search

felixchenfy / Realtime-Action-Recognition

Apply ML to the skeletons from OpenPose; 9 actions; multiple people. (WARNING: I'm sorry that this is only good for course demo, not for real world applications !!! Those ary very difficult !!!)
MIT License
857 stars 248 forks source link

How to add other neural network models with least modifications of your work? #55

Closed BenoitKAO closed 3 years ago

BenoitKAO commented 4 years ago

Thank you for your marvelous work!

I have already read this issue: https://github.com/felixchenfy/Realtime-Action-Recognition/issues/46

However, I would like to know how to add other neural network models with the least modifications of your work? like mobilenet_v2_large, mobilenet_v2_small, mobilenet V1, V2 ,V3, openpose-darknet, YOLO, SSD, vgg-???, resnet-??? ... and so on.

Any help is appreciated.

felixchenfy commented 3 years ago

Hi, sorry there are only 2 options... mobilenet_thin and cmu.

I used the code of this github project https://github.com/ildoonet/tf-pose-estimation, which only supports the above two options.