search

jfzhang95 / pytorch-video-recognition

PyTorch implemented C3D, R3D, R2Plus1D models for video activity recognition.
MIT License
1.18k stars 250 forks source link

C3D training from scratch met RuntimeError: CUDNN_STATUS_EXECUTION_FAILED #41

Open Magsun opened 4 years ago

Magsun commented 4 years ago

Hello @jfzhang95 , thanks for your code firstly.

I'm trying to train C3D from scratch on my own ucf101 style dataset.

I changed ucf101 config from 101 to 2 & num_workers=1 in train.py and dataset path in mypath.py, except mentioned above I didn't change any other settings.

When I run 'python train.py', I got this runtime error and don't know what happened.

Traceback (most recent call last): File "C:/Users/google/Desktop/pytorch-video-recognition-master/train.py", line 203, in train_model() File "C:/Users/google/Desktop/pytorch-video-recognition-master/train.py", line 131, in train_model outputs = model(inputs) File "D:\Anaconda3\envs\video\lib\site-packages\torch\nn\modules\module.py", line 491, in call result = self.forward(*input, *kwargs) File "C:\Users\google\Desktop\pytorch-video-recognition-master\network\C3D_model.py", line 46, in forward x = self.relu(self.conv1(x)) File "D:\Anaconda3\envs\video\lib\site-packages\torch\nn\modules\module.py", line 491, in call result = self.forward(input, **kwargs) File "D:\Anaconda3\envs\video\lib\site-packages\torch\nn\modules\conv.py", line 421, in forward self.padding, self.dilation, self.groups) RuntimeError: CUDNN_STATUS_EXECUTION_FAILED

The env is win10 cuda9 torch0.4.0, I'm not sure if I should run this under linux.

Thanks if anyone can help.

Magsun commented 4 years ago

cudann 7.6.1

vaibhav0195 commented 4 years ago

Hi magsun, Hope you have solved the error, but if not this might help you. This error usually occurs when there is compatibility issue with the driver or with the cudnn and the pytorch. Please refer here : https://discuss.pytorch.org/t/cudnn-error-cudnn-status-mapping-error/69079 for me by adding the line torch.backends.cudnn.enabled = False worked.

Thanks.

Magsun commented 4 years ago

Hi magsun, Hope you have solved the error, but if not this might help you. This error usually occurs when there is compatibility issue with the driver or with the cudnn and the pytorch. Please refer here : https://discuss.pytorch.org/t/cudnn-error-cudnn-status-mapping-error/69079 for me by adding the line torch.backends.cudnn.enabled = False worked.

Thanks.

Oh, thanks for your help, I tried another version of pytorch and it works.

I just use torch=0.4.1 instead of 0.4.0. I'll try it your way.

Thanks again!