Cannot run pytorch with GTX 730 4GB GPU

Accelerated Computing CUDA CUDA Programming and Performance
1

Hi,
I am using GTX 730 4GB GPU with compute capability - 3.5
I have a yolov3 model which is built on darknet and PyTorch but whenever I run the .py model, it throws an error-

CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.

Let me brief you about the situation - I’m using NVIDIA-SMI 470.57.02 Driver Version: 470.57.02 CUDA Version: 11.4 and have built PyTorch from source on Ubuntu 20.04 LTS OS. But still, I’m not able to run the model.

I just wanna know what is the issue with this setup and another thing is that whether I should jump to a lower cuda version and Nvidia driver and then try to run the model?

I would also need an answer whether this dGPU can run this model or not?

@dusty_nv any help you can provide?