ujgygy656565

Results 7 comments of ujgygy656565

I set resume to false. According to the parameters given in params, I trained to 100 epoch and 250 epoch, and tested them separately. But the effect of visualize is...

Why don't I change the parameters and train from scratch to 400 epoch and the result is like this. Thank you. ![image](https://user-images.githubusercontent.com/46241022/57610461-7126d480-75a3-11e9-9312-764b553c2dae.png) ![image](https://user-images.githubusercontent.com/46241022/57610500-856ad180-75a3-11e9-8d65-00d859048d26.png) ![image](https://user-images.githubusercontent.com/46241022/57610517-8bf94900-75a3-11e9-8314-8037d403af1b.png)

> @ujgygy656565 Did you use a pretrained FlowNet? yes,I changed pretained flownet in params to. / pretrained / flownets_bn_EPE2.459. pth. tar. What may be my problem? Is the label relative...

> try flownets_EPE1.951.pth.tar. Also it seems that your NN is undertrained. Thank you. I've got the normal trajectory now. How to calculate the evaluation index of KITTI SLAM?

@Ironbrotherstyle My results are the same as before. Do you know where the problem is now?

Did you training from the beginning?

> Did you training from the beginning? > > I think so Do you know how to use Kitti dataset evaluation indicators?