forward() takes exactly 2 arguments (3 given) about flownet2-pytorch

[foolwood]

Fix in this line.

flownet2-pytorch/models.py

Line 142 in fdf3166

flownets2_flow2 = self.flownets_2(concat2, '2')[0]

flownets2_flow2 = self.flownets_2(concat2, '2')[0]
->
flownets2_flow2 = self.flownets_2(concat2)[0]

BTW, the author can also fix this line.

flownet2-pytorch/models.py

Line 249 in fdf3166

def forward(self, x, ntk_num='1'):

def forward(self, x, ntk_num='1'): -> def forward(self, inputs, ntk_num='1'):

Some similar spelling errors should be fixed.

[fitsumreda]

depricated arguments for lines such as these flownets2_flow2 = self.flownets_2(concat2, '2')[0]
have been removed now.

[PkuRainBow]

@foolwood Thanks, however I find that the EPE error does not converge when I train the model on FlyingChairs. The EPE is increasing after some epochs.

[foolwood]

@PkuRainBow
I meet the same problem.
So I first train the flownet2c with a learning rate of 1e-6 for 2000 epoches in MPI-Sintel.
But when I back the lr to 1e-4. The EPE error explodes again.