jiangduwang

quesions about dataset

4

hi,author! The data set link you provided includes three training sets, one test set and one verification set. How do you put these files under the CrowdHuman folder？ Thanks!

[Bug]

1

### Prerequisite - [X] I have searched [Issues](https://github.com/open-mmlab/mmocr/issues) and [Discussions](https://github.com/open-mmlab/mmocr/discussions) but cannot get the expected help. - [X] The bug has not been fixed in the [latest version (0.x)](https://github.com/open-mmlab/mmocr) or...

Code for training

2

Hello author, your work is very good! I am very interested in the training process in your paper, but unfortunately you have not provided the training code. I would like...

训练时直接卡住不动

1

 输出Epoch之后就不动了，nvidia-smi看也没有吃显卡资源。 

As the question requires, I would like to know how to infer a single image. The code generate.py you provided is for inferring a batch image. Thank you!

作者，您好！VLPT-STD是个很棒的工作，但是目前发布的只有预训练的代码，能否提供测试模型的代码和交叉注意力可视化的代码？