search

isl-org / MiDaS

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"
MIT License
4.27k stars 599 forks source link

Training code #175

Open GeforcePotenza opened 2 years ago

GeforcePotenza commented 2 years ago

Congratulations on this excellent work.

I would like to train your model on a custom dataset, would it be possible for you to share the training code with us?

Thank you.

masakinakada commented 1 year ago

I have the same request. I would like to try to finetune the trained model, so I would appreciate it if you guys can provide me the training code as well. Thanks for the great work!

karttikeya commented 1 year ago

Thanks for the great work. It has been over a year since the paper's publication, please do release the training code. Simply releasing pre-trained weights is essentially moot for future work trying to build on your paper.

eyildiz-ugoe commented 10 months ago

That's something I'd also like to have. Authors not sharing the training code is not really something that helps other scientists to build on the method.