-
Notifications
You must be signed in to change notification settings - Fork 145
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
The link of STARKST_ep0500.pth.tar of stark_ref-baseline is invalid in STARK_LT #84
Comments
我有同样的问题,你解决了吗?或者您ep500的模型下好了吗?可以发一份吗 |
不好意思啊,我也没解决>﹏< |
我确实需要第一阶段模型,麻烦你发我邮箱[email protected], 好像第一阶段模型按照代码应该有如下,如果你都有的话,麻烦你都发我吧,谢谢! |
邮件不方便发送,直接登录 airportal.cn,由于是在线的,请尽快下载
提取码:338350
密码:012356
…---Original---
From: ***@***.***>
Date: Sun, Nov 27, 2022 22:00 PM
To: ***@***.***>;
Cc: "Birny ***@***.******@***.***>;
Subject: Re: [researchmm/Stark] The link of STARKST_ep0500.pth.tar ofstark_ref-baseline is invalid in STARK_LT (Issue #84)
***@***.***, 好像第一阶段模型按照代码应该有如下,如果你都有的话,麻烦你都发我吧,谢谢!
-- stark_st1
-- baseline
STARKST_ep0500.pth.tar
-- baseline_got10k_only
STARKST_ep0500.pth.tar
-- baseline_R101
STARKST_ep0500.pth.tar
-- baseline_R101_got10k_only
STARKST_ep0500.pth.tar
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
|
非常感谢,已经下载好了! |
1、这个是官方提供的模型,至于后缀为什么是50,我也不是很清楚;
2、如上所述,我也没有 epoch500 的模型;
3、没太懂这样做的用意,stark 的两阶段训练我不是很清楚,如果两个阶段模型有差别,只要不是用 strict 模式加载预训练模型应该是没问题的。
…---Original---
From: ***@***.***>
Date: Sun, Nov 27, 2022 23:39 PM
To: ***@***.***>;
Cc: "Birny ***@***.******@***.***>;
Subject: Re: [researchmm/Stark] The link of STARKST_ep0500.pth.tar ofstark_ref-baseline is invalid in STARK_LT (Issue #84)
邮件不方便发送,直接登录 airportal.cn,由于是在线的,请尽快下载 提取码:338350 密码:012356
…
---Original--- From: @.> Date: Sun, Nov 27, 2022 22:00 PM To: @.>; Cc: "Birny @.@.>; Subject: Re: [researchmm/Stark] The link of STARKST_ep0500.pth.tar ofstark_ref-baseline is invalid in STARK_LT (Issue #84) @., 好像第一阶段模型按照代码应该有如下,如果你都有的话,麻烦你都发我吧,谢谢! -- stark_st1 -- baseline STARKST_ep0500.pth.tar -- baseline_got10k_only STARKST_ep0500.pth.tar -- baseline_R101 STARKST_ep0500.pth.tar -- baseline_R101_got10k_only STARKST_ep0500.pth.tar — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.>
非常感谢,已经下载好了!
有几个疑惑可以请问你一下吗
1. 其中stark\checkpoints\train\stark_ref\baseline\STARKST_ep0050.pth.tar就是STARKST第一阶段的模型吧,其后缀是ep0050,是你自己复现50个epoch得到的吗?
2. 原文是作者第一阶段好像是训练了500个epoch的得到的模型,这个模型你是不是没有呀?
3. 请问可以直接使用作者提供的第二阶段最后的模型,放到第一阶段继续训练吗?
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
|
… ---Original---
From: ***@***.***>
Date: Fri, Dec 2, 2022 12:57 PM
To: ***@***.***>;
Cc: "Birny ***@***.******@***.***>;
Subject: Re: [researchmm/Stark] The link of STARKST_ep0500.pth.tar ofstark_ref-baseline is invalid in STARK_LT (Issue #84)
@kuaiJL @blxie 两位同学, 方便发一份第一阶段的模型给我吗?非常感谢!
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you were mentioned.Message ID: ***@***.***>
|
谢谢同学 |
@blxie did you find the model STARKST_ep0500.pth.tar ? Thanks in advance |
Hello, I am very interested in your work and thank you for your contribution.
When I test STARK_LT on VOT2021_LT, it was failed.
I have tried to downlowd from the link offered in READMEhttps://drive.google.com/file/d/1cfSAQYJMi7gn_ZCQZMhVp3pfqsSVTBEK/view?usp=sharing, but it gives me this message.

It is clear that the link you offered for downloading is invalid, could you please upload it again, thanks a lot!
The text was updated successfully, but these errors were encountered: