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

I feel that the processing speed is a little slow #91

New Issue
Open
opened 2021-08-16 03:54:55 +02:00 by wubangjunjava · 11 comments
wubangjunjava commented 2021-08-16 03:54:55 +02:00 (Migrated from github.com)
Copy Link

I feel that the processing speed is a little slow. How can I improve it? It takes too long for a video to be processed.

I feel that the processing speed is a little slow. How can I improve it? It takes too long for a video to be processed.
NNNNAI commented 2021-08-17 04:27:46 +02:00 (Migrated from github.com)
Copy Link

You can install the gpu version of onnx, the time to process a video will be greatly reduced. Using the command line below should be fine:

pip install onnxruntime-gpu==1.2.0

(Note: the version of onnxruntime-gpu may vary,which depend on you cuda version)

You can install the gpu version of onnx, the time to process a video will be greatly reduced. Using the command line below should be fine: ``` pip install onnxruntime-gpu==1.2.0 ``` (Note: the version of onnxruntime-gpu may vary,which depend on you cuda version)
wubangjunjava commented 2021-08-17 04:36:42 +02:00 (Migrated from github.com)
Copy Link

You can install the gpu version of onnx, the time to process a video will be greatly reduced. Using the command line below should be fine:

pip install onnxruntime-gpu==1.2.0

(Note: the version of onnxruntime-gpu may vary,which depend on you cuda version)

thank you. Problem solving.

> You can install the gpu version of onnx, the time to process a video will be greatly reduced. Using the command line below should be fine: > > ``` > pip install onnxruntime-gpu==1.2.0 > ``` > > (Note: the version of onnxruntime-gpu may vary,which depend on you cuda version) thank you. Problem solving.
ramnnv commented 2021-08-17 07:40:31 +02:00 (Migrated from github.com)
Copy Link

You can install the gpu version of onnx, the time to process a video will be greatly reduced. Using the command line below should be fine:

pip install onnxruntime-gpu==1.2.0

(Note: the version of onnxruntime-gpu may vary,which depend on you cuda version)

Hi. My installation of SimSwap was doing great and working perfectly, but i update to onnxruntime and now im getting error and not working. May you help me to know what i doing wrong please, im newbie with all of this but i want to try that speed improvement. Thank you for all your work.

I have Windows 10, GTX 1060 6gb and my SimSwap installation are on my second hard drive (E:)

C:\Users\ramnnv\anaconda3\envs\simswap\lib\site-packages\onnxruntime\capi_pybind_state.py:13: UserWarning: Cannot load onnxruntime.capi. Error: 'DLL load failed: No se puede encontrar el módulo especificado.'
warnings.warn("Cannot load onnxruntime.capi. Error: '{0}'".format(str(e)))
Traceback (most recent call last):
File "C:\Users\ramnnv\anaconda3\envs\simswap\lib\site-packages\insightface_init_.py", line 8, in
import onnxruntime
File "C:\Users\ramnnv\anaconda3\envs\simswap\lib\site-packages\onnxruntime_init_.py", line 12, in
from onnxruntime.capi._pybind_state import get_all_providers, get_available_providers, get_device, RunOptions, SessionOptions, set_default_logger_severity, NodeArg, ModelMetadata, GraphOptimizationLevel, ExecutionMode
ImportError: cannot import name 'get_all_providers'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "test_video_swapsingle.py", line 11, in
from insightface_func.face_detect_crop_single import Face_detect_crop
File "E:\SimSwap\SimSwap-main\insightface_func\face_detect_crop_single.py", line 8, in
from insightface.model_zoo import model_zoo
File "C:\Users\ramnnv\anaconda3\envs\simswap\lib\site-packages\insightface_init_.py", line 11, in
"Unable to import dependency onnxruntime. "
ImportError: Unable to import dependency onnxruntime.

> > > You can install the gpu version of onnx, the time to process a video will be greatly reduced. Using the command line below should be fine: > > ``` > pip install onnxruntime-gpu==1.2.0 > ``` > > (Note: the version of onnxruntime-gpu may vary,which depend on you cuda version) Hi. My installation of SimSwap was doing great and working perfectly, but i update to onnxruntime and now im getting error and not working. May you help me to know what i doing wrong please, im newbie with all of this but i want to try that speed improvement. Thank you for all your work. I have Windows 10, GTX 1060 6gb and my SimSwap installation are on my second hard drive (E:) > C:\Users\ramnnv\anaconda3\envs\simswap\lib\site-packages\onnxruntime\capi\_pybind_state.py:13: UserWarning: Cannot load onnxruntime.capi. Error: 'DLL load failed: No se puede encontrar el módulo especificado.' > warnings.warn("Cannot load onnxruntime.capi. Error: '{0}'".format(str(e))) > Traceback (most recent call last): > File "C:\Users\ramnnv\anaconda3\envs\simswap\lib\site-packages\insightface\__init__.py", line 8, in <module> > import onnxruntime > File "C:\Users\ramnnv\anaconda3\envs\simswap\lib\site-packages\onnxruntime\__init__.py", line 12, in <module> > from onnxruntime.capi._pybind_state import get_all_providers, get_available_providers, get_device, RunOptions, SessionOptions, set_default_logger_severity, NodeArg, ModelMetadata, GraphOptimizationLevel, ExecutionMode > ImportError: cannot import name 'get_all_providers' > > During handling of the above exception, another exception occurred: > > Traceback (most recent call last): > File "test_video_swapsingle.py", line 11, in <module> > from insightface_func.face_detect_crop_single import Face_detect_crop > File "E:\SimSwap\SimSwap-main\insightface_func\face_detect_crop_single.py", line 8, in <module> > from insightface.model_zoo import model_zoo > File "C:\Users\ramnnv\anaconda3\envs\simswap\lib\site-packages\insightface\__init__.py", line 11, in <module> > "Unable to import dependency onnxruntime. " > ImportError: Unable to import dependency onnxruntime. >
NNNNAI commented 2021-08-17 08:20:48 +02:00 (Migrated from github.com)
Copy Link

@ramnnv Did you use this command line :pip install onnxruntime-gpu==1.2.0 to install onnx gpu? If so ,you can try to use older version of onnx gpu like 1.1.2 by using pip install onnxruntime-gpu==1.1.2

@ramnnv Did you use this command line :***pip install onnxruntime-gpu==1.2.0*** to install onnx gpu? If so ,you can try to use older version of onnx gpu like 1.1.2 by using pip install onnxruntime-gpu==1.1.2
ramnnv commented 2021-08-17 10:20:09 +02:00 (Migrated from github.com)
Copy Link

@NNNNAI yes, first i use 1.2.0, then i tried the old version you said (1.1.2), but still getting the same error. Now i back to the cpu onnx and SimSwap it's working again...

@NNNNAI yes, first i use 1.2.0, then i tried the old version you said (1.1.2), but still getting the same error. Now i back to the cpu onnx and SimSwap it's working again...
NNNNAI commented 2021-08-17 10:31:55 +02:00 (Migrated from github.com)
Copy Link

@ramnnv which version of cuda did you use.You can type nvcc -V in your terminal to find out the cuda version

@ramnnv which version of cuda did you use.You can type nvcc -V in your terminal to find out the cuda version
ramnnv commented 2021-08-17 10:38:13 +02:00 (Migrated from github.com)
Copy Link

@NNNNAI CUDA Version: 11.2

@NNNNAI CUDA Version: 11.2
NNNNAI commented 2021-08-17 10:43:05 +02:00 (Migrated from github.com)
Copy Link

As shown in the offcial website of onnx,you could try to install 1.7.0 or 1.8.0
image
@ramnnv

As shown in the offcial website of [onnx](https://onnxruntime.ai/docs/reference/execution-providers/CUDA-ExecutionProvider.html#version-dependency),you could try to install 1.7.0 or 1.8.0 ![image](https://user-images.githubusercontent.com/30747212/129693699-55eb1ede-8a97-4ae6-9859-bc79815cf7f3.png) @ramnnv
👍 1
ramnnv commented 2021-08-18 01:32:30 +02:00 (Migrated from github.com)
Copy Link

@NNNNAI I just tried 1.7.0 and 1.8.0 and got the same error, but thank you for trying to help me. In a few days i will reinstall windows, anaconda, gpu drivers, simswap... etc, so let's hope my problem can be solved.

@NNNNAI I just tried 1.7.0 and 1.8.0 and got the same error, but thank you for trying to help me. In a few days i will reinstall windows, anaconda, gpu drivers, simswap... etc, so let's hope my problem can be solved.
NNNNAI commented 2021-08-18 05:41:04 +02:00 (Migrated from github.com)
Copy Link

Hope you can solve the problem, have a nice day.

Hope you can solve the problem, have a nice day.
JamesWilson19947 commented 2021-10-24 16:24:09 +02:00 (Migrated from github.com)
Copy Link

@NNNNAI I just tried 1.7.0 and 1.8.0 and got the same error, but thank you for trying to help me. In a few days i will reinstall windows, anaconda, gpu drivers, simswap... etc, so let's hope my problem can be solved.

Try 1.9.0. I think this should solve your issues.

pip install onnxruntime-gpu==1.9.0

> @NNNNAI I just tried 1.7.0 and 1.8.0 and got the same error, but thank you for trying to help me. In a few days i will reinstall windows, anaconda, gpu drivers, simswap... etc, so let's hope my problem can be solved. Try 1.9.0. I think this should solve your issues. ```pip install onnxruntime-gpu==1.9.0```
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 Increase inference time
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#91
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?