the model report on the paper is trained by 300 epoches or 500 epoches? about detr HOT 8 CLOSED

The batch/GPU for 150 epoch provided in the github is 4 img/GPU or 2img/GPU?

from detr.

@gaopengcuhk sorry for the confusion in the gist! the 150 epoch model we provide to simplify reproducibility on a single 8-gpu machine, it was trained with batch size 4, thus total 32, to fit into 16GB cards.
Both the ablation 300-epoch (40.6) and the final 500-epoch (42.0) models were trained on 4 nodes with 2 im/gpu, thus total 64.

I will update non-DC5 cmd lines to submitit, and move the gist to the repo.

from detr.

Hi,

The ablations in the paper were conducted on 300 epochs, while the models reported in table 1 (main results) were trained for 500 epochs.

I believe I have answered your question, and as such I'm closing the issue but let us know if you have further questions.

from detr.

The final performance is trained for 500 epoches by 16GPU with 4img/GPU for DETR/DETR-DC5/DETR-R101/DETR-DC5-R101?

from detr.

If I understand correctly, the performance for 150 epoch is 39.5, for 500 epoch is 42.0. What's the performance of 300 epochs? I guess all models should be trained with the same batch size.

from detr.

If I understand correctly, the performance for 300 epochs should be 40.6?

from detr.

Yes, the performance for 300 epochs is 40.6, from table 2 in the paper.

from detr.

@szagoruyko same question as @gaopengcuhk, also, could you pls provide the pretrained model of 150epoch run?

from detr.