NVIDIA / flownet2-pytorch

Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Other
3.08k stars 738 forks source link

dimension unmatch problem in model #289

Open lelucermaireme opened 3 days ago

lelucermaireme commented 3 days ago

There is an error at concat4 = torch.cat((out_conv4,out_deconv4,flow5_up),1) RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 15 but got size 16 for tensor number 1 in the list.

The conv and deconv cause dimension unmatch. The out_deconv4 and flow5_up should be checked and cropped to the same size as out_conv4.