Roberto Pellerito

## Environment: Thats my environment _libgcc_mutex 0.1 conda_forge conda-forge _openmp_mutex 4.5 2_gnu conda-forge absl-py 1.1.0 pypi_0 pypi argon2-cffi 20.1.0 pypi_0 pypi astroid 2.4.2 pypi_0 pypi async-generator 1.10 pypi_0 pypi attrs...

same issue, any update ?

Only a side comment on this, @lahavlipson you are saying that the last pose is given by `lietorch.SE3(slam.poses_[n-1]).inv().data.cpu().numpy()` but n is the keyframe number, so you are not effectively giving...

@lahavlipson but then what is the whole purpose of this [code part](https://github.com/princeton-vl/DPVO/blob/4f2f0cc7efbfe2547e788844412a3a2a72a923bd/dpvo/dpvo.py#L231) inside dpvo evaluation script. I understood that, if the estimated flow between i and j is less then...

Possibly a follow-up question. I was trying to understand the same softagg. I see that ii and jj are arrays with the same number inside e.g. ii=[0,0,0,...] and jj=[1,1,1,...] therefore...

It's clear thanks.

Haven’t tried yet but I'm also interested in porting DPVO in ONNX / TensorRT framework

I also have the same question, seems that inner thoughts or agent controls are somewhat absent from the official code. Also the conversation between agents is not there. did you...

I have experienced the very same error when starting the simulation and doing `call -- load history` directly. I think the issue resides in the fact that "personas" object has...