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

some doubt about convert to TensorRT engine? #260

New Issue
Closed
opened 2021-08-30 08:36:02 +02:00 by jcyhcs · 2 comments
jcyhcs commented 2021-08-30 08:36:02 +02:00 (Migrated from github.com)
Copy Link
Copy Source

hi,professor:
i have a weights file trained in darknet, with cfg resolution 608x608, when i use tkDNN to infer, think about speed, i may convert 416x416 tensorRT engine, so , can i just use the trained weights in 608*608? is there any modify should i do? please help!

hi,professor: i have a weights file trained in darknet, with cfg resolution 608x608, when i use tkDNN to infer, think about speed, i may convert 416x416 tensorRT engine, so , can i just use the trained weights in 608*608? is there any modify should i do? please help!
mive93 commented 2021-08-30 09:25:51 +02:00 (Migrated from github.com)
Copy Link
Copy Source

Hi @jcyhcs,

Yes you can. When you export the weights in tkDNN format, you should change the width and height of the cfg file to 416x416.

Hi @jcyhcs, Yes you can. When you [export the weights in tkDNN format](https://github.com/ceccocats/tkDNN/blob/master/docs/exporting_weights.md#1export-weights-from-darknet), you should change the width and height of the cfg file to 416x416.
mive93 commented 2021-11-25 11:12:30 +01:00 (Migrated from github.com)
Copy Link
Copy Source

Closing for inactivity

Closing for inactivity
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#260
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?