firebase_ml_custom

Description:

firebase ml custom

Firebase Machine Learning Custom #

A Flutter plugin to use the Firebase ML Custom Models API.
For Flutter plugins for other Firebase products, see README.md.
Usage #
To use this plugin, add firebase_ml_custom as a dependency in your pubspec.yaml file. You must also configure Firebase for each platform project: Android and iOS (see the example folder or https://codelabs.developers.google.com/codelabs/flutter-firebase/#4 for step by step details).
Android #
In order to use methods referencing those of Firebase Model Manager minimum SDK version required is 24.
Otherwise minimum SDK version is 21.
This can be specified in your app-level build.gradle file.
iOS #
A minimum deployment target of 9.0 is required. You can add the line platform :ios, '9.0' in your iOS project Podfile.
You may also need to update your app's deployment target to 9.0 using Xcode. Otherwise, you may see
compilation errors.
Using Firebase Model Manager #
1. Create a FirebaseCustomRemoteModel. #
Create a FirebaseCustomRemoteModel object.
You should already have a model in your Firebase console available for download. Use the name that you gave your model in the Firebase console.
FirebaseCustomRemoteModel remoteModel = FirebaseCustomRemoteModel('myModelName');
copied to clipboard
2. Create a FirebaseModelDownloadConditions. #
Create a FirebaseModelDownloadConditions object.
Specify optional platform-specific conditions for the model download.
FirebaseModelDownloadConditions conditions =
FirebaseModelDownloadConditions(
androidRequireWifi: true,
androidRequireDeviceIdle: true,
androidRequireCharging: true,
iosAllowCellularAccess: false,
iosAllowBackgroundDownloading: true);
copied to clipboard
All of these parameters except iosAllowCellularAccess default to false if not specified. iosAllowCellularAccess defaults to true.
Each platform looks only at its platform-specific parameters and ignores the rest.
3. Create an instance of FirebaseModelManager. #
Create a FirebaseModelManager object corresponding to the default FirebaseApp instance.
FirebaseModelManager modelManager = FirebaseModelManager.instance;
copied to clipboard
4. Call download() with FirebaseCustomRemoteModel and FirebaseModelDownloadConditions. #
Initiate the download of a remote model if the download hasn't begun.
If the model's download is already in progress, the current download task will continue executing.
If the model is already downloaded to the device, and there is no update, the call will immediately succeed.
If the model is already downloaded to the device, and there is update, a download for the updated version will be attempted.
await modelManager.download(remoteModel, conditions);
copied to clipboard
5. Call isModelDownloaded() with FirebaseCustomRemoteModel. #
Return whether the given remote model is currently downloaded.
if (await modelManager.isModelDownloaded(model) == true) {
// do something with this model
} else {
// fall back on a locally-bundled model or do something else
}
copied to clipboard
You can also check if download was successfully completed by surrounding download method with try and catch.
5. Call getLatestModelFile() with FirebaseCustomRemoteModel. #
Return the File containing the latest model for the remote model name. This will fail if the model is not yet downloaded on the device or valid custom remote model is not provided.
File modelFile = await modelManager.getLatestModelFile(model);
copied to clipboard
You can feed this file directly into an interpreter or preprocess it, depending on the interpreter of your choice.
Possible Flutter TF Lite interpreters:

tflite
tflite_flutter

Google does not recommend usage of any specific interpreter and leaves it up to the user to decide.
Getting Started #
See the example directory for a complete sample app using Firebase Machine Learning Custom.
Issues and feedback #
Please file Flutterfire specific issues, bugs, or feature requests in our issue tracker.
Plugin issues that are not specific to Flutterfire can be filed in the Flutter issue tracker.
To contribute a change to this plugin,
please review our contribution guide,
and send a pull request.