TechNuggets VS tfjs-models

Next, we will create our components. Nothing too crazy, just a text component and a notifications component. Each one will have its own css file in the src/components directory. (you can check out the code at this repo) Eventually, our frontend will look like something like this

I've have all the code used in this post available in this repo

I've created a notebook in this Github repo to demo some of Plotly basic capabilities and I highly recommend checking out the official documentations for examples of each plot type and to discover lots of cool stuff that you can put in your notebook/site 🙂.

If you are eager to see a complete example on a Tkinter gui, I've created and example which is more or less simulating the actual situation which I told you about earlier in this post. You can find it in this github repo. I've separated my business logic (killer_script.py) from my GUI (myapp.py) and I used a launcher module (app_launcher.py) for further modularity. I did my best commenting the py files 🙂 but you will always find something that I missed and you didn't totally understand! That's completely normal. You only have to look it up online or in the docs! If that didn't work, just drop it below in the comments and I'll try my best to make it simpler for you 😉

Pandas can import data from a wide variety of data sources. Usually it uses the function read_x where "x" is csv, excel, json, ..., etc. In this tutorial, we will use a csv (comma separated values) file representing a transactions (purchases) log in a grocery store. Each row represents one item in a single transaction. One transaction can have multiple items. Sometimes, manual entries can happen 😬. You can find the sample dataset and all the code in this tutorial in this Github repo. The goal of this tutorial is to wrangle this file to find out what is the total revenue per item category and the top 3 purchased items.

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.