Join our Meetup group for more events! https://www.meetup.com/data-umbrella
- Transcript: https://github.com/data-umbrella/event-transcripts/blob/main/2022/65-shivay-tensorflowjs.md
- Meetup event: https://www.meetup.com/data-umbrella/events/288166766/
- Video: https://youtu.be/k1rHkMmORA4
- Transcriber: ? [needs a transcriber]
- Slides: https://docs.google.com/presentation/d/1HxU3EsjY5mf98t0IoDkMbcvzrdmaSWxT_r5oSlYPKM4/edit?usp=sharing
- Website / API: https://www.tensorflow.org/js
- Models: https://www.tensorflow.org/js/models
- GitHub Code: https://github.com/tensorflow/tfjs
- Google Group: [email protected]
- TensorFlow forum: https://discuss.tensorflow.org/tag/tjfs
- YouTube playlist: goo.gle/made-with-tfjs
- Codepen: https://codepen.io/topic/tensorflow/
- Glitch: https://glitch.com/@TensorFlowJS
- Sample dataset: https://www.kaggle.com/datasets/uciml/pima-indians-diabetes-database
- Recommended Reading: Deep Learning with JavaScript - https://www.manning.com/books/deep-learning-with-javascript
- Book: LearningTensorFlow.js - https://github.com/GantMan/learn-tfjs
- edX: https://www.edx.org/learn/javascript/google-google-ai-for-javascript-developers-with-tensorflow-js
## Timestamps
00:00 Data Umbrella Introduction
03:06 Speaker Introduction
04:17 Presentation Intro - Machine Learning for the Web: Introduction to TensorFlow.JS
06:27 Why do we need machine learning in JavaScript (JS)?
08:02 What is TensorFlow?
09:03 Versatility & language popularity - ML can be used on any platform JS can run
10:30 ML application ideas (e.g. accessible web apps, sound recognition, etc.)
11:38 3 options for using TensorFlow
13:00 Option 1: Use pre-trained models with JS classes
15:14 Real-world examples
19:15 Option 2: Retrain existing neural network models to work with your own data
19:51 Image classification example (100 images) with Teachable Machine (separate tool with downloadable code)
26:24 Pause for Q&A
26:55 Example using Cloud Auto ML for larger image datasets (100,000+)
28:29 Option 3: Coding your own model
29:32 High-level TensorFlow architecture
31:06 Backends and hardware execution
32:07 Chart - Model Inference Performance Only
32:45 Chart - performance comparison between JS and Python of Hugging Face DistilBERT (NLP-based model)
33:05 5 benefits of using TensorFlow on the front end (client side)
33:59 4 benefits of using TensorFlow on the back end (server side)
35:00 Demo code example 1 - image detection
42:35 Demo code example 2 - TensorFlow.JS converter (converting Python model to JS model)
47:24 More resources for learning and inspiration
49:40 Join the community - #MadeWithTFJS
50:34 What will you make? Machine learning is for everyone.
50:57 Q&A (Using PyTorch, using TensorFlow in production) & final thoughts
- Introduction to Tensorflow.JS
- Benefits of running Tensorflow.js with Nodejs on backend and on Frontend/Client Side
- Workshop to build a project using TensorFlowjs during live demonstration
This workshop gives an introduction about Tensorflow.JS which is an open source Javascript Library that allows running machine learning models on the browser itself and helps integrate the models with web applications. Tensorflow.JS gives creators working with Web Development a powerful tool to use with their web apps to create dynamic web apps using machine learning. The developers might require powerful CPUs/GPUs to be used for training of the models. This is where Tensorflow.JS ( TFJS ) comes into the picture. It allows standard machine learning libraries and models to be used directly with Javascript. It runs the models on the Browser ( client side ), or on the backend with Nodejs. And it makes it really easy for the Javascript developers to integrate machine learning models without much knowledge behind how these models work.
Shivay Lamba is a software developer specializing in DevOps, Machine Learning and Full Stack Development. He is an Open Source Enthusiast and has been part of various programs like Google Code In and Google Summer of Code as a Mentor and has also been a MLH Fellow.
- LinkedIn: https://www.linkedin.com/in/shivaylamba
- Twitter: https://twitter.com/howdevelop
- GitHub: https://github.com/shivaylamba
#tensorflowjs #deeplearning
