TensorFlow - La IA detrás de Google

Presentación para el Google Developer Group DevFest 2016 de Granada sobre "TensorFlow", la biblioteca de inteligencia artificial de Google

Transcript

1. +Israel Blancas @iblancasa TensorFlow La IA detrás de Google #DevFestGRX GDG Granada
2. How Can You Get Started with Machine Learning? Three ways, with varying complexity: (1) Use a Cloud-based or Mobile API (Vision, Natural Language, etc.) (2) Use an existing model architecture, and retrain it or fine tune on your dataset (3) Develop your own machine learning models for new problems More flexible, but more effort required #DevFestGRX GDG Granada
3. Cloud Machine Learning APIs See, Hear and Understand the world #DevFestGRX GDG Granada
4. Cloud Natural Language Cloud Speech Cloud Translate Cloud Vision #DevFestGRX GDG Granada
5. 5 5 Vision API https://cloud.google.com/vision/ #DevFestGRX GDG Granada
6. Faces Faces, facial landmarks, emotions OCR Read and extract text, with support for > 10 languages Label Detect entities from furniture to transportation Logos Identify product logos Landmarks & Image Properties Detect landmarks & dominant color of image Safe Search Detect explicit content - adult, violent, medical and spoof Cloud Vision API #DevFestGRX GDG Granada
7. API Usage: Detect Objects in an Image Image Detected Items Vision API Create JSON request with the image or pointer to an image Process the JSON response Call the REST API 1 2 3 #DevFestGRX GDG Granada
8. 8 8 Cloud Natural Language API https://cloud.google.com/natural-language/ #DevFestGRX GDG Granada
9. Confidential & Proprietary Google Cloud Platform 9 Cloud Natural Language API Extract sentence, identify parts of speech and create dependency parse trees for each sentence. Identify entities and label by types such as person, organization, location, events, products and media. Understand the overall sentiment of a block of text. Syntax Analysis Entity Recognition Sentiment Analysis #DevFestGRX GDG Granada
10. 10 10 Cloud Speech API Demo https://cloud.google.com/speech/ #DevFestGRX GDG Granada
11. Confidential & Proprietary Google Cloud Platform 11 Cloud Speech API Automatic Speech Recognition (ASR) powered by deep learning neural networking to power your applications like voice search or speech transcription. Recognizes over 80 languages and variants with an extensive vocabulary. Returns partial recognition results immediately, as they become available. Filter inappropriate content in text results. Audio input can be captured by an application’s microphone or sent from a pre-recorded audio file. Multiple audio file formats are supported, including FLAC, AMR, PCMU and linear-16. Handles noisy audio from many environments without requiring additional noise cancellation. Audio files can be uploaded in the request and, in future releases, integrated with Google Cloud Storage. Automatic Speech Recognition Global Vocabulary Inappropriate Content Filtering Streaming Recognition Real-time or Buffered Audio Support Noisy Audio Handling Integrated API #DevFestGRX GDG Granada
12. Mobile Vision API Providing on-device vision for applications #DevFestGRX GDG Granada
13. Face API faces, facial landmarks, eyes open, smiling Barcode API 1D and 2D barcodes Text API Latin-based text / structure Common Mobile Vision API Support for fast image and video on-device detection and tracking. #DevFestGRX GDG Granada
14. Googly Eyes Android App Video credit Google 1. Create a face detector for facial landmarks (e.g., eyes) 3. For each face, draw the eyes FaceDetector detector = new FaceDetector.Builder() .setLandmarkType(FaceDetector.ALL_LANDMARKS) .build(); SparseArray<Face> faces = detector.detect(image); for (int i = 0; i < faces.size(); ++i) { Face face = faces.valueAt(i); for (Landmark landmark : face.getLandmarks()) { // Draw eyes 2. Detect faces in the image #DevFestGRX GDG Granada
15. Face API Photo credit developers.google.com/vision #DevFestGRX GDG Granada
16. Easy to use Java API image detected items Detector 1. Create a detector object 2. detectedItems = detector.detect(image) Photo credit developers.google.com/vision #DevFestGRX GDG Granada
17. Text Detection Latin based language Understand text structure Photo credit Getty Images #DevFestGRX GDG Granada
18. Text Structure Blocks Lines Words Lines Words Words Words #DevFestGRX GDG Granada
19. Barcode Detection 1D barcodes EAN-13/8 UPC-A/E Code-39/93/128 ITF Codabar 2D barcodes QR Code Data Matrix PDF-417 AZTEC UPC DataMatrix QR Code PDF 417 Video and image credit Google #DevFestGRX GDG Granada
20. Combined Vision & Translation #DevFestGRX GDG Granada
21. • Open source Machine Learning library • Especially useful for Deep Learning • For research and production • Apache 2.0 license #DevFestGRX GDG Granada
22. Architecture • Core in C++ • Different front ends ◦ Python and C++ today, community may add more Core TensorFlow Execution System CPU GPU Android iOS ... C++ front end Python front end ... #DevFestGRX GDG Granada
23. Raspberry Pi Datacenters Your laptop Android iOS Portable & Scalable #DevFestGRX GDG Granada
24. /Serving Open-source solution for serving trained models #DevFestGRX GDG Granada
25. From the whitepaper: “TensorFlow is an interface for expressing machine learning algorithms, and an implementation for executing such algorithms.” In short: TensorFlow is Theano++. • Symbolic ML dataflow framework that compiles to native / GPU code What is TensorFlow? #DevFestGRX GDG Granada
26. Data Flow Graphs Computation is defined as a directed acyclic graph (DAG) to optimize an objective function • Graph is defined in high-level language (Python) • Graph is compiled and optimized • Graph is executed (in parts or fully) on available low level devices (CPU, GPU) • Data (tensors) flow through the graph • TensorFlow can compute gradients automatically #DevFestGRX GDG Granada
27. Graph? #DevFestGRX GDG Granada
28. Variables are 0-ary stateful nodes which output their current value. (State is retained across multiple executions of a graph.) (parameters, gradient stores, eligibility traces, …) Graph? #DevFestGRX GDG Granada
29. Placeholders are 0-ary nodes whose value is fed in at execution time. (inputs, variable learning rates, …) Graph? #DevFestGRX GDG Granada
30. Mathematical operations: MatMul: Multiply two matrix values. Add: Add elementwise (with broadcasting). ReLU: Activate with elementwise rectified linear function. Graph? #DevFestGRX GDG Granada
31. In code, please! 1. Create model weights, including initialization a. W ~ Uniform(-1, 1); b = 0 2. Create input placeholder x a. m * 784 input matrix 3. Create computation graph import tensorflow as tf b = tf.Variable(tf.zeros((100,))) W = tf.Variable(tf.random_uniform((784, 100), -1, 1)) x = tf.placeholder(tf.float32, (None, 784)) h_i = tf.nn.relu(tf.matmul(x, W) + b) 1 2 3 #DevFestGRX GDG Granada
32. So far we have defined a graph. We can deploy this graph with a session: a binding to a particular execution context (e.g. CPU, GPU) How do we run it? #DevFestGRX GDG Granada
33. Getting output sess.run(fetches, feeds) Fetches: List of graph nodes. Return the outputs of these nodes. Feeds: Dictionary mapping from graph nodes to concrete values. Specifies the value of each graph node given in the dictionary. import numpy as np import tensorflow as tf b = tf.Variable(tf.zeros((100,))) W = tf.Variable(tf.random_uniform((784, 100),-1, 1)) x = tf.placeholder(tf.float32, (None, 784)) h_i = tf.nn.relu(tf.matmul(x, W) + b) 1 2 3 sess = tf.Session() sess.run(tf.initialize_all_variables()) sess.run(h_i, {x: np.random.random(64, 784)}) #DevFestGRX GDG Granada
34. 1. Build a graph a. Graph contains parameter specifications, model architecture, optimization process, … 2. Initialize a session 3. Fetch and feed data with Session.run a. Compilation, optimization, etc. happens at this step — you probably won’t notice Basic flow #DevFestGRX GDG Granada
35. Questions? #DevFestGRX GDG Granada
36. tensorflow.org github.com/tensorflow Want to learn more? Udacity class on Deep Learning, goo.gl/iHssII Guides, codelabs, videos MNIST for Beginners, goo.gl/tx8R2b TF Learn Quickstart, goo.gl/uiefRn TensorFlow for Poets, goo.gl/bVjFIL ML Recipes, goo.gl/KewA03 TensorFlow and Deep Learning without a PhD, goo.gl/pHeXe7 What's Next #DevFestGRX GDG Granada
37. +Israel Blancas @iblancasa TensorFlow La IA detrás de Google #DevFestGRX GDG Granada