
duplicate
enhancement
explanation
help wanted
invalid
question
wontfix
No Label
Milestone
No items
No Milestone
Assignees
Clear assignees
eeeck (Erick)
No Assignees
1 Participants
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: mmr/tkDNN#279
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?