border_mode=border_mode,
name='conv_{}'.format(i))
for i, (filter_size, num_filter)
in enumerate(zip(filter_sizes, num_filters))),
conv_activations,
(MaxPooling(pooling_sizes, name='pool_{}'.format(i))
for i, size in enumerate(pooling_sizes))]))
convnet = ConvolutionalSequence(conv_layers, num_channels=3,
image_size=(32, 32),
weights_init=Uniform(0, 0.2),
biases_init=Constant(0.))
convnet.push_initialization_config()
convnet.initialize()
conv_features = Flattener().apply(convnet.apply(X))
# MLP
mlp = MLP(activations=[Logistic(name='sigmoid_0'),
Softmax(name='softmax_1')], dims=[256, 256, 256, 2],
weights_init=IsotropicGaussian(0.01), biases_init=Constant(0))
[child.name for child in mlp.children]
['linear_0', 'sigmoid_0', 'linear_1', 'softmax_1']
Y = mlp.apply(conv_features)
mlp.initialize()
border_mode=border_mode,
name='conv_{}'.format(i))
for i, (filter_size,
num_filter) in enumerate(zip(filter_sizes, num_filters))),
conv_activations,
(MaxPooling(pooling_sizes, name='pool_{}'.format(i))
for i, size in enumerate(pooling_sizes))
]))
convnet = ConvolutionalSequence(conv_layers,
num_channels=3,
image_size=(32, 32),
weights_init=Uniform(0, 0.2),
biases_init=Constant(0.))
convnet.push_initialization_config()
convnet.initialize()
conv_features = Flattener().apply(convnet.apply(X))
# MLP
mlp = MLP(activations=[Logistic(name='sigmoid_0'),
Softmax(name='softmax_1')],
dims=[256, 256, 256, 2],
weights_init=IsotropicGaussian(0.01),
biases_init=Constant(0))
[child.name for child in mlp.children]
['linear_0', 'sigmoid_0', 'linear_1', 'softmax_1']
Y = mlp.apply(conv_features)
mlp.initialize()
