How to run PoseNet model and save data points for multiple images?

• yoga-pose-estimation

  1 31 0.0 Jupyter Notebook

  Discontinued Model to classify yoga pose type and estimate joint positions of a person from an image

Or OpenPose yoga pose classifier, though I prefer OpenPifPaf because it deploys quicker and easier.

• Face Recognition

  34 51,755 0.0 Python

  The world's simplest facial recognition api for Python and the command line

You feed the 17 landmark pairs as 34 inputs into a feed forward regression network (last time I did this I just tweaked something like this) with 34 pairs. However, it can help a lot to also add in the face detection to speed this up. So if you were to combine the landmarks from face detection as well like this face recognition and expand up to include the landmarks which helps I've found.

• InfluxDB

  www.influxdata.com featured

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

• yoga-pose-CNN

  1 11 0.0 Python

  Simple image classification convolutional neural net and prediction for 10 different yoga poses

Other people have used CNNs to do this: https://github.com/amarchenkova/yoga-pose-CNN/ I haven't played with this.

Suggest a related project