search

NeurAI-Lab / biHomE

This is the official repo for the CVPR 2021 IMW paper: "Perceptual Loss for Robust Unsupervised Homography Estimation"
MIT License
37 stars 5 forks source link

Can you provide the trained model? #1

Closed lyres closed 3 years ago

lyres commented 3 years ago

Hi, Thanks for providing the source code. I want to test your model with my own data. I would be very grateful if you can provide a well-trained model.

dkoguciuk commented 3 years ago

Hi @lyres ,

unfortunatelly I am not able to share trained models, however it is really easy to reproduce it. I suggest you use Zeng backbone + biHomE loss trained on PDS-COCO dataset, since this is the most robust configuration:

python3 train.py --config_file config/pds-coco/zeng-bihome-lr-1e-3.yaml

To use the trained model on your own data you would probably have to write your own dataset.py file, but it should also be really easy if you just copy existing dataset.py file (i.e. src/data/flir_adas/dataset.py) and modify it for your case. Please let me know if you have any questions.

Best, Daniel

lyres commented 3 years ago

Thanks for your advice! I will try it soon.