Alexander

@Ironbrotherstyle you can find the links to the trained model in the readme

@Ironbrotherstyle , did you use the model mentioned in https://github.com/ChiWeiHsiao/DeepVO-pytorch#download-trained-model section?

@Ironbrotherstyle you can find description of the changes at https://github.com/ChiWeiHsiao/DeepVO-pytorch/issues/4 Regarding GT file, I also included rotation matrix 'as is' from KITTI data. It is used in ImageSequenceDataset class to...

@Ironbrotherstyle I have just tried to reproduce the experiment using the code from this repo. It works as expected. I only updated the following parameters in params.py. self.img_means = (0.19007764876619865,...

@Ironbrotherstyle setting img_means and img_stds should help. I overlooked to update them in the repo. I created a pull request https://github.com/ChiWeiHsiao/DeepVO-pytorch/pull/9 to fix that.

@Ironbrotherstyle the key idea of the transformation is to let the model 'thinks' that every sequence starts at 0 point and has 0 Euler angles initially. So we need to...

@Ironbrotherstyle , As you know, in KITTI dataset every track starts with camera looking along Z axis. X axis is oriented to the right. Imagine that the car made a...

@Ironbrotherstyle I used the parameters as they were specified in the repository. It is difficult to say what might be wrong in your case without knowing all the details.

@Ironbrotherstyle, I dont' remember exactly. I might have used a subset of the dataset to calculate the values to save time. That is why I think you get different results.

@Ironbrotherstyle The performance is better because the model was trained using these particular img_means and img_std. If you retrain the model using your values, you should get good results too....