Keras conv2d batchnorm

# import BatchNormalization
from keras.layers.normalization import BatchNormalization

# instantiate model
model = Sequential()

# we can think of this chunk as the input layer
model.add(Dense(64, input_dim=14, init='uniform'))
model.add(BatchNormalization())
model.add(Activation('tanh'))
model.add(Dropout(0.5))

# we can think of this chunk as the hidden layer    
model.add(Dense(64, init='uniform'))
model.add(BatchNormalization())
model.add(Activation('tanh'))
model.add(Dropout(0.5))

# we can think of this chunk as the output layer
model.add(Dense(2, init='uniform'))
model.add(BatchNormalization())
model.add(Activation('softmax'))

# setting up the optimization of our weights 
sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='binary_crossentropy', optimizer=sgd)

# running the fitting
model.fit(X_train, y_train, nb_epoch=20, batch_size=16, show_accuracy=True, validation_split=0.2, verbose = 2)

Source: stackoverflow.com

Similar codes

4 votes171 views2 answers
List(map(int input().split()))
Python
6 votes169 views4 answers
Calculate area of circle
Python
8 votes172 views3 answers
Subtract one list from another python
Python
0 vote167 views1 answer
From decimal to binary python without using any libraries
Python
0 vote166 views2 answers
For loop to while loop in python
Python
0 vote167 views1 answer
Pip install mod_wsgi error
Python
2 votes162 views1 answer
Python calculate time taken
Python
1 vote178 views1 answer
Using-len-for-text-but-discarding-spaces-in-the-count
Python
0 vote211 views1 answer
Generate 50 characters long for django
Python Django
0 vote172 views1 answer
Get path of notebook
Python