DenisTome / Lifting-from-the-Deep-release

Implementation of "Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image"

Home Page:https://denistome.github.io/papers/lifting-from-the-deep

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Unable to run it on videos

Zumbalamambo opened this issue · comments

How do I run it in a realtime video?

Im getting the following error ```
from prob_model import Prob3dPose
ModuleNotFoundError: No module named 'prob_model'

About running the program on a real time video, our approach has been designed for a single image. Therefore, if you want to run on a video you have to run the pose_estimator.estimate(image) for each of the frames in your video, independently.
About the error, make sure that you are running the demo.py file inside the project folder using python2.7