xiaoyudanaa
xiaoyudanaa
> hi, i don't really know how to get table5 in your essay without pre-train model provided by you. Did you train on sceneflow and finetune on kitti 2012 and...
加个微信，我也在弄这个，讨论一下：Weafree
> Hi @xiaoyudanaa , thanks for your interest. Definitely, the test-time optimization can be improved. At the moment, the method relies on a stochastic gradient descent with the Adam optimizer....
Based on your response, I checked my configuration path and its doesn't seem to be wrong. The details are shown in the attached image：  
> Hi, > > I'm working on similar research and I was wondering when would you release the code used for training the model? I saw on the read me...
> Hi! :) > > Would you be able to share the evaluation code and settings? In addition, the paper mentions using 110 videos as the training set and 27...
I need it too, can I talk to you first, my email is [email protected]
> Is it possible to at least release the data splits (which files are in train / val)? I'd like to do more analysis of the model. [@ThunderVVV](https://github.com/ThunderVVV) I need...