Open victorhqx opened 3 years ago
AttributeError: 'NoneType' object has no attribute 'serialize'
why
The AttributeError isn't the main problem here; the actual error is occurring at the TensorRT cublas lines. When the TRT engine can't be initialized (in this case, because of cublas issues), it returns None, causing the AttributeError downstream.
The "Could not initialize cublas" error has two main causes: first, you may have installed CUDA incorrectly, or installed a version of CUDA incompatible with your driver. Make sure your driver, CUDA, cudnn, and TensorRT versions are all compatible by checking their official installation guides. The second main culprit behind a bad cublas init is an out-of-memory error (which isn't made clear by the given error message). I've noticed some other people complain that yolact edge has large memory demands, so I would suspect this is your problem (unless you're using a GPU with >4GB of VRAM).
Also, if this is an issue specific to yolact edge, I would suggest posting an issue on their repo instead. After all, it appears that this error occurs inside of their eval.py.
CUDA OOM was a problem in my case! Thanks @nhewitt99 !
CUDA OOM was a problem in my case! Thanks @nhewitt99 !
@nhewitt99 i can't fix error torch.save(model_trt.state_dict(),"model.trt") please help me to fix in jetson nano
when I try to use torch2trt in yolactedge evaluation:
What is the problem?