keyu-tian / SparK

[ICLR'23 Spotlight🔥] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"
https://arxiv.org/abs/2301.03580
MIT License
1.42k stars 82 forks source link

请问下ppt中的动图是怎么画的 #13

Closed whuhit closed 1 year ago

whuhit commented 1 year ago

十分感谢TechBeat上的视频分享,文章思路非常清晰,PPT也很漂亮,想请教下,ppt中的网络结构动图是通过什么画的呀

keyu-tian commented 1 year ago

(cn version) 谢谢!基本上先是画的静态页面,然后用“平滑”这个切换效果,让PPT自动在不同静态页面之间补帧,得到的动画效果。我们把 slides 文件上传到 https://github.com/keyu-tian/SparK/releases/tag/file_sharing 了,可供下载和查看。

(en version) Thanks! Basically, we're using a lot of "Morph" transitions between slides to animate slides/video. We first make a static slide, duplicate it, and then move some object on the second slide to different places, or add some new objects. Using "Morph" transition between the two slides can automatically animate and move those changed or added object, in a pretty smooth way. Check https://github.com/keyu-tian/SparK/releases/tag/file_sharing for download and viewing.

whuhit commented 1 year ago

好的,感谢。