def evaluate(rnn, testing_data, classes):
    confusion = torch.zeros(len(classes), len(classes))

    rnn.eval() #set to eval mode
    with torch.no_grad(): # do not record the gradients during eval phase
        for i in range(len(testing_data)):
            (label_tensor, text_tensor, label, text) = testing_data[i]
            output = rnn(text_tensor)
            guess, guess_i = label_from_output(output, classes)
            label_i = classes.index(label)
            confusion[label_i][guess_i] += 1

    # Normalize by dividing every row by its sum
    for i in range(len(classes)):
        denom = confusion[i].sum()
        if denom > 0:
            confusion[i] = confusion[i] / denom

    # Set up plot
    fig = plt.figure()
    ax = fig.add_subplot(111)
    cax = ax.matshow(confusion.cpu().numpy()) #numpy uses cpu here so we need to use a cpu version
    fig.colorbar(cax)

    # Set up axes
    ax.set_xticks(np.arange(len(classes)), labels=classes, rotation=90)
    ax.set_yticks(np.arange(len(classes)), labels=classes)

    # Force label at every tick
    ax.xaxis.set_major_locator(ticker.MultipleLocator(1))
    ax.yaxis.set_major_locator(ticker.MultipleLocator(1))

    # sphinx_gallery_thumbnail_number = 2
    plt.show()



evaluate(rnn, test_set, classes=alldata.labels_uniq)