Open Wangman1 opened 3 years ago
Sorry for my late reply. (A little busy at work) My result is lower than in the paper, about ~2-3 percent lower than it. Maybe next week I'll push my training code.
Thank you for your reply. Looking forward to your open source!
------------------ 原始邮件 ------------------ 发件人: "lhwcv/mlsd_pytorch" @.>; 发送时间: 2021年7月13日(星期二) 中午11:57 @.>; @.**@.>; 主题: Re: [lhwcv/mlsd_pytorch] How to train the models (#2)
Sorry for my late reply. (A little busy at work) My result is lower than in the paper, about ~2-3 percent lower than it. Maybe next week I'll push my training code.
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.
@Wangman1 Here is my result in mlsd_pytorch/README.md
Wow, these results look great, and I can't wait to see how you train the model, so great job, thank you!!!
Hi, when I train the model in your mode, raise the follow error:
And the Google link to JSON file cannot download the content. It does not have relevant download permission.
@Wangman1
@lhwcv
Thank you so much for your help. My code has been successfully run!!!
all loss will be nan after about 15 epoch, anyone knows why?
@lhwcv Thank you so much for your help. My code has been successfully run!!!
hi, could you please share the datasets with me ? It seems that the url for the datasets is unusable.
@lhwcv
Thanks for your code and I can run the demo successfully. But loss values are both "nan" on wireframe and custom datasets during training, do you have any idea?
Hi, how long does it take (on average obviously) to train this model? I am trying using Colab GPUs and the process seems extremely slow...
Hi, thank you for your code, and I want to know how to train the model in your code? thank you!