qiaosiyi

Thank you for your response, of course, I can make many products in future, because I am not in China mainland, so I need a delegation, you are the best...

> shou dong dian zan why you so beautiful.

> you > two > guys > so > diao happy Valentine‘s day

人家不是说只支持中文的嘛，再说英文切词，应该不用这个方法，直接按照空格划分就行。你要是标词性那肯定不行，这个得有对应的模型。

> I'm struggling to find deployment configurations for MMDeploy [this link](https://github.com/open-mmlab/mmdeploy/blob/master/docs/en/02-how-to-run/convert_model.md) https://github.com/DerryHub/BEVFormer_tensorrt this project can convert model 2 onnx, it works.

> You can try this project to convert bevformer to onnx or tensorrt engine: https://github.com/DerryHub/BEVFormer_tensorrt This works for me.