search

Ugness / PiCANet-Implementation

Pytorch Implementation of PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection
MIT License
178 stars 40 forks source link

Running error #3

Closed githubBingoChen closed 5 years ago

githubBingoChen commented 6 years ago

When I change the path of duts's training set, I get some error like torch.backends.cudnn.CuDNNError: 4: CUDNN_STATUS_INTERNAL_ERROR Exception ctypes.ArgumentError: "argument 1: <type 'exceptions.TypeError'>: Don't know how to convert parameter 1" in <bound method CuDNNHandle.del of <torch.backends.cudnn.CuDNNHandle instance at 0x7fc76508a248>> ignored Could you upload a guidance that explain how to use your code for convenience?

Ugness commented 6 years ago

I am sorry. I didn't see that error before, so it's hard to solve that problem. Can you find the line in my code that the error occured? I think that you got the error because you don't have gpu to use cuda or cudnn. My suggestion is in train.py 20 line,
device = torch.device("cuda") to device = torch.device("cpu")

This is my computing environment NVIDIA gtx 1080ti windows 10 python 3.5 pytorch 0.4.0 CUDA 9.0 CUDNN 7.0

And also there are some mismatch cases in DUTS dataset. Please check the dataset carefully. I hope you solve this problem.