Can I program multiple models in one code script?

[p1n0cch10]

Hi,

I would like to detect the person in an image and classify the person(i.e. chef, soldier, ...).

So, I firstly use a pp-yolo for detection. Then get the patch based on the person's bbox. At last, I use a resnet50_vd for classification.

Currently I completed the training for the classification. But do not know how to put the detection model and the classification model in one piece of code.

Are there any examples for the application? Many thanks.

[littletomatodonkey]

For this case, it may be a better solution for you to export the pretrained weights to infernce models. And then you just need to extract the pre-process codes and post-process codes from the repos, therefore you can avoid defining so many models for the actual inference process.

[paddle-bot-old[bot]]

Since this issue has not been updated for more than three months, it will be closed, if it is not solved or there is a follow-up one, please reopen it at any time and we will continue to follow up. It is recommended to pull and try the latest code first. 由于该问题超过三个月未更新，将会被关闭，若问题未解决或有后续问题，请随时重新打开（建议先拉取最新代码进行尝试），我们会继续跟进。