Yazan Murhij

Any updates on this?

已收到！祝每天开开心心！:D

Any updates?

Any updates on this?

Any updates?

> @519174419 Yeah, I solved the problem by setting a smaller thresh but the ego-motion prediction looks so weird with my self-trained model. Is anything wrong with your disparity map?...

I figured it out and made some changes in class ``` UpdateModule(nn.Module) ``` ``` self.weight = nn.Sequential( nn.Conv2d(128, 128, 3, padding=1), nn.ReLU(inplace=True), nn.Conv2d(128, 3, 3, padding=1), GradientClip(), nn.Sigmoid()) ``` also...

any updates on this ?

you can use ``` pip install git+https://github.com/princeton-vl/lietorch.git ```

Hi @jinyummiao @xhangHU I have the same problem here, have you managed to fix this ??