henghuiding / ReLA

[CVPR2023 Highlight] GRES: Generalized Referring Expression Segmentation
https://henghuiding.github.io/GRES/
MIT License
656 stars 19 forks source link

Inconsistency in LR Schedule Between Paper and Code #24

Open charon517-517 opened 2 months ago

charon517-517 commented 2 months ago

Thank you for your excellent work! I’ve been working on reproducing the results of ReLA on the GRefCOCO validation set (SwinB version) and came across a discrepancy regarding the learning rate decay schedule.

According to the Supplementary Material for GRES https://openaccess.thecvf.com/content/CVPR2023/supplemental/Liu_GRES_Generalized_Referring_CVPR_2023_supplemental.pdf, the learning rate is initially set to 1e-5 and decreases by a factor of 10 at the 10,000th and 140,000th iterations. However, the default config file https://github.com/henghuiding/ReLA/blob/1cf1e9fe46cd69fea44e1cbe7917e599e895e438/configs/referring_R50.yaml#L56 specifies the first decay step at 110,000 iterations, which differs significantly from the paper.

Could you please clarify which learning rate schedule should be followed for the best results?

Thank you for your time and assistance!