search

NVIDIA / flownet2-pytorch

Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Other
3.12k stars 738 forks source link

cuDNN error: CUDNN_STATUS_NOT_INITIALIZED #161

Open saijunhu opened 5 years ago

saijunhu commented 5 years ago

` File "/mnt/storage/husaijun/Projects/flownet2-pytorch/models.py", line 118, in forward flownetc_flow2 = self.flownetc(x)[0]

File "/home/husaijun/storage/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 493, in call result = self.forward(*input, **kwargs)

File "/mnt/storage/husaijun/Projects/flownet2-pytorch/networks/FlowNetC.py", line 75, in forward out_conv1a = self.conv1(x1)

File "/home/husaijun/storage/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 493, in call result = self.forward(*input, **kwargs)

File "/home/husaijun/storage/anaconda3/lib/python3.6/site-packages/torch/nn/modules/container.py", line 92, in forward input = module(input)

File "/home/husaijun/storage/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 493, in call result = self.forward(*input, **kwargs)

File "/home/husaijun/storage/anaconda3/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 338, in forward self.padding, self.dilation, self.groups) RuntimeError: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED `

my environment as follows:

my run command: ` python main.py --inference --model FlowNet2 --save_flow --save

--inference_dataset ImagesFromFolder --inference_dataset_root --resume /home/husaijun/storage/Projects/flownet2-pytorch/FlowNet2_checkpoint.pth.tar --number_gpus 3 --batch_size 1` thx!!!
Gong2Kun commented 2 years ago

if you take it,could you please me,my problem also is it;