JSONFeed VS tfjs-models

Imagine you have an RSS feed similar to this. The objective is to obtain that RSS feed, analyze the data it contains, and take action with it. RSS is an XML format, whereas JSON is arguably easier to work with than XML. While many APIs provide JSON results, RSS is less likely to receive them, despite their existence.

At least for now, Astro clearly falls short in this category. Its built-in ability to provide RSS feeds is rather limited, and it doesn’t yet enable JSON feeds at all.5 In the meantime, some users, including Yours Truly, have gotten around this by using the third-party feed package, which supports RSS and JSON feeds.6

want to also support JSON Feed?

-------- # Metadata comes from _data/metadata.json permalink: "{{ metadata.jsonfeed.path | url }}" eleventyExcludeFromCollections: true -------- { "version": "https://jsonfeed.org/version/1", "title": "{{ metadata.title }}", "home_page_url": "{{ metadata.url }}", "feed_url": "{{ metadata.jsonfeed.url }}", "description": "{{ metadata.description }}", "author": { "name": "{{ metadata.author.name }}", "url": "{{ metadata.author.url }}" }, "items": [ {%- for post in collections.posts | reverse %} {%- set absolutePostUrl %}{{ post.url | url | absoluteUrl(metadata.url) }}{% endset -%} { "id": "{{ absolutePostUrl }}", "url": "{{ absolutePostUrl }}", "title": "{{ post.data.title }}", "tags": [ {%- for tag in helpers.removeCollectionTags(post.data.tags) -%} "{{tag}}" {%- if not loop.last %}, {%- endif %} {%- endfor %}], "summary": "{{ post.data.description }}", "content_html": {% if post.templateContent %}{{ post.templateContent | dump | safe }}{% else %}""{% endif %}, "date_published": "{{ post.date | rssDate }}" } {%- if not loop.last -%} , {%- endif -%} {%- endfor %} ] }

Your wish is my command.

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.

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.

All data to be used with a model needs to be prepared to be in the correct input format. In this case images needs to be turned into tensors. The exact format is usually documented but I found the underlying documentation for this model a bit lacking in details about the exact input/outputs but still useful for interpreting them https://github.com/tensorflow/tfjs-models/tree/master/face-landmarks-detection. Instead we can examine the model.json which is more explict. We can find a few keys that define the input and output:

The BlazePose software determines the position of the human body based on the camera image. For instance, a fitness app can automatically evaluate your technique, an online store can suggest suitable clothing styles, or games - create an avatar that repeats your actions. Model code is available on GitHub, there is also a demo in the browser.

Since the release of the latest version of the MediaPipe handpose detection machine learning model that allows the detection of multiple hands, I've had in mind to try to use it to create UIs, and here's the result of a quick prototype built in a few hours!