CalvinBackup/neuralchen-SimSwap
1
0
Fork 0
Code Issues 288 Pull Requests 16 Actions Packages Projects Releases 2 Wiki Activity

Slow inference | GPU Issue #147

New Issue
Open
opened 2021-11-07 06:46:27 +01:00 by SaroshZDandoti · 5 comments
SaroshZDandoti commented 2021-11-07 06:46:27 +01:00 (Migrated from github.com)
Copy Link

Hello, I cant seem to get my GPU to use for training.
I have :
gtx 1650 4GB
windows 11
CUDA: 11.5

onnx runtime GPU version : 1.9

I have these installed and my GPU is not being used.

Training and everything is working just fine, but it's very slow
I'm getting like: 2.5 it/s

Please help me how can I fix this.
I have read other similar issues , and cant seems to find an answer.
If i want to install old CUDA versions , they are not available for windows 11.
Thanks in Advance!!!

Edit : Slow Inference not Training

Hello, I cant seem to get my GPU to use for training. I have : gtx 1650 4GB windows 11 CUDA: 11.5 onnx runtime GPU version : 1.9 I have these installed and my GPU is not being used. ~~Training~~ and everything is working just fine, but it's very slow I'm getting like: 2.5 it/s Please help me how can I fix this. I have read other similar issues , and cant seems to find an answer. If i want to install old CUDA versions , they are not available for windows 11. Thanks in Advance!!! Edit : Slow Inference not Training
jz-exwzd commented 2021-11-08 01:06:19 +01:00 (Migrated from github.com)
Copy Link

Did you write the training codes yourself?

Did you write the training codes yourself?
SaroshZDandoti commented 2021-11-08 03:38:32 +01:00 (Migrated from github.com)
Copy Link

Did you write the training codes yourself?

What? no. I'm just trying to run the scripts with Anaconda Prompt, everything runs fine but its very slow.

> Did you write the training codes yourself? What? no. I'm just trying to run the scripts with Anaconda Prompt, everything runs fine but its very slow.
jz-exwzd commented 2021-11-08 04:22:15 +01:00 (Migrated from github.com)
Copy Link

Did you write the training codes yourself?

What? no. I'm just trying to run the scripts with Anaconda Prompt, everything runs fine but its very slow.

It is not training then, as stated in your title of the issue.
It should be "slow inference".
In fact, they do not provide the code for training, just inferencing.
Correct me if I am wrong.

> > Did you write the training codes yourself? > > What? no. I'm just trying to run the scripts with Anaconda Prompt, everything runs fine but its very slow. It is not training then, as stated in your title of the issue. It should be "slow inference". In fact, they do not provide the code for training, just inferencing. Correct me if I am wrong.
SaroshZDandoti commented 2021-11-08 05:21:16 +01:00 (Migrated from github.com)
Copy Link

Did you write the training codes yourself?

What? no. I'm just trying to run the scripts with Anaconda Prompt, everything runs fine but its very slow.

It is not training then, as stated in your title of the issue. It should be "slow inference". In fact, they do not provide the code for training, just inferencing. Correct me if I am wrong.

Yep, you are right, that's my bad and i apologize for being careless about it.
Anyways, i don't seem to know what's wrong with it.

I have checked if GPU is available with torch.is_cuda_available as well and it says true.
But it seems that only GPU is not being used at all.

> > > Did you write the training codes yourself? > > > > > > What? no. I'm just trying to run the scripts with Anaconda Prompt, everything runs fine but its very slow. > > It is not training then, as stated in your title of the issue. It should be "slow inference". In fact, they do not provide the code for training, just inferencing. Correct me if I am wrong. Yep, you are right, that's my bad and i apologize for being careless about it. Anyways, i don't seem to know what's wrong with it. I have checked if GPU is available with torch.is_cuda_available as well and it says true. But it seems that only GPU is not being used at all.
👍 1 👀 1
whenupdate commented 2021-11-20 17:21:24 +01:00 (Migrated from github.com)
Copy Link

have same issue, only take 2GB GPU maximum working. are u solve this issue ?

have same issue, only take 2GB GPU maximum working. are u solve this issue ?
👍 1
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
GIF
GUI
Increase inference time
A solution to increase inference time
 bug
Something isn't working
 documentation
Improvements or additions to documentation
 duplicate
This issue or pull request already exists
 enhancement
New feature or request
 good first issue
Good for newcomers
 help wanted
Extra attention is needed
 invalid
This doesn't seem right
 question
Further information is requested
 wontfix
This will not be worked on
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
CalvinBackup
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: CalvinBackup/neuralchen-SimSwap#147
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?