facebookresearch / ijepa

Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."
Other
2.83k stars 358 forks source link

How to create the visualizations on your README and Figure 6 of your paper? #65

Open alanwang8 opened 5 months ago

alanwang8 commented 5 months ago

Hello,

I'm currently trying to generate visualizations similar to those you generated in the "Visualizations" section of your README and Figure 6 in your paper.

Could you provide code and describe the process for generating the visualizations in Figure 6 of your paper and your README section?

Also, if I'm using my own dataset instead of the one that you used, what changes would I need to make from your code to generate my own visualizations?

Thanks!