Why is the optimal result different each time during training？

[Cao-PeiPei]

Excuse me, I've encountered an issue. I'm currently training on AutoDL, and I've noticed that the performance of my training differs by 8 points compared to my junior's training of Deformable DETR with the same configuration. I'm considering whether the difference is due to different random seeds. However, even after setting the same random seed, there is still a 5-point difference in performance. I would like to ask how to handle this situation, as I'm concerned that the subsequent experiments might show significant variations in the AP50 values.

[rentainhe]

How many GPUs do u use for this training

[Cao-PeiPei]

Sorry, just saw the reply. We are all using a single GPU, and the rest of the configurations are the same.

[rentainhe]

Hello! Do u use 16 batch-size for training in single GPU?

[Cao-PeiPei]

NO, we have used batch size=4.