Reformat predict poses to save all sequences

aofrancani / TSformer-VO

Implementation of the paper "Transformer-based model for monocular visual odometry: a video understanding approach".

https://arxiv.org/abs/2305.06121

MIT License

71 stars 11 forks source link

Reformat predict poses to save all sequences #13

Closed MohitBurkule closed 7 months ago

MohitBurkule commented 8 months ago

Currently, predict_poses.py saves only the last sequence, but plot_results.py assumes that outputs for all sequences are present.

aofrancani commented 7 months ago

Hey, thanks for pointing that out.

To be honest, this is the original idea since I want to save the predicted_poses for each sequence in separate files, not just the last one. I don't know why I missed the indentation, it's probably due to copying from one text editor to another. That's how I implemented it and how it runs on my machine. Since there is no major contribution to the code or significant improvement in the pipeline, I will decline the pull request (sorry).