C:\ProgramData\Miniconda3\envs\simswap\lib\site-packages\torch\cuda__init__.py:104: UserWarning:
NVIDIA GeForce RTX 3090 with CUDA capability sm_86 is not compatible with the current PyTorch installation.
The current PyTorch install supports CUDA capabilities sm_37 sm_50 sm_60 sm_61 sm_70 sm_75 compute_37.
If you want to use the NVIDIA GeForce RTX 3090 GPU with PyTorch, please check the instructions at https://pytorch.org/get-started/locally/
C:\ProgramData\Miniconda3\envs\simswap\lib\site-packages\torch\cuda\__init__.py:104: UserWarning:
NVIDIA GeForce RTX 3090 with CUDA capability sm_86 is not compatible with the current PyTorch installation.
The current PyTorch install supports CUDA capabilities sm_37 sm_50 sm_60 sm_61 sm_70 sm_75 compute_37.
If you want to use the NVIDIA GeForce RTX 3090 GPU with PyTorch, please check the instructions at https://pytorch.org/get-started/locally/
warnings.warn(incompatible_device_warn.format(device_name, capability, " ".join(arch_list), device_name))
Theoretically, it can be inference on the cpu. But inference time will be much longer than on gpu. So I recommend you to use colab instead of your own cpu
Theoretically, it can be inference on the cpu. But inference time will be much longer than on gpu. So I recommend you to use [colab](https://colab.research.google.com/github/neuralchen/SimSwap/blob/main/SimSwap%20colab.ipynb) instead of your own cpu
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Can you describe in detail how it doesn't work. For example, bug reports and the like.
C:\ProgramData\Miniconda3\envs\simswap\lib\site-packages\torch\cuda__init__.py:104: UserWarning:
NVIDIA GeForce RTX 3090 with CUDA capability sm_86 is not compatible with the current PyTorch installation.
The current PyTorch install supports CUDA capabilities sm_37 sm_50 sm_60 sm_61 sm_70 sm_75 compute_37.
If you want to use the NVIDIA GeForce RTX 3090 GPU with PyTorch, please check the instructions at https://pytorch.org/get-started/locally/
warnings.warn(incompatible_device_warn.format(device_name, capability, " ".join(arch_list), device_name))
conda install pytorch torchvision torchaudio cudatoolkit=10.2 -c pytorch
just try
pip install torch==1.7.0+cu110 torchvision==0.8.1+cu110 torchaudio===0.7.0 -f https://download.pytorch.org/whl/torch_stable.html
pip install --pre torch torchvision torchaudio -f https://download.pytorch.org/whl/nightly/cu110/torch_nightly.html
Try it
pip install error,wuwu
IValueError: check_hostname requires server_hostname
I'v finished the virtual environment...
thanks, I'v slove it
@NNNNAI can inference be done on cpu?
Theoretically, it can be inference on the cpu. But inference time will be much longer than on gpu. So I recommend you to use colab instead of your own cpu