Arash
@feroze it is not right. @foolishair opengl_helper is part of the [g2o](https://github.com/RainerKuemmerle/g2o/blob/master/g2o/stuff/CMakeLists.txt#L29) . IMHO [this part ](https://github.com/RainerKuemmerle/g2o/blob/master/g2o/apps/CMakeLists.txt#L8) causes the problem, since it is configurable, even tough you set opengl to...
I am also facing the same issue in a siamese network!
I also get the same error on windows 10 and NVIDIA TITAN. Pytorch version: 1.4.0 But the same code runs on linux with the same python and pytorch version. Code...
> Hi @JulianFeinauer, > we are working on a Ditto integration but there is still a "way to go"... > As @stefbehl mentioned we will replace some internal beans in...
@crh8598 i also had the same issue, the solution suggested [here](https://github.com/introlab/rtabmap_ros/issues/291#issuecomment-476322984) solved the problem!
@rginjapan your sequence is not correct for an RNN-based architecture. The combination should be: ``` combinations: [ [ 0, 1 ],[1, 2],[2,3] ] ``` Also, I would first try with...
@rginjapan yes and no ;) for RNN-based network, it is better to have consecutive frame combination, e.g. [[0,1], [1,2], [2,3]]. Regarding gradient-clipping: see [here](https://pytorch.org/docs/stable/generated/torch.nn.utils.clip_grad_norm_.html), [](url) and [here](https://neptune.ai/blog/understanding-gradient-clipping-and-how-it-can-fix-exploding-gradients-problem).
@rginjapan plz look at the loss function [here](https://github.com/ArashJavan/DeepLIO/blob/master/deeplio/models/trainer.py#L260). As you can see in the loss function we already take care for global motion since the loss is calculated for local...
@rginjapan Can you share your config-file and your meta-data settings (lr, wd and so on).
@KleinYuan unfortunately the lack of synchronization is not the only thing, also the odometry benchmark (or synced) does not contain IMU values. But the timestamps are defined from the same...