TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Show HN: VRE Dataset generation for MultiTask vision models training from videos

2 pointsby meehai7 months ago
Been working on this tool for my PhD which involves training multi task vision models using various pre-trained models as inputs or pseudolabels in order to improve generalization. I work mostly on UAV datasets, but it should work okay on indoor scenes or self driving (at least Marigold and Mask2Former).<p>For example, this dataset was generated using this tool: <a href="https:&#x2F;&#x2F;huggingface.co&#x2F;datasets&#x2F;Meehai&#x2F;dronescapes" rel="nofollow">https:&#x2F;&#x2F;huggingface.co&#x2F;datasets&#x2F;Meehai&#x2F;dronescapes</a><p>I&#x27;m quite aggressively trying to &quot;just get the nn.Module&quot; from the public repos that other researchers put up in their overly convoluted frameworks. A simple `forward(rgb_input: torch.Tensor) -&gt; torch.Tensor` is nice, having 100 imports from a generic framework that has versions incompatibilities with everything else is not.<p>PS: most mains are standalone runnable too, i.e. - <a href="https:&#x2F;&#x2F;gitlab.com&#x2F;meehai&#x2F;video-representations-extractor&#x2F;-&#x2F;blob&#x2F;master&#x2F;vre&#x2F;representations&#x2F;depth&#x2F;marigold&#x2F;marigold.py" rel="nofollow">https:&#x2F;&#x2F;gitlab.com&#x2F;meehai&#x2F;video-representations-extractor&#x2F;-&#x2F;...</a> or - <a href="https:&#x2F;&#x2F;gitlab.com&#x2F;meehai&#x2F;video-representations-extractor&#x2F;-&#x2F;blob&#x2F;master&#x2F;vre&#x2F;representations&#x2F;semantic_segmentation&#x2F;mask2former&#x2F;mask2former.py?ref_type=heads#L110" rel="nofollow">https:&#x2F;&#x2F;gitlab.com&#x2F;meehai&#x2F;video-representations-extractor&#x2F;-&#x2F;...</a>

no comments

no comments