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

Performance Issues on Jetson Xavier NX #230

New Issue
Open
opened 2021-05-19 07:37:36 +02:00 by MsWik · 4 comments
MsWik commented 2021-05-19 07:37:36 +02:00 (Migrated from github.com)
Copy Link
Copy Source

CV 4.5.0 + CUDA, jetpack 4.5.1.
Low performance of models like yolo4, yolo4x (lower than in the original darcnet), performance of tiny models is correct.
Also, when I try to convention any model in INT8, I get the following error:
failed to open 
/home/andry/test_jetson_xavier/tkDNN-master/tkDNN/src/Int8BatchStream.cpp:69
Aborting...

CV 4.5.0 + CUDA, jetpack 4.5.1. Low performance of models like yolo4, yolo4x (lower than in the original darcnet), performance of tiny models is correct. Also, when I try to convention any model in INT8, I get the following error: failed to open  /home/andry/test_jetson_xavier/tkDNN-master/tkDNN/src/Int8BatchStream.cpp:69 Aborting...
perseusdg commented 2021-05-19 08:17:23 +02:00 (Migrated from github.com)
Copy Link
Copy Source

Regarding the int8 model conversion ,have you downloaded the dataset and followed the steps mentioned in the Readme? Cause it looks there is a problem with your dataFilePath for image paths

And about the low performance on Xavier nx ...are you using the current master branch ?

Regarding the int8 model conversion ,have you downloaded the dataset and followed the steps mentioned in the Readme? Cause it looks there is a problem with your dataFilePath for image paths And about the low performance on Xavier nx ...are you using the current master branch ?
MsWik commented 2021-05-19 11:03:36 +02:00 (Migrated from github.com)
Copy Link
Copy Source

FP16 / FP32 dimension models are obtained correctly, the error occurs only when I use INT8. yes, the current master branch is used

FP16 / FP32 dimension models are obtained correctly, the error occurs only when I use INT8. yes, the current master branch is used
MsWik commented 2021-05-19 13:18:49 +02:00 (Migrated from github.com)
Copy Link
Copy Source

Yolo 4, yolo 4x performance issue resolved by reinstalling tkDNN, int8 issue not resolved yet.

Yolo 4, yolo 4x performance issue resolved by reinstalling tkDNN, int8 issue not resolved yet.
mive93 commented 2021-11-25 11:17:54 +01:00 (Migrated from github.com)
Copy Link
Copy Source

@MsWik have you downloaded the dataset as suggested by @perseusdg ?
Have you exported the needed env variables as explained here?

I tested everything yesterday on a Jetson Xavier AGX and I got no problems.

@MsWik have you downloaded the dataset as suggested by @perseusdg ? Have you exported the needed env variables as explained [here](https://github.com/ceccocats/tkDNN/blob/master/docs/demo.md#int8-inference)? I tested everything yesterday on a Jetson Xavier AGX and I got no problems.
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#230
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?