Williamed
Williamed
Hi, I met the same problem as you, may I know have you resolved this problem?
> have you solved this error? Hi, I also met this problem on Linux, have you resolved this problem?
> I have tested it on Ubuntu v20.04 with python 3.8, pytorch 1.0. The demo run works fine now. > I think it's OS env issue with my RHEL6. cuda...
Hi， Thanks for your reply. I also resolved it by changing the version of gcc to 5.5.0. Kind regards, William On 4 May 2021, 02:37 +0100, uranuscc ***@***.***>, wrote: Hi...
> I opened this issue so that I hope people can share their best results and see if we can figure out how to reproduce VLocNet paper result together. >...
Hi, Thanks for your reply and your detailed explanation. I will try with your suggestions. BTW, if possible could you share your revised code of VLocNet. Have a nice weekend!...
Hi，thanks for your advice, keep in touch!
> I also experienced the error-accumulating issue and according to my simple mind, this couldn't be avoided in the VLocNet. I haven't found any module in the model which might...
> I opened this issue so that I hope people can share their best results and see if we can figure out how to reproduce VLocNet paper result together. >...
> In VLocNet paper section III-A, "we feed the previous pose (groundtruth pose during training and predicted pose during evaluation)" > > So first part of your question is correct....