-
Notifications
You must be signed in to change notification settings - Fork 152
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
AssertionError: Torch not compiled with CUDA enabled #34
Comments
Are you running on MacOS? |
Hi Jixiaozhong/Sonic,
no, i am running on the windows.
and is it possible that the output video keeps the original size and layout
of the picture we uploaded?
regards,
xiao
…On Wed, Jan 22, 2025 at 10:16 AM jonny ***@***.***> wrote:
Are you running on MacOS?
—
Reply to this email directly, view it on GitHub
<#34 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AYMJDTHRAFPMQBRLT2ZIKJT2L7OBDAVCNFSM6AAAAABVTN3XT6VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDMMBXHE2DGMBUGM>
.
You are receiving this because you authored the thread.Message ID:
***@***.***>
|
1 Try to install on windows Better to install torch using cu124 pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu124 2 keeps the original size and layout |
thanks very much.
i have it installed correctly on my linux system.
i am wondering for the windows system, do you have a preferred python
version?
…On Thu, Jan 23, 2025 at 2:52 AM Jin ***@***.***> wrote:
1 Try to install on windows
See #17 <#17>
Better to install torch using cu124
pip install torch torchvision torchaudio --index-url
https://download.pytorch.org/whl/cu124
2 keeps the original size and layout
#27 <#27>
—
Reply to this email directly, view it on GitHub
<#34 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AYMJDTAEVKLVCAHQWTDYSED2MDCW5AVCNFSM6AAAAABVTN3XT6VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDMMBZGQ4TAMZYGY>
.
You are receiving this because you authored the thread.Message ID:
***@***.***>
|
I test on windows with python 3.10 or 3.11, |
Traceback (most recent call last):
File "D:\ai\sonic\Sonic\demo.py", line 4, in
pipe = Sonic(0)
File "D:\ai\sonic\Sonic\sonic.py", line 160, in init
audio2token = AudioProjModel(seq_len=10, blocks=5, channels=384, intermediate_dim=1024, output_dim=1024, context_tokens=32).to(device)
File "C:\Users\bunny\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1152, in to
return self._apply(convert)
File "C:\Users\bunny\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 802, in _apply
module._apply(fn)
File "C:\Users\bunny\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 825, in apply
param_applied = fn(param)
File "C:\Users\bunny\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1150, in convert
return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
File "C:\Users\bunny\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\cuda_init.py", line 293, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled
how can i solve this issue?
i already have the pytorch installed.
The text was updated successfully, but these errors were encountered: