tfjs-models VS deep-high-resolution-net.pytorch

I am wondering, will this also work with tensoflow.js or only tflite? I'd like to use this hand pose estimation from mediapipe: https://github.com/tensorflow/tfjs-models/tree/master/hand-pose-detection

I got the basic concept working using TensorFlow QnA model but the answers don't seem very accurate. Infact, unless you specifically ask the exact question, you dont get the right answer. Its not intelligent enough because the entire PDF content becomes a bag of words instead of having context to those words. for eg. When someone types "languages", it should search within a section named Languages.

I think you are beginning to connect the dots by now 😉 What we will do is to build a small proof-of-concept (POC) by writing a simple react app and hook up a pre-trained tensorflow.js model, The text toxicity model to "moderate" the user's text input and show a notification of what's wrong with it, a text toxicity meter if you will...

TensorFlow.js is a JavaScript library developers can use to run pre-trained machine-learning models in the browser. The library has a variety of models for tasks such as object identification and language processing. One of these models is the text toxicity detection model.

TensorFlow has a toxicity classification model available. I don't find it to work that well, but it does something. Not sure if it works in other languages than English. Tried the demo with some offensive Dutch and it passed it.

No clue if it will work on drawn images. It depends on what the model was trained on. The models github is a good place to get started on figuring that out: https://github.com/tensorflow/tfjs-models/tree/body-pix-v2.0.4/body-pix

You probably want to check out something like tensorflow https://github.com/tensorflow/tfjs-models where you can build and test your models.

I decided to start with the toxicity model OOTB demo code for simplicity. You can find this code in their Github repo.

I am sure you have some great ideas in mind for your model design, but a quick tip (from having worked on a similar project) - it may be very challenging to simply take raw videos as input (especially with unconstrained camera viewpoints) without doing some feature extraction/keypoint detection first. For example, open-source plug-and-play 2D keypoint detectors are extremely good nowadays (e.g HRNet), and explicitly detecting 2D keypoints before classifying deadlift videos as "good" or "bad" will likely make the task more feasible!

The repo is well maintained on GitHub and I have replicated the author's work. But I didn't get much understanding of how things are working there. I didn't see any results.