zengyan-97 / X-VLM

X-VLM: Multi-Grained Vision Language Pre-Training (ICML 2022)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

pretrain-base-4m for the X_VLM

wfx0330 opened this issue · comments

Dear authors:
Thanks for your great works. While pretraining the model, I don't know how to organize the open dateset. I have already tried the following yaml.

图片
图片

Hi,

I am sorry we cannot re-distribute the data. I provide some data examples and hope it can help. Please see README for details.