init_W=init_W,
init_b=init_b)
c2 = ConvertLayer(name='c2',
parent=['h3'],
outshape=(batch_size, 128))
# Global average pooling missing
h4 = FullyConnectedLayer(name='h4',
parent=['c2'],
nout=10,
unit='softmax',
init_W=init_W,
init_b=init_b)
cost = MulCrossEntropyLayer(name='cost', parent=['y', 'h4'])
# You will fill in a list of nodes and fed them to the model constructor
nodes = [c1, c2, h1, h2, h3, h4, cost]
# Your model will build the Theano computational graph
cnn = Net(inputs=inputs, inputs_dim=inputs_dim, nodes=nodes)
cnn.build_graph()
# You can access any output of a node by doing model.nodes[$node_name].out
cost = cnn.nodes['cost'].out
err = error(predict(cnn.nodes['h4'].out), predict(y))
cost.name = 'cost'
err.name = 'error_rate'
model.graphs = [cnn]
outshape=(batch_size, 128, 1, 1),
unit='relu',
init_W=init_W,
init_b=init_b)
c2 = ConvertLayer(name='c2', parent=['h3'], outshape=(batch_size, 128))
# Global average pooling missing
h4 = FullyConnectedLayer(name='h4',
parent=['c2'],
nout=10,
unit='softmax',
init_W=init_W,
init_b=init_b)
cost = MulCrossEntropyLayer(name='cost', parent=['y', 'h4'])
# You will fill in a list of nodes and fed them to the model constructor
nodes = [c1, c2, h1, h2, h3, h4, cost]
# Your model will build the Theano computational graph
cnn = Net(inputs=inputs, inputs_dim=inputs_dim, nodes=nodes)
cnn.build_graph()
# You can access any output of a node by doing model.nodes[$node_name].out
cost = cnn.nodes['cost'].out
err = error(predict(cnn.nodes['h4'].out), predict(y))
cost.name = 'cost'
err.name = 'error_rate'
model.graphs = [cnn]