Image Recognition Using Deep Learning

Deep learning can be applied to many image processing and computer vision problems with great success. Using NetChain and NetTrain, you can define and train a neural network that categorizes a handwritten digit given an image.

Obtain training and validation data from the MNIST database of handwritten digits.

In[1]:=

resource = ResourceObject["MNIST"]; trainingData = ResourceData[resource, "TrainingData"]; testData = ResourceData[resource, "TestData"];

In[2]:=

RandomSample[trainingData, 5]

Out[2]=

Design a convolutional neural network architected for recognizing 28×28 grayscale images.

In[3]:=

lenet = NetChain[ {ConvolutionLayer[20, 5], Ramp, PoolingLayer[2, 2], ConvolutionLayer[50, 5], Ramp, PoolingLayer[2, 2], FlattenLayer[], 500, Ramp, 10, SoftmaxLayer[]}, "Output" -> NetDecoder[{"Class", Range[0, 9]}], "Input" -> NetEncoder[{"Image", {28, 28}, "Grayscale"}] ]

Out[3]=

Train the network for three training rounds.

In[4]:=

lenet = NetTrain[lenet, trainingData, ValidationSet -> testData, MaxTrainingRounds -> 3];

Out[4]=

Evaluate the trained network directly on images randomly sampled from the validation set.

In[5]:=

imgs = Keys @ RandomSample[testData, 5]; Thread[imgs -> lenet[imgs]]

Out[5]=