Using the conda environment from deepsatmodels_env.yml followed by conda install pytorch torchvision torchaudio cudatoolkit=10.1 -c pytorch-nightly, followed by running the training command leads to the following error:
Traceback (most recent call last):
File "train_and_eval/segmentation_training_transf.py", line 5, in <module>
import torch
File "/opt/conda/envs/deepsatmodels/lib/python3.8/site-packages/torch/__init__.py", line 364, in <module>
from torch._C import * # noqa: F403
ImportError: /opt/conda/envs/deepsatmodels/lib/python3.8/site-packages/torch/lib/libtorch_cpu.so: undefined symbol: cblas_gemm_bf16bf16f32
Upgrading the pytorch and torchvision doesnt seem to help.
CUDA version 12.4
Using the conda environment from
deepsatmodels_env.yml
followed byconda install pytorch torchvision torchaudio cudatoolkit=10.1 -c pytorch-nightly
, followed by running the training command leads to the following error:Upgrading the pytorch and torchvision doesnt seem to help. CUDA version 12.4