search

NVIDIA-AI-IOT / cuDLA-samples

YOLOv5 on Orin DLA
Other
185 stars 18 forks source link

How to choose which DLA to run the code on? #23

Closed yunyao2011800 closed 8 months ago

yunyao2011800 commented 9 months ago

When I ran the project code, I found that DLA0 and GPU resources were being used, but DLA1 resources were not being used.

ou525 commented 9 months ago

You can change the '0' to '1' in the function cudlaCreateDevice(0, &m_DevHandle, CUDLA_CUDA_DLA), and then you can activate DLA1.