def feature_re_extract():
#pdb.set_trace()
test_class = ['FAML_S', 'FDHH_S', 'FEAB_S', 'FHRO_S',
'FJAZ_S', 'FMEL_S', 'FMEV_S', 'FSLJ_S', 'FTEJ_S',
'FUAN_S', 'MASM_S', 'MCBR_S', 'MFKC_S', 'MKBP_S',
'MLKH_S', 'MMLP_S', 'MMNA_S', 'MNHP_S', 'MOEW_S',
'MPRA_S', 'MREM_S', 'MTLS_S']
m = ModelInterface.load('model/model.out')
# construct train set
train_set = []
for c in test_class:
for i in m.features[c]:
train_set.append(i)
# construct autoencoder
train_data = T.dmatrix('train_data')
x = T.dmatrix('x') # the data is presented as rasterized images
rng = numpy.random.RandomState(123)
theano_rng = RandomStreams(rng.randint(2 ** 10))
da = dA(
numpy_rng=rng,
theano_rng=theano_rng,
input=x,
n_visible=39,
n_hidden=100
)
cost, updates = da.get_cost_updates(
corruption_level=0.,
learning_rate=0.4
)
train_da = theano.function(
[train_data],
cost,
updates=updates,
givens={
x: train_data
}
)
# train autoencoder
training_epochs = 100
c1 = []
for epoch in xrange(training_epochs):
c1.append(train_da(numpy.asarray(train_set)))
print 'Training epoch %d, cost ' % epoch, c1[len(c1)-1]
for c in test_class:
m.features[c] = da.get_hidden_values(m.features[c]).eval()
m.train()
m.dump('model/model_da.out')
with open('model/da.out', 'w') as f:
pickle.dump(da, f, -1)
def train(self, train_set, batch_size=100):
for i in xrange(len(self.layers) - 1):
train_data = T.dmatrix("train_data")
x = T.dmatrix("x")
rng = numpy.random.RandomState(123)
theano_rng = RandomStreams(rng.randint(2 ** 10))
da = dA(
numpy_rng=rng, theano_rng=theano_rng, input=x, n_visible=self.layers[i], n_hidden=self.layers[i + 1]
)
cost, updates = da.get_cost_updates(corruption_level=0.0, learning_rate=0.4)
train_da = theano.function([train_data], cost, updates=updates, givens={x: train_data})
for epoch in xrange(20):
train_cost = []
for index in xrange(len(train_set) / batch_size):
train_cost.append(train_da(numpy.asarray(train_set[index * batch_size : (index + 1) * batch_size])))
print "Training 1st ae epoch %d, cost " % epoch, numpy.mean(train_cost)
train_set = da.get_hidden_values(train_set).eval()
self.dAs.append(da)
def feature_re_extract():
#pdb.set_trace()
test_class = ['FAML_S', 'FDHH_S', 'FEAB_S', 'FHRO_S',
'FJAZ_S', 'FMEL_S', 'FMEV_S', 'FSLJ_S', 'FTEJ_S',
'FUAN_S', 'MASM_S', 'MCBR_S', 'MFKC_S', 'MKBP_S',
'MLKH_S', 'MMLP_S', 'MMNA_S', 'MNHP_S', 'MOEW_S',
'MPRA_S', 'MREM_S', 'MTLS_S']
m = ModelInterface.load('model/model.out')
# construct train set
train_set = []
up_bound = []
lower_bound = []
for c in test_class:
for i in m.features[c]:
train_set.append(i)
'''
# put all values into -1~1
up_bound = []
lower_bound = []
for j in xrange(len(train_set[0])):
up_bound.append(train_set[0][j])
lower_bound.append(train_set[0][j])
for i in xrange(len(train_set)):
for j in xrange(len(train_set[0])):
up_bound[j] = max(up_bound[j], train_set[i][j])
lower_bound[j] = min(lower_bound[j], train_set[i][j])
for i in xrange(len(train_set)):
for j in xrange(len(train_set[0])):
train_set[i][j] = 2*((train_set[i][j]-lower_bound[j]) / (up_bound[j]-lower_bound[j]))-1
'''
# construct autoencoder
train_data = T.dmatrix('train_data')
x = T.dmatrix('x') # the data is presented as rasterized images
rng = numpy.random.RandomState(123)
theano_rng = RandomStreams(rng.randint(2 ** 10))
da = dA(
numpy_rng=rng,
theano_rng=theano_rng,
input=x,
n_visible=39,
n_hidden=30
)
cost, updates = da.get_cost_updates(
corruption_level=0.,
learning_rate=0.4
)
train_da = theano.function(
[train_data],
cost,
updates=updates,
givens={
x: train_data
}
)
# train first autoencoder
training_epochs = 20
c1 = []
for epoch in xrange(training_epochs):
c1.append(train_da(numpy.asarray(train_set)))
print 'Training 1st ae epoch %d, cost ' % epoch, c1[len(c1)-1]
# train second autoencoder
train_set2 = da.get_hidden_values(train_set).eval()
train_data = T.dmatrix('train_data')
x = T.dmatrix('x') # the data is presented as rasterized images
rng = numpy.random.RandomState(123)
theano_rng = RandomStreams(rng.randint(2 ** 10))
da2 = dA(
numpy_rng=rng,
theano_rng=theano_rng,
input=x,
n_visible=30,
n_hidden=20
)
cost, updates = da2.get_cost_updates(
corruption_level=0.,
learning_rate=0.4
)
train_da2 = theano.function(
[train_data],
cost,
updates=updates,
givens={
x: train_data
}
)
training_epochs = 20
c1 = []
for epoch in xrange(training_epochs):
c1.append(train_da2(numpy.asarray(train_set2)))
print 'Training 2nd ae epoch %d, cost ' % epoch, c1[len(c1)-1]
for c in test_class:
m.features[c] = da2.get_hidden_values(da.get_hidden_values(m.features[c]).eval()).eval()
m.train()
m.dump('model/model_sda.out')
with open('model/da1.out', 'w') as f:
pickle.dump(da, f, -1)
with open('model/da2.out', 'w') as f:
pickle.dump(da2, f, -1)
return up_bound, lower_bound
