You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
when I train with multiply GPU,an erro occur: File "/wytdata/Real-SR/codes/models/SRGAN_model.py", line 74, in __init__ model = create_model(opt) File "/wytdata/Real-SR/codes/models/__init__.py", line 14, in create_model m = M(opt) File "/wytdata/Real-SR/codes/models/SRGAN_model.py", line 74, in __init__ device_ids=[torch.cuda.current_device()]) File "/opt/conda/lib/python3.7/site-packages/torch/nn/parallel/distributed.py", line 238, in __init__ device_ids=[torch.cuda.current_device()]) File "/opt/conda/lib/python3.7/site-packages/torch/nn/parallel/distributed.py", line 238, in __init__ "DistributedDataParallel is not needed when a module " AssertionError: DistributedDataParallel is not needed when a module doesn't have any parameter that requires a gradient. "DistributedDataParallel is not needed when a module " AssertionError: DistributedDataParallel is not needed when a module doesn't have any parameter that requires a gradient.
The cause of the error appears to be to stop updating the parameters of VGG,Is there any solution?
if self.cri_fea: # load VGG perceptual loss
self.netF = networks.define_F(opt, use_bn=False).to(self.device)
if opt['dist']:
self.netF = DistributedDataParallel(self.netF,device_ids=[torch.cuda.current_device()]) #erro occurs here
else:
self.netF = DataParallel(self.netF)
The text was updated successfully, but these errors were encountered:
when I train with multiply GPU,an erro occur:
File "/wytdata/Real-SR/codes/models/SRGAN_model.py", line 74, in __init__ model = create_model(opt) File "/wytdata/Real-SR/codes/models/__init__.py", line 14, in create_model m = M(opt) File "/wytdata/Real-SR/codes/models/SRGAN_model.py", line 74, in __init__ device_ids=[torch.cuda.current_device()]) File "/opt/conda/lib/python3.7/site-packages/torch/nn/parallel/distributed.py", line 238, in __init__ device_ids=[torch.cuda.current_device()]) File "/opt/conda/lib/python3.7/site-packages/torch/nn/parallel/distributed.py", line 238, in __init__ "DistributedDataParallel is not needed when a module " AssertionError: DistributedDataParallel is not needed when a module doesn't have any parameter that requires a gradient. "DistributedDataParallel is not needed when a module " AssertionError: DistributedDataParallel is not needed when a module doesn't have any parameter that requires a gradient.
The cause of the error appears to be to stop updating the parameters of VGG,Is there any solution?
if self.cri_fea: # load VGG perceptual loss
self.netF = networks.define_F(opt, use_bn=False).to(self.device)
if opt['dist']:
self.netF = DistributedDataParallel(self.netF,device_ids=[torch.cuda.current_device()]) #erro occurs here
else:
self.netF = DataParallel(self.netF)
The text was updated successfully, but these errors were encountered: