Tweet
Tweet

Slide 1

Slide 1 text

Android Developers Guide to Machine Learning With MLKit, Tensorflow & Firebase

Slide 2

Slide 2 text

Rebecca Franks @riggaroo Google Developer Expert Android @ Over Pluralsight Author GDG Johannesburg Organiser

Slide 3

Slide 3 text

Who considers themselves an expert in Machine Learning?

Slide 4

Slide 4 text

No content

Slide 5

Slide 5 text

What is Machine Learning?

Slide 6

Slide 6 text

Machine learning is an application of Artificial Intelligence in which we input a lot of data and let the machines learn “by themselves”

Slide 7

Slide 7 text

No content

Slide 8

Slide 8 text

No content

Slide 9

Slide 9 text

No content

Slide 10

Slide 10 text

No content

Slide 11

Slide 11 text

No content

Slide 12

Slide 12 text

No content

Slide 13

Slide 13 text

No content

Slide 14

Slide 14 text

No content

Slide 15

Slide 15 text

Face detection$% W orks offline

Slide 16

Slide 16 text

No content

Slide 17

Slide 17 text

No content

Slide 18

Slide 18 text

No content

Slide 19

Slide 19 text

No content

Slide 20

Slide 20 text

No content

Slide 21

Slide 21 text

No content

Slide 22

Slide 22 text

Demo

Slide 23

Slide 23 text

No content

Slide 24

Slide 24 text

⛩ Landmark detection

Slide 25

Slide 25 text

No content

Slide 26

Slide 26 text

No content

Slide 27

Slide 27 text

Demo

Slide 28

Slide 28 text

No content

Slide 29

Slide 29 text

Image Labelling W orks offline

Slide 30

Slide 30 text

No content

Slide 31

Slide 31 text

Barcode scanning W orks offline

Slide 32

Slide 32 text

No content

Slide 33

Slide 33 text

No content

Slide 34

Slide 34 text

val options = FirebaseVisionBarcodeDetectorOptions.Builder() .setBarcodeFormats(FirebaseVisionBarcode.FORMAT_QR_CODE) .build() val image = FirebaseVisionImage.fromBitmap(bitmap) val detector = FirebaseVision.getInstance() .getVisionBarcodeDetector(options) detector.detectInImage(image) .addOnSuccessListener { processedBitmap.postValue(barcodeProcessor.drawBoxes(bitmap, it))

Slide 35

Slide 35 text

val options = FirebaseVisionBarcodeDetectorOptions.Builder() .setBarcodeFormats(FirebaseVisionBarcode.FORMAT_QR_CODE) .build() val image = FirebaseVisionImage.fromBitmap(bitmap) val detector = FirebaseVision.getInstance() .getVisionBarcodeDetector(options) detector.detectInImage(image) .addOnSuccessListener { processedBitmap.postValue(barcodeProcessor.drawBoxes(bitmap, it)) var result = String() it.forEach { result += "VALUE TYPE: ${it.valueType} Raw Value: ${it.rawValue}" textResult.postValue(result)

Slide 36

Slide 36 text

val image = FirebaseVisionImage.fromBitmap(bitmap) val detector = FirebaseVision.getInstance() .getVisionBarcodeDetector(options) detector.detectInImage(image) .addOnSuccessListener { processedBitmap.postValue(barcodeProcessor.drawBoxes(bitmap, it)) var result = String() it.forEach { result += "VALUE TYPE: ${it.valueType} Raw Value: ${it.rawValue}" textResult.postValue(result) } }.addOnFailureListener{ textResult.postValue(it.message) }

Slide 37

Slide 37 text

No content

Slide 38

Slide 38 text

OCR W orks offline

Slide 39

Slide 39 text

No content

Slide 40

Slide 40 text

On Device vs Cloud

Slide 41

Slide 41 text

private fun doOcrDetection(bitmap: Bitmap){ val detector = FirebaseVision.getInstance() .visionTextDetector val firebaseImage = FirebaseVisionImage.fromBitmap(bitmap) detector.detectInImage(firebaseImage) .addOnSuccessListener { processedBitmap.postValue(ocrProcessor.drawBoxes(bitmap, it)) var result = String() it.blocks.forEach { result += " " + it.text textResult.postValue(result)

Slide 42

Slide 42 text

private fun doOcrDetection(bitmap: Bitmap){ val detector = FirebaseVision.getInstance() .visionTextDetector val firebaseImage = FirebaseVisionImage.fromBitmap(bitmap) detector.detectInImage(firebaseImage) .addOnSuccessListener { processedBitmap.postValue(ocrProcessor.drawBoxes(bitmap, it)) var result = String() it.blocks.forEach { result += " " + it.text textResult.postValue(result) } } .addOnFailureListener{ Toast.makeText(/../“Error detecting Text $it”/../) }

Slide 43

Slide 43 text

private fun doOcrDetection(bitmap: Bitmap){ val detector = FirebaseVision.getInstance() .visionTextDetector val firebaseImage = FirebaseVisionImage.fromBitmap(bitmap) detector.detectInImage(firebaseImage) .addOnSuccessListener { processedBitmap.postValue(ocrProcessor.drawBoxes(bitmap, it)) var result = String() it.blocks.forEach { result += " " + it.text textResult.postValue(result) } } .addOnFailureListener{ Toast.makeText(/../“Error detecting Text $it”/../) }

Slide 44

Slide 44 text

No content

Slide 45

Slide 45 text

Custom Tensorflow Models W orks offline

Slide 46

Slide 46 text

TensorFlow

Slide 47

Slide 47 text

No content

Slide 48

Slide 48 text

No content

Slide 49

Slide 49 text

Retrain existing model 0 mobilenet_v1

Slide 50

Slide 50 text

What if I could tell what kind of chips I was eating?

Slide 51

Slide 51 text

Gather Training Data FFMPEG Folders of Images Retrain with new images Optimize for mobile Embed in app Store in Firebase App uses model

Slide 52

Slide 52 text

Gather training data

Slide 53

Slide 53 text

Export to Images using ffmpeg ffmpeg -i flings.mp4 flings/flings_%04d.jpg

Slide 54

Slide 54 text

Folders of images

Slide 55

Slide 55 text

Retrain with new images python -m scripts.retrain \ --bottleneck_dir=tf_files/bottlenecks \ --how_many_training_steps=500 \ --model_dir=tf_files/models/ \ --summaries_dir=tf_files/training_summaries/"${ARCHITECTURE}" \ --output_graph=tf_files/retrained_graph.pb \ --output_labels=tf_files/retrained_labels.txt \ --architecture="${ARCHITECTURE}" \ --image_dir=training_data/south_african_chips

Slide 56

Slide 56 text

Optimize for mobile bazel-bin/tensorflow/contrib/lite/toco/toco \ --input_file=AgencyDay/retrained_graph.pb \ --output_file=AgencyDay/chips_optimized_graph.tflite \ --input_format=TENSORFLOW_GRAPHDEF \ --output_format=TFLITE \ --input_shape=1,${IMAGE_SIZE},${IMAGE_SIZE},3 \ --input_array=input \ --output_array=final_result \ --inference_type=FLOAT \ --input_data_type=FLOAT

Slide 57

Slide 57 text

Insert into App https://codelabs.developers.google.com/codelabs/tensorflow-for-poets-2-tflite/ https://github.com/googlecodelabs/tensorflow-for-poets-2

Slide 58

Slide 58 text

Nik Nak 1 Or Not 2 bit.ly/mlkit-riggaroo

Slide 59

Slide 59 text

What if our model changes?

Slide 60

Slide 60 text

Ship an app update 3 And hope that people download it 4

Slide 61

Slide 61 text

Host on Firebase Updates automatically downloaded

Slide 62

Slide 62 text

val cloudSource = FirebaseCloudModelSource.Builder("my_cloud_model") .enableModelUpdates(true) .setInitialDownloadConditions(conditions) .setUpdatesDownloadConditions(conditions) .build() FirebaseModelManager.getInstance() .registerCloudModelSource(cloudSource) ……

Slide 63

Slide 63 text

g.co/codelabs/mlkit-android-custom-model

Slide 64

Slide 64 text

You don’t need to be a ML Expert to take advantage of ML in your apps!

Slide 65

Slide 65 text

Thank you!

Slide 66

Slide 66 text

Resources - https://codelabs.developers.google.com/ codelabs/tensorflow-for-poets - https://codelabs.developers.google.com/ codelabs/tensorflow-for-poets-2-tflite/ - https://codelabs.developers.google.com/ codelabs/mlkit-android-custom-model/ #0 - https://github.com/riggaroo/android- demo-mlkit