The scarches command below:
scarches_model = sca.models.SCVI.load_query_data( adata=adata_to_map_augmented, reference_model="./reference_model", freeze_dropout=True)
gave the following error:
RuntimeError: The NVIDIA driver on your system is too old (found version 11040). Please update your GPU driver by downloading and installing a new version from the URL: http://www.nvidia.com/Download/index.aspx Alternatively, go to: https://pytorch.org to install a PyTorch version that has been compiled with your version of the CUDA driver.
nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2021 NVIDIA Corporation
Built on Thu_Nov_18_09:45:30_PST_2021
Cuda compilation tools, release 11.5, V11.5.119
Build cuda_11.5.r11.5/compiler.30672275_0
12.1
So, I ran the following:
pip install light-the-torch
ltt install torch torchvision
Looks like my cuda and torch versions are not same. it is scary to update nvidia drivers without backing up. Coz this may result in issues. So thought I will not delve into cuda for now.
But again I got this error:
RuntimeError: Detected that PyTorch and torchvision were compiled with different CUDA major versions. PyTorch has CUDA Version=12.1 and torchvision has CUDA Version=11.8. Please reinstall the torchvision that matches your PyTorch install.
I did the following:
conda install pytorch torchvision torchaudio pytorch-cuda=12.1 -c pytorch -c nvidia
This time again another error:
undefined symbol when importing torchaudio with pytorch...
Now, did the following, the above error was resolved
pip install -U torch torchaudio --no-cache-dir
Instead of gpu I relied on CPU.
scarches_model = sca.models.SCVI.load_query_data( adata=adata_to_map_augmented, reference_model="./reference_model", freeze_dropout=True, use_gpu=False )
Now, I have only a warning as below:
WARNING:jax._src.xla_bridge:An NVIDIA GPU may be present on this machine, but a CUDA-enabled jaxlib is not installed. Falling back to cpu.
