(Conv2DLayer, {'num_filters': 32, 'filter_size': (3, 3), 'pad': 1}),
(Conv2DLayer, {'num_filters': 32, 'filter_size': (3, 3), 'pad': 1}),
(MaxPool2DLayer, {'pool_size': (2, 2)}),
(Conv2DLayer, {'num_filters': 64, 'filter_size': (3, 3), 'pad': 1}),
(Conv2DLayer, {'num_filters': 64, 'filter_size': (3, 3), 'pad': 1}),
(Conv2DLayer, {'num_filters': 64, 'filter_size': (3, 3), 'pad': 1}),
(MaxPool2DLayer, {'pool_size': (2, 2)}),
(DenseLayer, {'num_units': 64}),
(DropoutLayer, {}),
(DenseLayer, {'num_units': 64}),
(DenseLayer, {'num_units': 10, 'nonlinearity': softmax}),
]
net4 = NeuralNet(
layers=layers4,
update_learning_rate=0.01,
verbose=2,
)
net4.initialize()
layer_info(net4)
# get more information by increasing the verbosity level beyond 2.
net4.verbose = 3
layer_info(net4)
# http://nbviewer.jupyter.org/github/dnouri/nolearn/blob/master/docs/notebooks/CNN_tutorial.ipynb
