Introduction
Machine learning is one of the trending topics but using the power of machine learning in your application was a hectic process.more over implementation in a mobile application was an area concerning experts. The situation is changing with the launch of ML kit.ML Kit is a mobile SDK with which you can utilize Google's machine learning technologies in your Android and IOS application. Google has bundled Google Cloud Vision API, TensorFlow Lite, and the Android Neural Networks API together into a single SDK. You don't have to know about neural networks or any other deep learning concepts. If you are having some experience in ML, then you can go with your own custom Tensorflow model for prediction or regression or anything that you want to do. Since ML kit is in beta, APIs might change in future. So For production-ready cloud-based APIs, consider using Cloud Vision APIs directly.
Features
- Easy and Ready to use common use cases
ML kit provides you with ready to use APIs for common use cases like text recognition, face detection, landmark identification and labeling images.
- Run-on device and Cloud
ML Kit’s APIs can run on-device as well as in the cloud. on-device APIs can process your data quickly and work even when there’s no network connection. cloud-based APIs, on the other hand, leverage the power of Google Cloud Platform's machine learning technology to give you an even higher level of accuracy.
These are the features supported on-device
These are the features supported in the cloud
- Use custom model
You can host your custom Tensorflow model in Firebase, so that it is available to your application. To host custom model navigate to your firebase console and select "ML Kit" from the side panel. Now select "CUSTOM" add your custom model in here.
