Torch is not using gpu full performance

1

Hi when i try to run two CNN algorithms with separate torch weights the execution is slow. Also i checked the GPU utilization it is not fully utilized it is lying in 30% only . I need to use full GPU potential when parallely running two algorithms. kindly help me to overcome this issue.

Algorithms links
1.GitHub - ultralytics/ultralytics: NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite
2.GitHub - bigmb/Unet-Segmentation-Pytorch-Nest-of-Unets: Implementation of different kinds of Unet Models for Image Segmentation - Unet , RCNN-Unet, Attention Unet, RCNN-Attention Unet, Nested Unet

2

Profile your code and check where the bottleneck is using the native PyTorch profiler or e.g. Nsight Systems.