search

mli0603 / stereo-transformer

Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers. (ICCV 2021 Oral)
Apache License 2.0
659 stars 107 forks source link

sttr_light_kitti_finetuned_model.pth.tar #15

Closed emepetres closed 3 years ago

emepetres commented 3 years ago

Hi @mli0603 , first of all great work!

I'd like to run the inference on the kitti finetuned model. To do that I guess I have to finetune the _sttr_light_sceneflow_pretrainedmodel, but I'm having problems installing nvidia apex.

Could you please, If you have it, publish sttr_light_kitti_finetuned_model.pth.tar as well so I can test the inference on the kitti dataset directly?

BTW I'm creating a docker image and a inference script that I expect to share via PR when I manage to fix the nvidia apex issue.

Thanks!

mli0603 commented 3 years ago

Hi @emepetres , I haven't got time to fine-tune the light version on KITTI yet. I planned to do it, but to be honest I have too much on my plate now and I confess I am behind...

I would really appreciate the docker image if you can share ;) Thank you! There is already a inference script proposed on this PR #13 . Maybe you can check too to see if it runs on your end?

mli0603 commented 3 years ago

I have merged #13 already!