Fix GPU not being used even when it available

On lots of systems onnxruntime doesn't detect GPU unless pytorch is imported before it. So despite having CUDA and CUDNN setup correctly, it is only using CPUExecutionProvider. By importing pytorch first, the issue is fixed. So let's use this until any official solution is available.

See: https://stackoverflow.com/questions/75294639/onnxruntime-inference-with-cudnn-on-gpu-only-working-if-pytorch-imported-first

This commit is contained in:

Shivam Kumar

2023-05-31 09:20:41 +05:30

committed by

GitHub

parent 6258f3c084

commit 9c1ea4fa01

No known key found for this signature in database

GPG Key ID: 4AEE18F83AFDEB23

1 changed files with 1 additions and 0 deletions

									
										1

core/globals.py
									
										View File
										
				@ -1,3 +1,4 @@

				import torch

				import onnxruntime

				use_gpu = False

Fix GPU not being used even when it available

1 core/globals.py Unescape Escape View File

1

core/globals.py

View File