Contents

require "dnn"
require "dnn/datasets/mnist"
# If you use numo/linalg then please uncomment out.
# require "numo/linalg/autoloader"

include DNN::Models
include DNN::Layers
include DNN::Optimizers
include DNN::Losses

x_train, y_train = DNN::MNIST.load_train
x_test, y_test = DNN::MNIST.load_test

x_train = Numo::SFloat.cast(x_train) / 255
x_test = Numo::SFloat.cast(x_test) / 255

y_train = DNN::Utils.to_categorical(y_train, 10, Numo::SFloat)
y_test = DNN::Utils.to_categorical(y_test, 10, Numo::SFloat)

model = Sequential.new

model << InputLayer.new([28, 28, 1])

model << Conv2D.new(16, 5)
model << BatchNormalization.new
model << ReLU.new

model << MaxPool2D.new(2)

model << Conv2D.new(32, 5)
model << BatchNormalization.new
model << ReLU.new

model << Flatten.new

model << Dense.new(256)
model << BatchNormalization.new
model << ReLU.new
model << Dropout.new(0.5)

model << Dense.new(10)

model.setup(Adam.new, SoftmaxCrossEntropy.new)

model.train(x_train, y_train, 10, batch_size: 100, test: [x_test, y_test])

accuracy, loss = model.evaluate(x_test, y_test)
puts "accuracy: #{accuracy}"
puts "loss: #{loss}"

Version data entries

13 entries across 13 versions & 1 rubygems

Version	Path
ruby-dnn-1.1.6	examples/mnist_conv2d_example.rb
ruby-dnn-1.1.5	examples/mnist_conv2d_example.rb
ruby-dnn-1.1.4	examples/mnist_conv2d_example.rb
ruby-dnn-1.1.3	examples/mnist_conv2d_example.rb
ruby-dnn-1.1.2	examples/mnist_conv2d_example.rb
ruby-dnn-1.1.1	examples/mnist_conv2d_example.rb
ruby-dnn-1.1.0	examples/mnist_conv2d_example.rb
ruby-dnn-1.0.0	examples/mnist_conv2d_example.rb
ruby-dnn-0.16.2	examples/mnist_conv2d_example.rb
ruby-dnn-0.16.1	examples/mnist_conv2d_example.rb
ruby-dnn-0.16.0	examples/mnist_conv2d_example.rb
ruby-dnn-0.15.3	examples/mnist_conv2d_example.rb
ruby-dnn-0.15.2	examples/mnist_conv2d_example.rb