henghuiding / Vision-Language-Transformer

[ICCV2021 & TPAMI2023] Vision-Language Transformer and Query Generation for Referring Segmentation
MIT License
347 stars 23 forks source link

Reproducing on refcocog #16

Open freshpearYoon opened 1 year ago

freshpearYoon commented 1 year ago

Has anyone tried reproducing the code on refcocog dataset? My environment is python=3.7 and tensorflow=2.13 . I've succeeded on debugging errors caused by version change , but when I train the model on refcocog, with given base.yaml, my final validation seg_iou is around 28% .