Bevformer temporal and no temporal configs are the same about robobev HOT 3 OPEN

I've corrected it. You only need to change the following argument to switch between temporal and non-temporal mode.

video_test_mode=False

Thanks for pointing out this issue.

from robobev.

@Daniel-xsy Isn't that only for testing? The training is still done with temporal information with Temporal Attention?

from robobev.

Yes, that's correct. In the official BEVFormer paper, the authors trained two versions: BEVFormer and BEVFormer-S. The BEVFormer-S is trained without temporal information, i.e., video_test_mode=False for both training and testing. You can find more details here.

However, since we couldn't find the training configuration and checkpoint of BEVFormer-S, we opted to use the BEVFormer checkpoint and turn off video_test_mode during testing. This might cause a discrepancy between training and testing, as evident from the lower performance of BEVFormer-non-temporal compared to the official results. We might try to reproduce this version and update the checkpoint in the future if possible.

from robobev.