Fashion-MNIST

Description

Fashion-MNIST is a dataset of Zalando’s article images—consisting of a training set of 60,000 examples and a test set of 10,000 examples. Each example is a 28x28 grayscale image, associated with a label from 10 classes. We intend Fashion-MNIST to serve as a direct drop-in replacement for the original MNIST dataset for benchmarking machine learning algorithms.

See more details

Neural network

This is the test with the neural network architecture used to obtain up to 88.13% accuracy on this dataset. To reach this accuracy you may need more attempts and more learning time.

TEST_F(FashionMnistTest, convolutionalNeuralNetwork)
{
    StraightforwardNeuralNetwork neuralNetwork({
        Input(28, 28, 1),
        Convolution(1, 5),
        FullyConnected(70),
        FullyConnected(10)
        });
    neuralNetwork.train(*data, 1_ep || 45_s);
    auto accuracy = neuralNetwork.getGlobalClusteringRate();
    ASSERT_ACCURACY(accuracy, 0.75);
}

See the code