New model support: Support for inference with TESTR (Mutually exclusive with the next task). 新模型支持：支持 TESTR 的推理

[OpenMMLab-Assistant-004]

New model support: Support for inference with TESTR (Mutually exclusive with the next task).

新模型支持：支持 TESTR 的推理

Referring to the official implementation of TESTR, implement the inference code in the projects/ directory. The results should align with the official accuracy. The weights can be directly obtained by converting them from the official script.
References:

• Paper: https://openaccess.thecvf.com/content/CVPR2022/html/Zhang_Text_Spotting_Transformers_CVPR_2022_paper.html
• Official implementation: https://github.com/mlpc-ucsd/TESTR

（与 #290 互斥）参考 TESTR 的官方实现，在 projects/ 文件夹中实现推理部分代码，结果需要对齐官方精度。权重可直接通过脚本从官方转换得到。
参考：

• 论文: https://openaccess.thecvf.com/content/CVPR2022/html/Zhang_Text_Spotting_Transformers_CVPR_2022_paper.html
• 官方实现：https://github.com/mlpc-ucsd/TESTR

Task Information

Repository：MMOCR

Difficulty：Medium

Points：30

Estimated Time Consumption：7 days

Task Status

Claimant's Github ID：xiangyw99

Claim Time：2023年10月08日

PR Link：None

Points to Note

To claim the task, please reply Claim the mission in the comment section. After claiming the task, please add our assistant bot called MeowMewo on WeChat at: openmmlabwx.

After completing the task, please submit a PR with the title starting with [MMSIG]. After submission, please reply with your PR link in the comments section of this Discussion. We will review your work as soon as possible.

在评论区回复 Claim the mission 领取任务，领取任务后请及时添加小助手喵喵微信: openmmlabwx

完成任务后提交相关链接（如是PR，标题请以[MMSIG]开头）回复到本Disucssion评论区，我们会第一时间审核您的贡献。

[xiangyw99]

Claim the mission