关于FFHQ训练集

[ivcagcowkh]

作者您好！我想问一下，FFHQ数据集（512×512）我已经下载好了，但是它对应的退化图像怎么获取呢？我想尝试训练您的网络，但不知道LQ图像应该怎么获得？可以麻烦您提供一下解决办法吗？感谢！

[guyuchao]

Hi, The LR image is not generated before training. It is generated on the fly when training. Best, Yuchao ivcagcowkh ***@***.***> 于2024年1月8日周一 10:19写道：

…

作者您好！我想问一下，FFHQ数据集（512×512）我已经下载好了，但是它对应的退化图像怎么获取呢？我想尝试训练您的网络，但不知道LQ图像应该怎么获得？可以麻烦您提供一下解决办法吗？感谢！ — Reply to this email directly, view it on GitHub <#34>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AHR2OMXQOSBCMCWCNBMKHV3YNNJTRAVCNFSM6AAAAABBQY36NWVHI2DSMVQWIX3LMV43ASLTON2WKOZSGA3DSNBXGQ3TCNI> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>

[ivcagcowkh]

十分感谢十分感谢！

…

---原始邮件--- 发件人: "Yuchao ***@***.***&gt; 发送时间: 2024年1月8日(周一) 上午10:29 收件人: ***@***.***&gt;; 抄送: ***@***.******@***.***&gt;; 主题: Re: [TencentARC/VQFR] 关于FFHQ训练集 (Issue #34) Hi, The LR image is not generated before training. It is generated on the fly when training. Best, Yuchao ivcagcowkh ***@***.***&gt; 于2024年1月8日周一 10:19写道： &gt; &gt; 作者您好！我想问一下，FFHQ数据集（512×512）我已经下载好了，但是它对应的退化图像怎么获取呢？我想尝试训练您的网络，但不知道LQ图像应该怎么获得？可以麻烦您提供一下解决办法吗？感谢！ &gt; &gt; — &gt; Reply to this email directly, view it on GitHub &gt; <#34&gt;, or unsubscribe &gt; <https://github.com/notifications/unsubscribe-auth/AHR2OMXQOSBCMCWCNBMKHV3YNNJTRAVCNFSM6AAAAABBQY36NWVHI2DSMVQWIX3LMV43ASLTON2WKOZSGA3DSNBXGQ3TCNI&gt; &gt; . &gt; You are receiving this because you are subscribed to this thread.Message &gt; ID: ***@***.***&gt; &gt; — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: ***@***.***&gt;

[ivcagcowkh]

Hi, The LR image is not generated before training. It is generated on the fly when training. Best, Yuchao ivcagcowkh @.> 于2024年1月8日周一 10:19写道：
…
作者您好！我想问一下，FFHQ数据集（512×512）我已经下载好了，但是它对应的退化图像怎么获取呢？我想尝试训练您的网络，但不知道LQ图像应该怎么获得？可以麻烦您提供一下解决办法吗？感谢！ — Reply to this email directly, view it on GitHub <#34>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AHR2OMXQOSBCMCWCNBMKHV3YNNJTRAVCNFSM6AAAAABBQY36NWVHI2DSMVQWIX3LMV43ASLTON2WKOZSGA3DSNBXGQ3TCNI . You are receiving this because you are subscribed to this thread.Message ID: @.>

By the way,did you use the validation set when training VQGAN, and how many images you used as the validation set ？(from the FFHQ dataset)Thanks!