search

lhwcv / mlsd_pytorch

Pytorch implementation of "M-LSD: Towards Light-weight and Real-time Line Segment Detection"
Apache License 2.0
189 stars 37 forks source link

How to train the models #2

Open Wangman1 opened 3 years ago

Wangman1 commented 3 years ago

Hi, thank you for your code, and I want to know how to train the model in your code? thank you!

lhwcv commented 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.

Wangman1 commented 3 years ago

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.

lhwcv commented 3 years ago

@Wangman1 Here is my result in mlsd_pytorch/README.md

lhwcv commented 3 years ago
model | img_size | sAP10 -- | -- | -- mlsd_tiny (this repo) | 512 | 56.4 mlsd_tiny (in the paper) | 512 | 58.0 mlsd_large (this repo) | 512 | 59.6 mlsd_large (in the paper) | 512 | 62.1
Wangman1 commented 3 years ago

Wow, these results look great, and I can't wait to see how you train the model, so great job, thank you!!!

Wangman1 commented 3 years ago

Hi, when I train the model in your mode, raise the follow error: image

Wangman1 commented 3 years ago

And the Google link to JSON file cannot download the content. It does not have relevant download permission. image

lhwcv commented 3 years ago

@Wangman1

  1. pip install yacs
  2. use https://github.com/lhwcv/mlsd_pytorch/blob/main/data/wireframe_anno.zip
  3. google cloud disk I'll check the issue later
Wangman1 commented 3 years ago

@lhwcv Thank you so much for your help. My code has been successfully run!!! image

ForestWang commented 2 years ago

all loss will be nan after about 15 epoch, anyone knows why?

YangTao516 commented 2 years ago

@lhwcv Thank you so much for your help. My code has been successfully run!!! image

hi, could you please share the datasets with me ? It seems that the url for the datasets is unusable.

harolddu commented 2 years ago

@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?

michelebechini commented 2 years ago

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...