TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Cannot reproduce the exact same training results – diffusion models

1 点作者 roxyrox超过 1 年前
Hi ! In order to collaborate with my team we want to be able to get the same training results based on a finetuned version of https:&#x2F;&#x2F;huggingface.co&#x2F;runwayml&#x2F;stable-diffusion-v1-5.<p>We have real issues defining the exact same environment, even if we have the same code&#x2F; use the same args with weight &amp; biaises. We try to do our best with some versioning of the image datasets but it seems that the issue can also come from CUDA versions and the different libs (I also read it can come from the GPU being used).<p>If you have some tools that could help us replicable the same training environment that would be great. Not sure exactly what&#x27;s wrong in our config.<p>Thanks!

暂无评论

暂无评论