TGINSIGHT SIMILAR POSTS
Source channel @githubtrending · Post #15365 · Dec 24
#jupyter_notebook DINOv3 offers powerful self-supervised vision models from Meta AI, like ViT up to 7B parameters and ConvNeXt, pretrained on 1.7B web or satellite images. Load them easily via PyTorch Hub, Hugging Face Transformers (v4.56+), or timm (v1.0.20+), with code examples for features, depth, detection, and segmentation. You benefit by using these top-performing, dense features without fine-tuning or labels—saving time and compute for tasks like classification, object detection, and zero-shot analysis on your images. https://github.com/facebookresearch/dinov3
Hashtags
Search: #yacd
@storage_qi · Post #764 · 02/07/2024, 05:45 PM
#Clash#ClashMeta#WebUI#metacubexd#Yacd GH 页面自定义域：http://d.metacubex.one GH 页面：https://metacubex.github.io/metacubexd Cloudflare 页面：https://metacubexd.pages.dev 省流（个人认为体验优于Yacd）： - 在Connections的功能相当丰富，功能体验最优（无法全部显示时，Shift+滚轮 可以横向滚动） - Proxies界面节点延迟可视化显示 - 还有一些其他Web UI所没有的功能 来源（ClashMeta官方支持）