Introduction to Convolutional Neural Networks
3 likes5,084 views
This document provides an introduction to machine learning using convolutional neural networks (CNNs) for image classification. It discusses how to prepare image data, build and train a simple CNN model using Keras, and optimize training using GPUs. The document outlines steps to normalize image sizes, convert images to matrices, save data formats, assemble a CNN in Keras including layers, compilation, and fitting. It provides resources for learning more about CNNs and deep learning frameworks like Keras and TensorFlow.
![Theano
• Created by the
University of Montreal
• Framework for
symbolic computation
• Provides GPU support
• Great Python libraries based on Theano:
Keras, Lasagne, PyLearn2
import numpy
import theano.tensor as T
x = T.dmatrix('x')
y = T.dmatrix('y')
z = x + y
f = function([x, y], z)](https://image.slidesharecdn.com/opensourcebridge-machinelearning101-160624030201/85/Introduction-to-Convolutional-Neural-Networks-13-320.jpg)
![Set the “compile”
parameters
• Keras provides various options for optimizing
your network
• SGD
• Adagrad
• Adadelta
• Etc.
• Set the learning rate, momentum, etc.
• Define your loss definition and metrics
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(
loss=‘categorical_crossentropy',
optimizer=sgd, metrics=['accuracy'])](https://image.slidesharecdn.com/opensourcebridge-machinelearning101-160624030201/85/Introduction-to-Convolutional-Neural-Networks-24-320.jpg)
Introduction to Convolutional Neural Networks
- 1. Machine Learning 101 Teach your computer the difference between cats and dogs Cole Howard & Hannes Hapke Open Source Bridge, June 23rd, 2016
- 2. Who are we? John Howard @uglyboxer Senior Developer at Dark Horse Comics Master of recommendation systems, convolutional neural networks Hannes Hapke @hanneshapke Senior Developer at CrowdStreet Excited about neural networks applications
- 3. We want to show you how you can train a computer to “recognize” images * * aka to decide between cats and dogs What is this all about ...
- 4. Convolutional Nets are good at determining ... • The spatial relationship of data • And therefore detecting determining patterns Are these dogs?
- 5. Convolutional Neural Nets are heavily used by For detecting patterns in images, videos, sounds and texts • Music recommendation at Spotify (http://benanne.github.io/2014/08/05/spotify-cnns.html) • Google’s PlaNet—Photo Geolocation with CNN (http://arxiv.org/abs/1602.05314) • Who else is using CNNs? (https://www.quora.com/Apart-from-Google-Facebook-who-is-commercially-using-deep-recurrent-convolutional- neural-networks)
- 6. What are conv nets? • In traditional feed-forward networks, we are learning weights to apply to the data • In conv-nets, we are learning to describe filters • After each convolutional layer we still have an “image” • Instead of 3 channels (r-g-b), we have n - channels. Each described by one of the learned filters
- 8. Filters (or Kernels) Example of Edge Detector Example of Blurring Filter
- 9. Pooling • Can condense information as filters pull details apart • With MaxPooling we take the local maximum activation as representative of the region. Usually a 2x2 subsample • As we filter, precise location becomes less relevant • This condenses the amount of information by ¼ per learned channel • BONUS: Net becomes tolerant to local perturbations in the data
- 10. Traditional Feed-Forward Icing on the Cake • Flatten the filtered image into one long 1 dimensional vector • Pass into a feed forward network • Out to classes -> to determine error • Learn like normal - backpropagation works on filter weights, just as it does on neuron weights
- 13. Theano • Created by the University of Montreal • Framework for symbolic computation • Provides GPU support • Great Python libraries based on Theano: Keras, Lasagne, PyLearn2 import numpy import theano.tensor as T x = T.dmatrix('x') y = T.dmatrix('y') z = x + y f = function([x, y], z)
- 14. TensorFlow • Developed by a small startup in Moutainview • Used for 50 Google products • Used as part of AlphaGo (trained on TPUs*) • Designed for distributed learning problems • Growing ecosystem: TensorBoard, tflearn, scikit-flow import tensorflow as tf a = tf.placeholder("float") b = tf.placeholder("float") y = tf.mul(a, b) # multiply the symbolic variables with tf.Session() as sess: print("%f should equal 2.0" % sess.run(y, feed_dict={a: 1, b: 2})) print("%f should equal 9.0" % sess.run(y, feed_dict={a: 3, b: 3}))
- 15. How to prepare your images for the classification?
- 16. Normalize the image size • Use the pillow package in Python • For small size differences, squeeze images • For larger differences, resize images • Or use Keras’ pre-processing functions y, x = image.size y = x if x > y else y resized_image = Image.new(color_schema, (y, y), (255, )) try: resized_image.paste(image, image.getbbox()) except ValueError: continue resized_image = resized_image.resize( (resized_px, resized_px), Image.ANTIALIAS) resized_image.save(new_filename, 'jpeg', quality=90)
- 17. Convert the images into matrices • Use the numpy package in Python • No magic, use numpy’s asarray method • Create a classification vector at the same time image = Image.open(directory + f) image.load() image_matrix = np.asarray(image, dtype="int32").T image_classification = 1 if animal == 'Cat/' else 0 data.append(image_matrix) classification.append(image_classification)
- 18. Save the matrices in a reusable format • Pickle or numpy is your best friend • You can split the dataset into training/test set with `train_test_split` • Store matrices as compressed pickles (use numpy for large arrays) • Use compression! X_train, X_test, y_train, y_test = train_test_split( data, classification, test_size=0.20, random_state=42) np.savez_compressed('petsTrainingData.npz', X_train=X_train, X_test=X_test, y_train=y_train, y_test=y_test)
- 19. How to assemble a simple CNN with Keras
- 20. What is Keras? Why? • Excellent Python wrapper library for Theano • Supports TensorFlow too! • Growing TensorFlow support • Amazing documentation • Amazing community
- 21. Steps 1. Setup your sequential model 2. Create a network structure 3. Set the “compile” parameters 4. Set the fit parameters
- 22. Setup a sequential model • Sequential models allow you to define the network structure • Use model.add() to add layers to the neural network Model = Sequential() model.add(Convolution2D(64, 2, 2, border_mode='same'))
- 23. Create your network structure • Keras provides various types of layers • Convolution2D • Convolution3D • Dense • Dropout • Activation • MaxPooling2D • etc. model.add(Convolution2D(64, 2, 2)) model.add(Activation(‘relu’)) model.add(MaxPooling2D(pool_size=(2, 2)))
- 24. Set the “compile” parameters • Keras provides various options for optimizing your network • SGD • Adagrad • Adadelta • Etc. • Set the learning rate, momentum, etc. • Define your loss definition and metrics sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True) model.compile( loss=‘categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
- 25. Set the fit parameters • This is where the magic starts! • model.fit() allows you to define: • The batch size • Number of epochs • Whether you want to shuffle your training data • Your validation set • Your callbacks • Callbacks are amazing!
- 26. Use Callbacks • Keras comes with various callbacks • ModelCheckpoint allows saving the model parameters after every/best run • EarlyStopping allows stopping the training if your training condition is met • Other callbacks: • LearningRateScheduler • TensorBoard • RemoteMonitor
- 27. Faster, Faster … • GPU’s are your friends • Unlike traditional feed-forward nets, there are large parts of CNN’s that are parallel-izable! • As each neuron normally depends on the neuron before it and the error reported from the neuron after it, filters are different. • In a layer, each filter and each filter at each position are independent of each other. • So all of those computations can happen simultaneously. • And as all are simple matrix multiplications, we can make use of the 1000’s of cores on modern GPU’s
- 28. Running on a GPU • Install proper dependencies (linux requires a few extra steps here) • Install Theano, Keras • Install CUDA (http://tleyden.github.io/blog/2015/11/22/cuda-7- dot-5-on-aws-gpu-instance-running-ubuntu-14-dot-04/) • Install cuDNN (requires registration with NVIDIA) • Configurations in ~/.theanorc • Set Theano Flags when running script (or in .theanorc) • Pre-configured AMI on AWS (ami-a6ec17c6 in region US-west-2/Oregon)
- 29. How does a training look like in action?
- 31. What to do once the training is completed?
- 33. Learning resources ConvNets • http://cs231n.stanford.edu/ • https://www.youtube.com/watch?v=bEUX_56Lojc • http://blog.keras.io/how-convolutional-neural-networks- see-the-world.html Keras • https://www.youtube.com/watch?v=Tp3SaRbql4k TensorFlow • http://learningtensorflow.com/examples/