search

albrateanu / LYT-Net

LYT-Net: Lightweight YUV Transformer-based Network for Low-Light Image Enhancement
https://arxiv.org/abs/2401.15204
MIT License
69 stars 11 forks source link

Regarding Batch Size #24

Open pranav-gupta-7 opened 4 days ago

pranav-gupta-7 commented 4 days ago

Hey, I found your work very interesting. I have a question regarding the batch size. Why did you choose a batch size of 1? How did the results compare when the batch size was greater than 1?

albrateanu commented 3 days ago

Hi @pranav-gupta-7, thanks for the question.

Our thought process was that a smaller batch size will allow us to capture more performance peaks of the model. In contrast, a higher batch size would probably result in a more stable training process - but you might miss some performance peaks.