JackyLiu
JackyLiu
@copark86 The IMU value is not directly connected to the se3 output. The LSTM still have chances output the right value according to the input. However, having a value closed...
I found that I misunderstood how to use SE3 composition layer.  The orange line is how it should look like.
@copark86 I'm porting the SE3 composition layer from gvnn (lua+torch) to PyTorch. I'll start training again after the porting is complete. Here is the draft of porting gvnn SE3 =>...
The complete SE3 composition layer implementation is out! ([link](https://github.com/HTLife/se3comp_pytorch)) I'll start to merge this implementation into VINet.
@JesperChristensen89 I have no time to focus on this project recently. But if you are interested in continue this work, I'll be willing to engage in the discussion.
@Adamquhao Cool, are you willing to share it with me? (By sending the pull request)
@xuqiwe I didn't finish this work in the end. But @Adamquhao seems to successfully build train the network. The following is his instruction: "Firstly, i recommend u to read "Selective...
Thanks for the suggestion. I'll try it out.
@ildoonet I just finish the draft of SE3 composition layer ported from [gvnn](https://github.com/ankurhanda/gvnn). ([code](https://github.com/HTLife/gvnn_pytorch/blob/master/TMSO3.py)) I'll do the unit test in my spare time.
The issue seems to be still exist.