Closed adam99goat closed 1 year ago
Hi, what version is your pytorch, different versions have an impact on the accuracy. Besides, the OFNet also has an impact on the accuray. Please try to load the given weights of OFNet to reproduce the accuracy of DepthNet in the state-wise manner.
Excited and thankful for your reply. My pytorch version is 1.8.0 and torchvision is 0.9.0 . And I would like to know your version if convenient. I will try your valuable suggestion and retrain the net in stage-2 with help of provided weights of OFNet. Thank you a lot!
My PyTorch is 1.2.0 and torchvision is 0.4.0.
Excited and thankful for your reply. My pytorch version is 1.8.0 and torchvision is 0.9.0 . And I would like to know your version if convenient. I will try your valuable suggestion and retrain the net in stage-2 with help of provided weights of OFNet. Thank you a lot!
Unfortunately pytorch 1.2.0 does not seem to support 30-series GPU. pytorch 1.2.0 corresponds to CUDA up to 10.0, but 30-series GPU requires CUDA 11.
Excited and thankful for your reply. My pytorch version is 1.8.0 and torchvision is 0.9.0 . And I would like to know your version if convenient. I will try your valuable suggestion and retrain the net in stage-2 with help of provided weights of OFNet. Thank you a lot!
Unfortunately pytorch 1.2.0 does not seem to support 30-series GPU. pytorch 1.2.0 corresponds to CUDA up to 10.0, but 30-series GPU requires CUDA 11.
The same trouble as me ... The experiment in the paper was conducted on Titan RTX.
My PyTorch is 1.2.0 and torchvision is 0.4.0.
What a pity I think there still exist some problems. Maybe the data preparation should be based on ffmpeg. So could you share related code or command of pre-processing if convenient? Thanks again!
Hi,I can't find the preprocessing code now since a long time has passed, maybe you can search for the usage of ffmpeg. When you load the given weight of OFNet, what is the accuracy of training DepthNet in a state-wise way?
I feel so sorry for my late reply. Actually when I followed the 2-stages custom training with the given weight of OFNet, the result is shown below. Also PyTorch 1.2.0 and torchvision 0.4.0.
Strongly grateful for your excellent work and sorry to bother you for some puzzle. I tried to retrain the network to acquire the same results of SCARED as yours but failed. The validation of end-to-end and stage-wise is shown below. Though the result is worse than what are reported in your paper, the experimental result of Monodepth2 by myself is strangely better. The abs_rel value in your paper is 0.071. The data preparation is based on OpenCV which leavage the same video encoder and decoder as ffmpeg. So I can't figure out why but only ask you for favour. Look forward to your reply and thank you again!