gem "tensorflow"

a = Tf.constant([1, 2, 3]) b = Tf.constant([4, 5, 6]) a + b

v = Tf::Variable.new(0.0) w = v + 1

Tf::Math.abs([-1, -2]) Tf::Math.sqrt([1.0, 4.0, 9.0])

def fizzbuzz(max_num) max_num.times do |i| num = Tf.constant(i + 1) if (num % 3).to_i == 0 && (num % 5).to_i == 0 puts "FizzBuzz" elsif (num % 3).to_i == 0 puts "Fizz" elsif (num % 5).to_i == 0 puts "Buzz" else puts num.to_i end end end fizzbuzz(15)

# load train_dataset = Tf::Data::Dataset.from_tensor_slices([train_examples, train_labels]) test_dataset = Tf::Data::Dataset.from_tensor_slices([test_examples, test_labels]) # shuffle and batch train_dataset = train_dataset.shuffle(100).batch(32) test_dataset = test_dataset.batch(32) # iterate train_dataset.each do |examples, labels| # ... end

mnist = Tf::Keras::Datasets::MNIST (x_train, y_train), (x_test, y_test) = mnist.load_data x_train = x_train / 255.0 x_test = x_test / 255.0 model = Tf::Keras::Models::Sequential.new([ Tf::Keras::Layers::Flatten.new(input_shape: [28, 28]), Tf::Keras::Layers::Dense.new(128, activation: "relu"), Tf::Keras::Layers::Dropout.new(0.2), Tf::Keras::Layers::Dense.new(10, activation: "softmax") ]) model.compile(optimizer: "adam", loss: "sparse_categorical_crossentropy", metrics: ["accuracy"]) model.fit(x_train, y_train, epochs: 5) model.evaluate(x_test, y_test)