search

hkchengrex / Cutie

[CVPR 2024 Highlight] Putting the Object Back Into Video Object Segmentation
https://hkchengrex.com/Cutie/
MIT License
691 stars 69 forks source link

Problem about trainer #19

Closed yahooo-m closed 11 months ago

yahooo-m commented 11 months ago

In XMem, I find that the model conducts "self.xmem.eval()". Here is "self.cutie.train()". Could you tell me the difference between them?

hkchengrex commented 11 months ago

Refactored for better semantics. We moved the batch norm freezing logic to the image/mask encoders. There are no practical differences.