jamesonthecrow

keras.backend.clear_session()
# Retrain the model with our new configuration and callback
model = build_model()

model.compile(
    keras.optimizers.Adam(lr=metadata['learning_rate']),
    loss=keras.losses.sparse_categorical_crossentropy,
    metrics=[keras.metrics.sparse_categorical_accuracy]
)

jamesonthecrow

import fritz
import fritz.train

# Fritz needs to be configured first. Calling the fritz.Configure() method will
# read the credentials we setup for the CLI earlier.
fritz.configure()

# Create the callback

# Start by defining a training configuration and storing it as metadata

jamesonthecrow

# Convert to mobile formats
import coremltools
import tensorflow as tf
import tempfile

def convert_to_coreml(model):
    return coremltools.converters.keras.convert(
        model,
        input_names=['input'],
        output_names=['digit']

jamesonthecrow

import keras
from keras.datasets import mnist
keras.backend.clear_session()

(x_train, y_train), (x_test, y_test) = mnist.load_data()


def build_model():
    input = keras.layers.Input((28, 28, 1))
    out = keras.layers.Conv2D(16, 3, strides=2, activation='relu')(input)

jamesonthecrow

// Run the image through the model to identify pixels belonging to a pet.
FritzVisionSegmentResult segmentResult = predictor.predict(visionImage);

jamesonthecrow

// Determine how to rotate the image from the camera used.
int imgRotation = FritzVisionOrientation.getImageRotationFromCamera(this, cameraId);

// Create a FritzVisionImage object from android.media.Image
FritzVisionImage visionImage = FritzVisionImage.fromMediaImage(image, imgRotation);

jamesonthecrow

// Initialize the model included with the app
PetSegmentationOnDeviceModel onDeviceModel = new PetSegmentationOnDeviceModel();

FritzVisionSegmentPredictorOptions options = new FritzVisionSegmentPredictorOptions.Builder()
  .targetConfidenceThreshold(.4f)
  .build();

// Create the predictor with the Pet Segmentation model.
predictor = FritzVision.ImageSegmentation.getPredictor(onDeviceModel, options);

jamesonthecrow

extension ViewController: AVCaptureVideoDataOutputSampleBufferDelegate {

  func captureOutput(_ output: AVCaptureOutput, didOutput sampleBuffer: CMSampleBuffer, from connection: AVCaptureConnection) {
    let image = FritzVisionImage(buffer: sampleBuffer)
    image.metadata = FritzVisionImageMetadata()
    image.metadata?.orientation = FritzImageOrientation(from: connection)

    guard let result = try? visionModel.predict(image) else { return }
    
    let mask = result.buildSingleClassMask(

jamesonthecrow

class ViewController: UIViewController, UIImagePickerControllerDelegate,
UINavigationControllerDelegate {
  /// The rest of the view controller...
  
  /// Scores output from model greater than this value will be set as 1.
  /// Lowering this value will make the mask more intense for lower confidence values.
  var clippingScoresAbove: Double { return 0.6 }
  
  /// Values lower than this value will not appear in the mask.
  var zeroingScoresBelow: Double { return 0.4 }

jamesonthecrow

// ...
import Fritz

class ViewController: UIViewController {

    var cameraView: UIImageView!
    
    override func viewDidLoad() {
        super.viewDidLoad()