Last active
April 26, 2019 09:51
-
-
Save edunuke/4c8eb8b11065b3d78d0424371df79ed8 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from keras.layers import Input, Dense, BatchNormalization | |
| from keras.models import Model | |
| from keras.callbacks import EarlyStopping | |
| # set input layer | |
| inputs = Input(shape=(X_train.shape[1],), name='input') | |
| # normalized the batches | |
| x = BatchNormalization(name='input_bn')(inputs) | |
| # add the fully connected layers | |
| x = Dense(X_train.shape[1], activation='relu', name='first')(x) | |
| x = Dense(64, activation='relu',name='second')(x) | |
| x = Dense(X_train.shape[1], activation='elu',name='last')(x) | |
| # get the final result | |
| predictions = Dense(1, activation='relu', name='ouput')(x) | |
| # This creates a model that includes | |
| # the Input layer and three Dense layers | |
| model = Model(inputs=inputs, outputs=predictions) | |
| model.compile(optimizer='adam', | |
| loss='mape') | |
| model.fit(X_train, | |
| Y_train, | |
| epochs = 100, | |
| batch_size = 1000, | |
| validation_data = (X_test,Y_test), | |
| shuffle=True, | |
| callbacks=[EarlyStopping(monitor='val_loss', patience=1,)]) | |
| #let's get the training and validation histories for plotting | |
| val_loss = model.history.history['val_loss'] | |
| loss = model.history.history['loss'] | |
| print(model.summary()) | |
| # let's plot the performance curve | |
| import matplotlib.pyplot as plt | |
| plt.figure() | |
| plt.plot(val_loss, label='val_loss') | |
| plt.plot(loss, label = 'loss') | |
| plt.legend() | |
| plt.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment