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

After generating .rt, there is no check boxes when using demo.exe to test #256

New Issue
Closed
opened 2021-08-19 13:01:34 +02:00 by B1ackg0d · 10 comments
B1ackg0d commented 2021-08-19 13:01:34 +02:00 (Migrated from github.com)
Copy Link
Copy Source

After the .rt is generated, the display is as follows：
image

After the .rt is generated, the display is as follows： ![image](https://user-images.githubusercontent.com/50610732/130055428-f1415930-dc52-4a32-8822-d818e86873be.png)
mive93 commented 2021-08-19 17:06:48 +02:00 (Migrated from github.com)
Copy Link
Copy Source

It seems like the debug file are missing.
Does the demo work?
Which steps did you follow to reach that result?

It seems like the debug file are missing. Does the demo work? Which steps did you follow to reach that result?
B1ackg0d commented 2021-08-19 17:38:04 +02:00 (Migrated from github.com)
Copy Link
Copy Source

Hi,mive93!I thought the debug file was not necessary, so I didn’t care about it.
I first used darknet to export the weights. Then I changed the names and cfg files under tkdnn/test/darknet. Then use test_yolo4.exe to generate the rt file, it is as shown in the figure above. Then I run demo.exe to test rt file, and I find that there is no check boxes.

Hi,mive93!I thought the debug file was not necessary, so I didn’t care about it. I first used darknet to export the weights. Then I changed the names and cfg files under tkdnn/test/darknet. Then use test_yolo4.exe to generate the rt file, it is as shown in the figure above. Then I run demo.exe to test rt file, and I find that there is no check boxes.
mive93 commented 2021-08-19 17:41:02 +02:00 (Migrated from github.com)
Copy Link
Copy Source

You should export the debug and check if the conversion works fine.

You should export the debug and check if the conversion works fine.
B1ackg0d commented 2021-08-19 17:43:40 +02:00 (Migrated from github.com)
Copy Link
Copy Source

This is what it says in the document，‘if you need debug export of every layer ouput you MUST compile in CPU mode’,I’m not sure how to compile with cpu, so I didn’t use.

This is what it says in the document，‘if you need debug export of every layer ouput you MUST compile in CPU mode’,I’m not sure how to compile with cpu, so I didn’t use.
mive93 commented 2021-08-19 17:50:12 +02:00 (Migrated from github.com)
Copy Link
Copy Source

It's quite easy, just leave GPU=0 in darknet makefile

It's quite easy, just leave ```GPU=0``` in darknet makefile
B1ackg0d commented 2021-08-19 17:52:57 +02:00 (Migrated from github.com)
Copy Link
Copy Source

Thank you very much! I will try it. After modifying it, recompiling, and then using export, will there be a debug file?

Thank you very much! I will try it. After modifying it, recompiling, and then using export, will there be a debug file?
mive93 commented 2021-08-19 17:54:23 +02:00 (Migrated from github.com)
Copy Link
Copy Source

A debug folder. Just create the debug and layers folder in advance.

A debug folder. Just create the debug and layers folder in advance.
B1ackg0d commented 2021-08-19 18:01:22 +02:00 (Migrated from github.com)
Copy Link
Copy Source

Thank you for your reply! I have another question. Do the parameters in the training cfg, the exported cfg and the cfg used by tkdnn all need to be consistent?Especially the size of batchsize.

Thank you for your reply! I have another question. Do the parameters in the training cfg, the exported cfg and the cfg used by tkdnn all need to be consistent?Especially the size of batchsize.
mive93 commented 2021-08-20 09:15:27 +02:00 (Migrated from github.com)
Copy Link
Copy Source

Yes, they need to be consistent, but the batch size of that config (only used for training) is not used in tkDNN.

Yes, they need to be consistent, but the batch size of that config (only used for training) is not used in tkDNN.
B1ackg0d commented 2021-08-20 12:32:12 +02:00 (Migrated from github.com)
Copy Link
Copy Source

It's quite easy, just leave GPU=0 in darknet makefile.

If I use VS2019 to compile darknet in Windows, can I just use this sln directly?
image

> It's quite easy, just leave `GPU=0` in darknet makefile. If I use VS2019 to compile darknet in Windows, can I just use this sln directly? ![image](https://user-images.githubusercontent.com/50610732/130220409-4cfd4e95-4078-42a4-901a-cfca2fbf1bbd.png)
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#256
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?