inconsistent tensor sizes in"dout8_out7 = torch.cat([dout8, out7], 1)"

[my1347]

[my1347]

Using torch 0.3.1

[my1347]

It seems that input image size must be less than 512??

[hezhangsprinter]

I guess 1024 should also work. However, since the network is trained on 512X512, the receptive field will be a issue. To get good results, please crop or resize to 512X512 first.