get error when running test.py about scaledyolov4

[larsoncs]

@WongKinYiu ,"把SyncBatchNorm轉回BatchNorm可以解決", but the common.py use BatchNorm2d, not use SyncBatchNorm,how to convert SyncBatchNorm to BatchNorm? thx

[larsoncs]

i use cpu to run test.py ,get this error:

Traceback (most recent call last):
File "test.py", line 281, in
opt.verbose)
File "test.py", line 99, in test
inf_out, train_out = model(img, augment=augment) # inference and training outputs
File "/D/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/data/home//odetect/yolov4/models/yolo.py", line 109, in forward
return self.forward_once(x, profile) # single-scale inference, train
File "/data/home//odetect/yolov4/models/yolo.py", line 129, in forward_once
x = m(x) # run
File "/D/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/data/home//odetect/yolov4/models/common.py", line 66, in forward
return self.cv4(self.act(self.bn(torch.cat((y1, y2), dim=1))))
File "/D/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/D/lib/python3.7/site-packages/torch/nn/modules/batchnorm.py", line 477, in forward
raise ValueError('SyncBatchNorm expected input tensor to be on GPU')
ValueError: SyncBatchNorm expected input tensor to be on GPU

[WongKinYiu]

把SyncBatchNorm轉回BatchNorm可以解決

[lx120]

I am confused : How to convert SyncBatchNorm to BatchNorm. Could you please tie codes, THKs

[Actor12]

I am confused : How to convert SyncBatchNorm to BatchNorm. Could you please tie codes, THKs

I changed the pytorch version and solved it, torch==1.3 && torchvision==0.4.2