Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

The VO results are bad when using newer pytorch #11

Open
eric-yyjau opened this issue Aug 7, 2020 · 5 comments
Open

The VO results are bad when using newer pytorch #11

eric-yyjau opened this issue Aug 7, 2020 · 5 comments

Comments

@eric-yyjau
Copy link

The KITTI VO results are bad when using the following pytorch version.

torch==1.5.1
torchvision==0.6.1

Follow the same scripts on KITTI sequence 10, I got the following results.

Sequence: 10
Translational error (%):  12.00700933424375
Rotational error (deg/100m):  5.758592589262757

image

The results are good under pytorch 1.2.
Why is it the case? Thanks.

@thuzhaowang
Copy link
Collaborator

We have yet not tested with pytorch 1.5. If you have any further findings about this version issue, please report here. Thanks.

@chaoxingxi
Copy link

chaoxingxi commented Jul 5, 2021

The KITTI VO results are bad when using the following pytorch version.

torch==1.5.1
torchvision==0.6.1

Follow the same scripts on KITTI sequence 10, I got the following results.

Sequence: 10
Translational error (%):  12.00700933424375
Rotational error (deg/100m):  5.758592589262757

image

The results are good under pytorch 1.2.
Why is it the case? Thanks.

The figure is the result of use
python infer_vo.py --config_file ./config/odo.yaml --gpu [gpu_id] --traj_save_dir_txt [where/to/save/the/prediction/file] --sequences_root_dir [the/root/dir/of/your/image/sequences] --sequence [the sequence id] ----pretrained_model [path/to/your/model] python ./core/evaluation/eval_odom.py --gt_txt [path/to/your/groundtruth/poses/txt] --result_txt [path/to/your/prediction/txt] --seq [sequence id to evaluate]
why my result use the provide pretrained models look more bad?
@B1ueber2y @thuzhaowang

@B1ueber2y
Copy link
Owner

Have you switched to the required pytorch version? It is reported that the grid sampling layer might be inconsistent with newer pytorch (e.g. pytorch==1.5)

@chaoxingxi
Copy link

Thank you for your reply. I have use the required pytorch version

2021-07-07 10-41-33屏幕截图

Is something wrong when I run the infer?

infer_vo.py --config_file ./config/odo.yaml --gpu 0 --traj_save_dir_txt ./results/prediction/pose_10.txt --sequences_root_dir /media/xxxxxx/disk4t/dataset/KITTI/odometry/dataset/sequences --sequence 10 --pretrained_model models/pretrained/kitti_odo.pth

then i plot the result like this
sequence_10

Another question
How convert the results from CC(or SfMlearner) to Translational error (%), Rotational error (deg/100m)
When i do this, i find the later part of the sequence is bad than preceding part, like this (CC in seq10)
sequence_10
A little different from the visualization in your paper

Thank you

@henry123-boy
Copy link

I also met this problem, we follow the same evaluation setting provided and test the pre-trained model in KITTI sequence 09, but the result is very bad?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

5 participants