X,
Z,
hidden_transfers=['tanh', 'tanh'],
out_transfer='identity',
loss='squared',
optimizer=optimizer,
batch_size=batch_size,
max_iter=max_iter)
elif typ == 'fd':
m = FastDropoutNetwork(2099, [800, 800],
14,
X,
Z,
TX,
TZ,
hidden_transfers=['tanh', 'tanh'],
out_transfer='identity',
loss='squared',
p_dropout_inpt=.1,
p_dropout_hiddens=.2,
optimizer=optimizer,
batch_size=batch_size,
max_iter=max_iter)
#climin.initialize.randomize_normal(m.parameters.data, 0, 1 / np.sqrt(m.n_inpt))
m.init_weights()
#Transform the test data
#TX = m.transformedData(TX)
TX = np.array([TX for _ in range(10)]).mean(axis=0)
print TX.shape
1,
X,
Z,
hidden_transfers=['tanh', 'tanh'],
out_transfer='identity',
loss='squared',
optimizer=optimizer,
batch_size=batch_size,
max_iter=max_iter)
elif typ == 'fd':
m = FastDropoutNetwork(X.shape[1], [100, 100],
1,
X,
Z,
hidden_transfers=['tanh', 'tanh'],
out_transfer='identity',
loss='squared',
p_dropout_inpt=.1,
p_dropout_hiddens=.2,
optimizer=optimizer,
batch_size=batch_size,
max_iter=max_iter)
#climin.initialize.randomize_normal(m.parameters.data, 0, 1 / np.sqrt(m.n_inpt))
m.init_weights()
#Transform the test data
#TX = m.transformedData(TX)
TX = np.array([TX for _ in range(10)]).mean(axis=0)
print TX.shape
losses = []