NVIDIA / flownet2-pytorch

Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Other
3.12k stars 739 forks source link

unexpected keyword argument 'fp16' #233

Open karims opened 4 years ago

karims commented 4 years ago

I am usinf flownet from inside vid2vid. I get this following error. Any idea how to resolve this? Using with docker, Ubuntu 16, pytorch 1.0.0

Traceback (most recent call last):
  File "train.py", line 149, in <module>
    train()
  File "train.py", line 28, in train
    models = create_model(opt)
  File "/vid2vid/models/models.py", line 83, in create_model
    flowNet.initialize(opt)
  File "/vid2vid/models/flownet.py", line 18, in initialize
    self.flowNet = flownet2_tools.module_to_dict(flownet2_models)['FlowNet2'](fp16=opt.fp16).cuda(self.gpu_ids[0])        
TypeError: __init__() got an unexpected keyword argument 'fp16'
moulimatsa commented 2 years ago

@karims I have the same issue. Were you able to resolve the issue.

zhangbowen1999 commented 1 year ago

@karims I have the same issue. Were you able to resolve the issue

zhangbowen1999 commented 1 year ago

@karims I have the same issue. Were you able to resolve the issue.

Excuse me. Have you solved it yet

zhangbowen1999 commented 1 year ago

I am usinf flownet from inside vid2vid. I get this following error. Any idea how to resolve this? Using with docker, Ubuntu 16, pytorch 1.0.0

Traceback (most recent call last):
  File "train.py", line 149, in <module>
    train()
  File "train.py", line 28, in train
    models = create_model(opt)
  File "/vid2vid/models/models.py", line 83, in create_model
    flowNet.initialize(opt)
  File "/vid2vid/models/flownet.py", line 18, in initialize
    self.flowNet = flownet2_tools.module_to_dict(flownet2_models)['FlowNet2'](fp16=opt.fp16).cuda(self.gpu_ids[0])        
TypeError: __init__() got an unexpected keyword argument 'fp16'

Excuse me. Have you solved it yet

UE-algo104 commented 1 year ago

runner.train(

engine=dl.CPUEngine(), # for simplicity reasons, let's run everything on cpu

engine=dl.GPUEngine("cuda:0"),       #< add use GPUEngine
model=model,
criterion=criterion,
MohammadRezaG commented 1 year ago

engine=dl.GPUEngine("cuda:0"),

Thanks