Click here to Skip to main content
15,867,330 members
Articles / Artificial Intelligence / Tensorflow

Android Tensorflow Lite Best Practices and Optimizations

Rate me:
Please Sign up or sign in to vote.
5.00/5 (1 vote)
22 Sep 2020CPOL2 min read 5.6K   1  
In this article we will consider the ways in which the network could be further optimized.
Here we look at how for pre-trained networks, the network can be altered through quantization. We also discuss how if the model isn’t compatible with 8-bit quantization, the network can be converted to use 16-bit. Finally, we quickly look at network pruning.

Views

Daily Counts

This article is part of the series 'Mobile Neural Networks On Android with TensorFlow Lite View All

License

This article, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)


Written By
Software Developer
United States United States
I attended Southern Polytechnic State University and earned a Bachelors of Science in Computer Science and later returned to earn a Masters of Science in Software Engineering. I've largely developed solutions that are based on a mix of Microsoft technologies with open source technologies mixed in. I've got an interest in astronomy and you'll see that interest overflow into some of my code project articles from time to time.



Twitter:@j2inet

Instagram: j2inet


Comments and Discussions