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

0 vote151 views1 answer
Fatal Python error: init_interp_main: can't initialize time
Python
0 vote152 views1 answer
How to perform a two-way anova with python
Python
0 vote145 views1 answer
Python create a lsit
Python
0 vote167 views1 answer
Form is undefined flask
Python
17 votes160 views4 answers
How to get int input in python
Python
1 vote182 views3 answers
Remove brackets from string python
Python
0 vote225 views1 answer
Send arrays over POST by Python requests library
Python
5 votes155 views5 answers
How to take space separated input in python
Python
0 vote158 views1 answer
Fast input python
Python
0 vote156 views1 answer
Use a callable instead, e.g., use `dict` instead of `{}`
Python