Merge pull request maxpumperla#196 from amw5g/patch-1

Create simple_notebook_multiple_inputs.ipynb

examples/simple_notebook_multiple_inputs.ipynb

@@ -0,0 +1,77 @@
+from __future__ import print_function
+from hyperopt import Trials, STATUS_OK, tpe
+from hyperas import optim
+from hyperas.distributions import choice, uniform
+
+from keras.models import Model
+from keras.layers import Input, Dense, Dropout, concatenate, Activation
+from keras.optimizers import RMSprop
+
+from keras.datasets import mnist
+from keras.utils import np_utils
+import numpy
+
+def data():
+    '''
+    Data providing function:
+    This function is separated from model() so that hyperopt
+    won't reload data for each evaluation run.
+    '''
+    (mnist_X_train, y_train), (mnist_X_test, y_test) = mnist.load_data()
+    mnist_X_train = mnist_X_train.reshape(60000, 784)
+    mnist_X_test = mnist_X_test.reshape(10000, 784)
+    mnist_X_train = mnist_X_train.astype('float32')
+    mnist_X_test = mnist_X_test.astype('float32')
+    mnist_X_train /= 255
+    mnist_X_test /= 255
+    nb_classes = 10
+    Y_train = np_utils.to_categorical(y_train, nb_classes)
+    Y_test = np_utils.to_categorical(y_test, nb_classes)
+    X_train = {'x1': mnist_X_train, 'x2': numpy.flip(mnist_X_train, axis=1)}
+    X_test = {'x1': mnist_X_test, 'x2': numpy.flip(mnist_X_test, axis=1)}
+    return X_train, Y_train, X_test, Y_test
+
+
+def model(X_train, Y_train, X_test, Y_test):
+    '''
+    Model providing function:
+    Create Keras model with double curly brackets dropped-in as needed.
+    Return value has to be a valid python dictionary with two customary keys:
+        - loss: Specify a numeric evaluation metric to be minimized
+        - status: Just use STATUS_OK and see hyperopt documentation if not feasible
+    The last one is optional, though recommended, namely:
+        - model: specify the model just created so that we can later use it again.
+    '''
+    x1 = Input(shape=(784,),  name='x1')
+    dense_x1 = Dense(512)(x1)
+    x2 = Input(shape=(784,),  name='x2')
+    dense_x2 = Dense(512)(x2)  
+    merged = concatenate([dense_x1, dense_x2])
+    merged = Activation('relu')(merged)
+    merged = Dropout({{uniform(0, 1)}})(merged)
+    merged = Dense({{choice([256, 512, 1024])}}, activation='relu')(merged)
+    merged = Dropout({{uniform(0, 1)}})(merged)
+    output = Dense(10, activation='softmax', name='output')(merged)
+    model = Model(inputs=[x1, x2], outputs=[output])
+
+    rms = RMSprop()
+    model.compile(loss='categorical_crossentropy', optimizer=rms, metrics=['accuracy'])
+
+    model.fit({'x1': X_train['x1'], 'x2': X_train['x2']}, {'output': Y_train},
+              batch_size={{choice([64, 128])}},
+              epochs=1,
+              verbose=2,
+              validation_data=({'x1': X_test['x1'], 'x2': X_test['x2']}, {'output': Y_test}))
+    score, acc = model.evaluate({'x1': X_test['x1'], 'x2': X_test['x2']}, {'output': Y_test}, verbose=0)
+    print('Test accuracy:', acc)
+    return {'loss': -acc, 'status': STATUS_OK, 'model': model}
+
+
+X_train, Y_train, X_test, Y_test = data()
+
+best_run, best_model = optim.minimize(model=model,
+                                      data=data,
+                                      algo=tpe.suggest,
+                                      max_evals=5,
+                                      trials=Trials(),
+                                      notebook_name='simple_notebook')