def test_ctc_differentiable(self):
costs = ctc.cost(
linear_out=self.lin_output,
frame_lengths=self.data_length,
labels=self.labels,
label_lengths=self.labels_length
)
g = T.grad(T.mean(costs), wrt=self.transform)
self.assertTrue((~np.isnan(g.eval())).all())
def label_seq(string):
idxs = font.indexify(string)
return idxs
if __name__ == "__main__":
P = Parameters()
X = T.matrix('X')
Y = T.ivector('Y')
predict = build_model(P, 8, 512, len(font.chars) + 1)
probs = predict(X)
alpha = 0.5
params = P.values()
cost = ctc.cost(probs, Y) #+ 1e-8 * sum(T.sum(T.sqr(w)) for w in params)
gradients = T.grad(cost, wrt=params)
gradient_acc = [theano.shared(0 * p.get_value()) for p in params]
counter = theano.shared(np.float32(0.))
acc = theano.function(inputs=[X, Y],
outputs=cost,
updates=[(a, a + g)
for a, g in zip(gradient_acc, gradients)] +
[(counter, counter + np.float32(1.))])
update = theano.function(
inputs=[],outputs=[],
updates = updates.momentum(params,[ g / counter for g in gradient_acc ]) \
+ [ (a, np.float32(0) * a) for a in gradient_acc ] \
+ [ (counter,np.float32(0.)) ]
)
predict = T.nnet.softmax(T.dot(hidden, W_hidden_output) + b_output)
return X, predict
def label_seq(string):
idxs = font.indexify(string)
result = np.ones((len(idxs) * 2 + 1, ), dtype=np.int32) * -1
result[np.arange(len(idxs)) * 2 + 1] = idxs
print result
return result
if __name__ == "__main__":
P = Parameters()
X = T.matrix('X')
Y = T.ivector('Y')
X, predict = build_model(P, X, 10, 10, 10)
cost = ctc.cost(predict, Y)
params = P.values()
grad = T.grad(cost, wrt=params)
train = theano.function(inputs=[X, Y],
outputs=cost,
updates=updates.adadelta(params, grad))
for _ in xrange(10):
print train(
np.eye(10, dtype=np.float32)[::-1], np.arange(10, dtype=np.int32))
predict = T.nnet.softmax(T.dot(hidden, W_hidden_output) + b_output)
return X, predict
def label_seq(string):
idxs = font.indexify(string)
result = np.ones((len(idxs) * 2 + 1,), dtype=np.int32) * -1
result[np.arange(len(idxs)) * 2 + 1] = idxs
print result
return result
if __name__ == "__main__":
P = Parameters()
X = T.matrix('X')
Y = T.ivector('Y')
X, predict = build_model(P, X, 10, 10, 10)
cost = ctc.cost(predict, Y)
params = P.values()
grad = T.grad(cost, wrt=params)
train = theano.function(
inputs=[X, Y],
outputs=cost,
updates=updates.adadelta(params, grad)
)
for _ in xrange(10):
print train(np.eye(10, dtype=np.float32)[::-1], np.arange(10, dtype=np.int32))
idxs = font.indexify(string)
return idxs
if __name__ == "__main__":
P = Parameters()
X = T.matrix('X')
Y = T.ivector('Y')
predict = build_model(P,8,512,len(font.chars)+1)
probs = predict(X)
alpha = 0.5
params = P.values()
cost = ctc.cost(probs, Y) #+ 1e-8 * sum(T.sum(T.sqr(w)) for w in params)
gradients = T.grad(cost, wrt=params)
gradient_acc = [ theano.shared(0 * p.get_value()) for p in params ]
counter = theano.shared(np.float32(0.))
acc = theano.function(
inputs=[X, Y],
outputs=cost,
updates = [
(a,a + g) for a,g in zip(gradient_acc,gradients)
] + [(counter,counter + np.float32(1.))]
)
update = theano.function(
inputs=[],outputs=[],
updates = updates.momentum(params,[ g / counter for g in gradient_acc ]) \
+ [ (a, np.float32(0) * a) for a in gradient_acc ] \
