TensorFlow Lite with Sayak Paul
Machine learning is magical, isn’t it? Sometimes, it comes at the cost of size and cost. This is particularly concerning when you are trying to incorporate machine learning in resource-constrained environments. This can include low-key computers, mobile, and embedded devices. So, to enable the developers to seamlessly integrate machine learning prowess in those applications, TensorFlow Lite was born.
In this session, we will discuss what TensorFlow Lite is, what it can do, different scenarios where developers can use it, some best practices of using it, and more. The session will be concluded with short QnA.
Sayak Paul is a Deep Learning Associate at PyImageSearch, where we works at the intersection of computer vision and deep learning. He enjoys understanding things and explaining them well.
This presentation was a part of our Virtual Deep Learning Salon, to sign up for updates on these join our meetup and slack community!
http://wandb.me/meetups
http://wandb.me/fs
Deck: http://wandb.me/tfl-pune
Our report on Quantization: https://app.wandb.ai/sayakpaul/tale-o...
GitHub repository: https://github.com/sayakpaul/Adventur...
👩🏼🚀Weights and Biases:
Record and visualize every detail of your research, collaborate easily, advance the state of the art - we’re always free for academics and open source projects. Email [email protected] with any questions or feature suggestions.
Blog: https://www.wandb.com/articles
Gallery: See what you can create with W&B -https://app.wandb.ai/gallery
Continue the conversation on our slack community - http://wandb.me/fs