Not Har Gow: Using Custom Models with ML Kit

ML Kit for Firebase comes with ready-to-use APIs for common machine learning tasks, but it also allows you to use your own custom models. In this talk, I want to give an overview of TensorFlow on mobile, show you how to set up and deploy custom models with Firebase, and walk through using the Android SDK. As a motivating example, I retrained an image classifier to recognize various dumplings!

Presented at Ohio DevFest, 2018-10-13

Note: this deck does not include the live demo. Will update with YouTube link when available.

Transcript

1. Not Har Gow: Using Custom Models with ML Kit Eric Fung • @gnufmuffin Ohio DevFest • #OhioDevFest18 • 2018-10-13
4. Demo
5. History Image credit: burst.shopify.com
6. TensorFlow ‣ Open-source framework for ML ‣ First release in Nov 2015 ‣ Included sample for Android Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
7. TensorFlow (Nov 2015) static { System.loadLibrary("tensorflow_demo"); } public native int initializeTensorflow(…) public native String classifyImageBmp(Bitmap bitmap) Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
8. TensorFlow (Jan 2017) // Load model from disk TensorFlowInferenceInterface tf = new TensorFlowInferenceInterface(assetManager, "my_model.pb"); // Copy the input data into TensorFlow tf.feed(inputName, floatValues, 1, inputSize, inputSize, 3); // Run the inference call. tf.run(outputNames, logStats); // Copy the output Tensor back into the output array. tf.fetch(outputName, outputs); Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
9. TensorFlow for Mobile (May 2017) dependencies { compile 'org.tensorflow:tensorflow-android:1.2.0-preview' } Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
10. TensorFlow for Mobile (Aug 2017) Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
11. I/O 2017 Announcements Neural Networks API ‣ Android Oreo ‣ Hardware accelerated, with software fallback TensorFlow Lite ‣ Designed for low-latency on mobile/ embedded ‣ Recommended solution for new projects Image credit: TensorFlow
12. Firebase ML Kit (May 2018) ‣ Easy-to-use base APIs for ‣ Image classification, OCR, face detection ‣ Barcode scanning, landmark detection ‣ Hybrid local/cloud execution ‣ Support for custom models Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
13. Custom Models with ML Kit Image credit: burst.shopify.com
14. Custom Models with ML Kit ‣ Bring your own TF Lite model ‣ Provides API to run inference on-device ‣ Hosted models are updated automatically Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
15. Custom Models Workflow 1. Build custom model or retrain existing model Image credit: burst.shopify.com
16. 1. Build custom model or retrain existing model 1. Use an existing model 2. Retrain an existing model 3. (Have someone) Write one from scratch Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
17. Custom Models Workflow 1. Build custom model or retrain existing model 2. Convert to TensorFlow Lite Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
18. 2. Convert to TensorFlow Lite ‣ Use the TensorFlow Optimizing Converter ‣ Might need custom TF Lite build if operators are missing Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
19. Custom Models Workflow 1. Build custom model or retrain existing model 2. Convert to TensorFlow Lite 3. Bundle with app and/or host on Firebase Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
20. 3. Bundle with app ‣ Include in src/main/assets ‣ Ensure model doesn't get compressed android { aaptOptions { noCompress "tflite" noCompress "lite" } } ‣ Could also download from your own server Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
21. 3. Host on Firebase
22. 3. Host on Firebase
23. 3. Host on Firebase
24. 3. Host on Firebase
25. Custom Models Workflow 1. Build custom model or retrain existing model 2. Convert to TensorFlow Lite 3. Bundle with app and/or host on Firebase 4. Integrate SDK into your app Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
26. 4. Integrate SDK into your app ‣ Add dependency ‣ Configure sources ‣ Create interpreter ‣ Define inputs/outputs ‣ Run inference ‣ Process outputs Image credit: burst.shopify.com
27. Add the dependency dependencies { implementation 'com.google.firebase:firebase-ml-model-interpreter:16.2.2' } Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
28. Configure a bundled source FirebaseLocalModelSource localSource = new FirebaseLocalModelSource.Builder("my_local_model") .setAssetFilePath("my-custom-model.tflite") .build(); FirebaseModelManager.getInstance() .registerLocalModelSource(localSource); Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
29. Configure a bundled source FirebaseLocalModelSource localSource = new FirebaseLocalModelSource.Builder("my_local_model") .setAssetFilePath("my-custom-model.tflite") .build(); FirebaseModelManager.getInstance() .registerLocalModelSource(localSource); Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
30. Configure a downloaded source FirebaseLocalModelSource downloadedSource = new FirebaseLocalModelSource.Builder("my_local_model") .setFilePath("/path/to/downloaded/model.tflite") .build(); FirebaseModelManager.getInstance() .registerLocalModelSource(downloadedSource); Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
31. Specify when hosted model is downloaded FirebaseModelDownloadConditions.Builder condBuilder = new FirebaseModelDownloadConditions.Builder() .requireWifi() .requireCharging() .requireDeviceIdle(); } FirebaseModelDownloadConditions conditions = condBuilder.build(); Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
32. Specify when hosted model is downloaded FirebaseModelDownloadConditions.Builder condBuilder = new FirebaseModelDownloadConditions.Builder() .requireWifi() .requireCharging() // Android 7.0+ .requireDeviceIdle(); // Android 7.0+ } FirebaseModelDownloadConditions conditions = condBuilder.build(); Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
33. Bind conditions to hosted source FirebaseCloudModelSource cloudSource = new FirebaseCloudModelSource.Builder("my-custom-model") .enableModelUpdates(true) .setInitialDownloadConditions(inConditions) .setUpdatesDownloadConditions(upConditions) .build(); FirebaseModelManager.getInstance() .registerCloudModelSource(cloudSource); Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
34. Bind conditions to hosted source FirebaseCloudModelSource cloudSource = new FirebaseCloudModelSource.Builder("my-custom-model") .enableModelUpdates(true) .setInitialDownloadConditions(conditions) .setUpdatesDownloadConditions(conditions) .build(); FirebaseModelManager.getInstance() .registerCloudModelSource(cloudSource); Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
35. Create interpreter FirebaseModelOptions options = new FirebaseModelOptions.Builder() .setCloudModelName("my-custom-model") .setLocalModelName("my_local_model") .build(); FirebaseModelInterpreter interpreter = FirebaseModelInterpreter.getInstance(options); Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
36. Define model input and output shapes FirebaseModelInputOutputOptions inputOutputOptions = new FirebaseModelInputOutputOptions.Builder() .setInputFormat(0, FirebaseModelDataType.BYTE, new int[]{1, 224, 224, 3}) .setOutputFormat(0, FirebaseModelDataType.BYTE, new int[]{1, 1000}) .build(); ‣ Example for image classification model with byte input and output ‣ Use TensorBoard or Netron to check (or ask the model author) Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
37. Define inputs byte[][][][] imageBytes = new byte[1][224][224][3]; // Convert Bitmap to input… FirebaseModelInputs inputs = new FirebaseModelInputs.Builder() .add(imageBytes) .build(); Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
38. Run inference Task<FirebaseModelOutputs> result = interpreter.run(inputs, inputOutputOptions) .addOnSuccessListener( new OnSuccessListener<FirebaseModelOutputs>() { @Override public void onSuccess(FirebaseModelOutputs result) { // Process outputs… } }) Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
39. Process outputs FirebaseModelOutputs result = …; byte[][] output = result.<byte[][]>getOutput(0); byte[] probabilities = output[0]; // Pick highest probability // Look up corresponding label Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
40. Things to watch for Image credit: burst.shopify.com
41. TensorFlow Lite ‣ Development on TensorFlow is very active ‣ GitHub: 110K stars, 68K forks, 12K closed issues ‣ ⚠ Broken links in documentation ‣ ⚠ Incorrect flags or commands in codelabs ‣ Check input and output shapes! ‣ Future: more operators, on-device training Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
42. ML Kit ‣ Firebase hosting only stores the model ‣ What about label files? ‣ What about versioning? ‣ SDK has no callbacks ‣ When did updated model get downloaded? ‣ What model am I running? ‣ Future: model optimization and compression ‣ Future: more domains (speech, text) Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
43. Are ML Kit custom models for you? It depends …if you can use an existing TF Lite model …if you can convert your model into TF Lite …if you want cloud hosting …if you want to get up and running now Image credit: burst.shopify.com
44. Resources Image credit: burst.shopify.com
45. Code ‣ Custom ML models with ML Kit for Firebase codelab ‣ github.com/efung/tensorflow-for-poets-2 ‣ My fork of TensorFlow for Poets codelab ‣ Added ML Kit version with live camera ‣ github.com/the-dagger/MLKitAndroid ‣ Pokémon Detector uses a custom model ‣ TensorFlow tutorials, e.g. image retraining
46. Reading ‣ ML for Android Developers • Mark Allison ‣ Who's Afraid of Machine Learning? • Britt Barak ‣ Android meets Machine Learning: From TensorFlow mobile/lite to ML Kit • Qian Jin ‣ Building “Pokédex” in Android using TensorFlow Lite and Firebase’s ML Kit • Harshit Dwivedi ‣ How to convert a custom model to TensorFlow Lite • Eric Hsiao
47. Reading ‣ Free ebook ‣ Covers TensorFlow Mobile, but has good background Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
48. Help ‣ Firebase Community Slack ‣ StackOverflow ‣ tensorflow-lite ‣ firebase-mlkit ‣ TensorFlow GitHub issues ! Using Custom Models with ML Kit • Eric Fung • Ohio DevFest 2018
49. The End ‣ Contact eric.fung@shopify.com • @gnufmuffin ‣ Work shopify.com/careers ‣ Blog code.gnufmuffin.com ‣ Slides speakerdeck.com/efung