Pretrained-Language-Model icon indicating copy to clipboard operation
Pretrained-Language-Model copied to clipboard

wukong-为什么以ILSVRC作为验证集,模型不是在中文数据集上的训练的吗?

Open ghost opened this issue 2 years ago • 1 comments

python main.py \ --config="configs/wukong_vit_l/wukong_vit_l.py" \ --checkpoint="/cache/ckpt/wukong_vit_l.ckpt" \ --data_dir="/cache/data/ILSVRC/"

ghost avatar Sep 29 '22 03:09 ghost

我们同时翻译了下游任务的英文标签到中文,在主页上公开了下游数据的中文版本(https://wukong-dataset.github.io/wukong-dataset/index.html)

As mentioned in the paper, we also provide various benchmarking datasets with human-verified image-text pairs and Chinese labels for model benchmarks.

mengxj08 avatar Dec 02 '22 09:12 mengxj08