DNGR.py 文件源码

def model(data, hidden_layers, hidden_neurons, output_file, validation_split=0.9):


    train_n = int(validation_split * len(data))
    batch_size = 50
    train_data = data[:train_n,:]
    val_data = data[train_n:,:]

    input_sh = Input(shape=(data.shape[1],))
    encoded = noise.GaussianNoise(0.2)(input_sh)
    for i in range(hidden_layers):
        encoded = Dense(hidden_neurons[i], activation='relu')(encoded)
        encoded = noise.GaussianNoise(0.2)(encoded)

    decoded = Dense(hidden_neurons[-2], activation='relu')(encoded)
    for j in range(hidden_layers-3,-1,-1):
        decoded = Dense(hidden_neurons[j], activation='relu')(decoded)
    decoded = Dense(data.shape[1], activation='sigmoid')(decoded)

    autoencoder = Model(input=input_sh, output=decoded)
    autoencoder.compile(optimizer='adadelta', loss='mse')

    checkpointer = ModelCheckpoint(filepath='data/bestmodel' + output_file + ".hdf5", verbose=1, save_best_only=True)
    earlystopper = EarlyStopping(monitor='val_loss', patience=15, verbose=1)

    train_generator = DataGenerator(batch_size)
    train_generator.fit(train_data, train_data)
    val_generator = DataGenerator(batch_size)
    val_generator.fit(val_data, val_data)

    autoencoder.fit_generator(train_generator,
        samples_per_epoch=len(train_data),
        nb_epoch=100,
        validation_data=val_generator,
        nb_val_samples=len(val_data),
        max_q_size=batch_size,
        callbacks=[checkpointer, earlystopper])
    enco = Model(input=input_sh, output=encoded)
    enco.compile(optimizer='adadelta', loss='mse')
    reprsn = enco.predict(data)
    return reprsn