Open priancho opened 2 years ago
Hi,
You are correct. It should be 58 epochs. We will correct this in future revisions. By 48 epochs we are following the COCO naming convention where 1x = 12 epochs. Apparently this is not true for LVIS.
Best, Xingyi
Hi, First, thank you for the great work :-)
While I was reading the paper, I found that the "Generalization to Deformable-DETR" section below mentions that the model is trained for ~48 epochs on LVIS data.
But the config file,
configs/DeformDETR_L_R50_4x.yaml
, shows that it trains 180k iterations with 32 batch size. https://github.com/facebookresearch/Detic/blob/bdf9eb82a9fb8f052b1511fbfc61bcabfc3cde51/configs/Base-DeformDETR_L_R50_4x.yaml#L30Considering that the LVIS training data consists of about 100k images, the training epoch is
180k batch iterations * 32images/batch / 100k images/epoch
should be ~58 epochs.Am I missing something, or was 48 epochs typo?
Best regards, Han-Cheol