Keras

Keras is a neural network library, popular for its high level API, thus being extremely user friendly. It was developed by François Chollet, who later joined Google. Keras was then merged with Tensorflow's library.

Metric Plots

The model compiled has a history method (model.history.history) that gives the accuracy and loss for both train & test sets for each time step. We can plot it out for a better visualization. Alternatively we can also use TensorBoard, which is installed together with TensorFlow package. It will also draw the model architecture.

def plot_validate(model, loss_acc):
    '''Plot model accuracy or loss for both train and test validation per epoch
    model = fitted model
    loss_acc = input 'loss' or 'acc' to plot respective graph
    '''
    history = model.history.history

    if loss_acc == 'loss':
        axis_title = 'loss'
        title = 'Loss'
        epoch = len(history['loss'])
    elif loss_acc == 'acc':
        axis_title = 'acc'
        title = 'Accuracy'
        epoch = len(history['loss'])

    plt.figure(figsize=(15,4))
    plt.plot(history[axis_title])
    plt.plot(history['val_' + axis_title])
    plt.title('Model ' + title)
    plt.ylabel(title)
    plt.xlabel('Epoch')

    plt.grid(b=True, which='major')
    plt.minorticks_on()
    plt.grid(b=True, which='minor', alpha=0.2)

    plt.legend(['Train', 'Test'])
    plt.show()


plot_validate(model, 'acc')
plot_validate(model, 'loss')