Hello!
First of all, I would like to express my sincere gratitude for your excellent work and the open-source source code. Your project MVSCPS has provided great inspiration and help for my relevant research/work, and I really appreciate your generosity in sharing the implementation details.
During the process of using your project, I noticed that it is necessary to first run the command ./launch_diligentmv.sh to complete the full training process before conducting subsequent testing and obtaining valid results.
However, due to limited computing resources, it is difficult for me to re-run the entire training process locally. Therefore, I would like to kindly ask you:
- Would it be convenient for you to provide the pre-trained results (such as model checkpoints, training logs, etc.) of this project?
- Is there any available way or guidance to directly perform testing on my own custom dataset without re-training from scratch?
It would be a great help to me if you could spare some time to reply to this question.
Thank you very much for your hard work again, and I look forward to your reply!
Best regards
Hello!
First of all, I would like to express my sincere gratitude for your excellent work and the open-source source code. Your project MVSCPS has provided great inspiration and help for my relevant research/work, and I really appreciate your generosity in sharing the implementation details.
During the process of using your project, I noticed that it is necessary to first run the command
./launch_diligentmv.shto complete the full training process before conducting subsequent testing and obtaining valid results.However, due to limited computing resources, it is difficult for me to re-run the entire training process locally. Therefore, I would like to kindly ask you:
It would be a great help to me if you could spare some time to reply to this question.
Thank you very much for your hard work again, and I look forward to your reply!
Best regards