camera: get the streaming image buffers
https://pub.dev/packages/camera

tflite: run our trained model
https://pub.dev/packages/tflite

image_picker: pick image from gallery
https://pub.dev/packages/image_picker

android/app/build.gradle

android {
    ...
    aaptOptions {
        noCompress 'tflite'
        noCompress 'lite'
    }
    ...
}


minSdkVersion 21

* Download the dataset for training
    Face Mask Lite Dataset

* Training
    - go to https://teachablemachine.withgoogle.com to train our model
    - Get Started
    - Image Project
    - Edit `Class 1` for any Label(example `WithMask`)
    - Edit `Class 2` for any Label(example `WithoutMask`)
    - Update image from dataset download above
    - Click `Train Model`(using default config) and waiting...
    - Click `Export Model` and select `Tensorflow Lite`
    - Download (include: *.tflite, labels.txt)

loadModel() async {
    Tflite.close();
    await Tflite.loadModel(
        model: "assets/model.tflite", 
        labels: "assets/labels.txt",
        //numThreads: 1, // defaults to 1
        //isAsset: true, // defaults: true, set to false to load resources outside assets
        //useGpuDelegate: false // defaults: false, use GPU delegate
    );
  }

Output format:
  [{
    index: 0,
    label: "WithMask",
    confidence: 0.989
  },...]

please checkout repo github
https://github.com/hiennguyen92/face_mask_detection_tflite