How to deploy it on the mobile device?

[ElegantLin]

No description provided.

[Seanseattle]

Hello, you can try Paddle Lite for deployment. This can speed up more than 19 FPS by running on the GPU of a mobile phone.

[ElegantLin]

Do you plan to release the code of deploying the model on the mobile device?

[ElegantLin]

Hello, you can try Paddle Lite for deployment. This can speed up more than 19 FPS by running on the GPU of a mobile phone.

Hi, do you know how to convert the pdparam to Paddle Lite model? I think I have to use opt tools to do the conversion. Thus I should convert the pdparam to inference model. I went through this link. However, I don't know how to do the conversion if the model is a special ResNet. Could you please provide more information?

Thanks!