RuntimeError: CUDA error: device-side assert triggered

[FYL0123]

Hello, I used a single 4090GPU to try to reproduce your work and the following error occurred. Do you have a solution?

thresh_mask = logits.ge(thresh).bool() * (target != 255).bool()
RuntimeError: CUDA error: device-side assert triggered
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.
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

[ZhenZHAO]

Sorry, I was using multiple gpus and single node. I will try single GPU later.