search

smellslikeml / ActionAI

Real-Time Spatio-Temporally Localized Activity Detection by Tracking Body Keypoints
https://www.hackster.io/actionai/actionai-custom-tracking-multiperson-activity-recognition-fa5cb5
GNU General Public License v3.0
765 stars 191 forks source link

bounding box and pose dots on video #45

Open nomaad42 opened 3 years ago

nomaad42 commented 3 years ago

Hello! Thanks a lot for your great work!

When I run inference.py on Yoga weights, on video it doesn't show the bounding box of the person and does not show dots of Pose Estimation, as in your GIFs. How can I put BB and Dots on the person on video, like in your GIFs?

hareskoruz commented 3 years ago

Yes Same doubt here,, pl share with output @smellslikeml

smellslikeml commented 3 years ago

Hi there! If you want to create something closer to the gifs in the README, try the instructions under Deployment. The iva.py script contains an annotator to draw the poses and bounding boxes. You can update the model to your own within the script.

hareskoruz commented 3 years ago

Hey, @smellslikeml in Train.py u were using two classes for Train.py in Code? I have "Indices out of range" error for using many classes.. pl provide solution