Hi,anyone can help me?

1

I have this problem in runing code!

’
Traceback (most recent call last):
File “train.py”, line 54, in
train(opt,model)
File “train.py”, line 34, in train
outputs=model(image)
File “/home/a/anaconda3/envs/bcw_env/lib/python3.6/site-packages/torch/nn/modules/module.py”, line 489, in call
result = self.forward(*input, **kwargs)
File “/home/a/Bcw_data/FCN/model/FCN.py”, line 26, in forward
fc2nn=self.fc2conv(x5)
File “/home/a/anaconda3/envs/bcw_env/lib/python3.6/site-packages/torch/nn/modules/module.py”, line 489, in call
result = self.forward(*input, **kwargs)
File “/home/a/anaconda3/envs/bcw_env/lib/python3.6/site-packages/torch/nn/modules/container.py”, line 92, in forward
input = module(input)
File “/home/a/anaconda3/envs/bcw_env/lib/python3.6/site-packages/torch/nn/modules/module.py”, line 489, in call
result = self.forward(*input, **kwargs)
File “/home/a/anaconda3/envs/bcw_env/lib/python3.6/site-packages/torch/nn/modules/conv.py”, line 320, in forward
self.padding, self.dilation, self.groups)
RuntimeError: cuDNN error: CUDNN_STATUS_BAD_PARAM

’
Anyone can help me to solve this?Thanks!

2

Is your code running fine on the CPU?
If so, could you run it again using
CUDA_LAUNCH_BLOCKING=1 python script.py args?

3

Thanks for your reply!I will try it.Btw,this error is in running the FCN code .But,when I run the other code like yolov3 and other code use gpu,it’s normal.So I don’t know this is why?

4

Thanks for your reply!I will try it.Btw,this error is in running the FCN code .But,when I run the other code like yolov3 and other code use gpu,it’s normal.So I don’t know this is why?