Closed Wshenv closed 2 months ago
Hi, please make sure you use the same versions of dependencies as we used. There are also some tickets discussing the reproduction of the results. Please search in this repo.
Thanks for your suggestion, I reconfigured the dependencies again and made the data set in.jpg format according to the way of monodepth2, but the result of retraining is still not satisfactory. This is my dependency, and only the version of tensorboardX dependency is inconsistent, but I think it will not affect the result of training
In addition, I found a torch>=1.8 in requirements.txt of linear_warmup_cosine_annealing_warm_restarts_weight_decay=1.0. Is that the reason?
It should be fine because we could reproduce our results using pytorch 1.7.1 and 1.12.1 https://github.com/noahzn/Lite-Mono/issues/58
Thank you very much. I tried to adjust the dropout to 0.3 and conducted the experiment again, and got a result very close to the paper in the 24th round. I have another question for you. Is the data set in jpg format converted strictly according to the conversion command in monodepth2?
Hi, good to know that you have better results now! Yes, we directly converted the images to .jpg according to the command in the monodepth2's repo.
Hello, thanks for great code.I got the pretrained model and I ran the train.py to reproduce the lite-mono, I trained with the same dependencies on the A6000,but I got different results.![564](https://github.com/noahzn/Lite-Mono/assets/119914305/10fdb2af-e701-487e-b5cb-a917f883b5f6)