eleventy-base-blog VS tfjs-models

11ty is a lightweight static site generator. I chopped up my HTML and used the 11ty starter template called eleventy-base-blog as the structural foundation for the site.

Sure! It's on github at https://github.com/nosecreek/dustin-lammiman - I started with https://github.com/11ty/eleventy-base-blog for the basic templating logic.

Eleventy Base Blog demo site Source

To generate a static blog, we will be using Eleventy. Using the blog example from Eleventy as a base for our blog. Clone the repository:

I would do this with Eleventy which is a powerful static site generator with support for html partials (partial is what I call your toolbar here). You would use the template language nunjucks which Eleventy comes with support for, or you can choose plain html too if you don't want the Nunjucks capabilities for logic like if/else, for loops, javascript injection of dynamic values in your html at site generation time, etc. This repo shows most of the techniques you could need and use: https://github.com/11ty/eleventy-base-blog

For the second site I made using 11ty, I used this repo which is a more advanced 11ty template that can be customized. After following the instructions in the README.md file and edited all the markdown I came up with this:

Pre-established Eleventy Blog Template Go to eleventy base blog to clone the repository to your local file/folder.

The next example we'll look at goes more into depth of 11ty. We are creating this site from this template.

Say you want a more professonal looking site without having to do a lot of extra work, you’re in luck! 11ty has a community that has created templates that are available at this site. For this example, we will use the eleventy-base-blog, make sure to go to this repo and select the USE THIS TEMPLATE button to make a copy of the project in your namespace.

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.