TensorFlow Lite for Mobile Development: Deploy Machine Learning Models on Embedded and Mobile Devices
MP4 | Video: h264, 1920x1080 | Audio: AAC, 44.1 KHz, 2 Ch
Genre: eLearning | Language: English | Duration: 11 Lessons (41m) | Size: 636.5 MB
Deploy machine learning models more easily and efficiently on embedded and mobile devices using TensorFlow Lite (TFLite). TFLite is an open source deep learning framework developed by Google.
Look under the hood at the system architecture to see how and when to use each component of TFLite. In the first section, you will learn what makes TFLite different from standard TensorFlow and other products like TFMobile. In the next section, you will learn about the pre-trained model that is available in TFLite, and how to use that pre-trained model to build your own. You will also learn how to convert a TensorFlow model into the TFLite format and train it. After that, you will cover the concept of transfer learning and how you can apply transfer learning to train a pre-trained model to perform some custom tasks in TFLite.
Having trained the model, you'll use the TFLite interpreter to run a machine learning model on mobile platforms. As part of this you will review a simple Android app, which will help you to start using TFLite on mobile devices. Running machine learning models on mobile devices is really exciting but it also comes with challenges so, you will need to optimize your model to reduce your app's size.
Finally, you will learn how to run TFLite on embedded devices such as Raspberry Pi. Overall this video will help anyone who wants to start learning TFLite and train their own machine learning models using TFLite. After watching this video, you can apply your newly learned TFLite skills to your own projects.
What You Will Learn
Run any machine learning model on mobile devices
Experiment with machine learning projects on the Raspberry Pi
Create a machine learning-based mobile app
Who This Video Is For
Data scientists, software engineers, and students working in these fields will find useful information on working with machine learning models in their current mobile development environments.
