def run(self, back=True):
super(DNN, self).run(back=back)
data, labels = self.dset.get_batch()
data = one_hot(data, self.hps.output_size)
data = data.reshape((-1, data.shape[2]))
#cost, grads = self.cost_and_grad(data, labels)
#self.check_grad(data, labels, grads, params_to_check=['Wih'], eps=0.01)
if back:
self.update_params(data, labels)
else:
cost, probs = self.cost_and_grad(data, labels, back=False)
return cost, probs
def run(self, back=True):
super(DNN, self).run(back=back)
data, labels = self.dset.get_batch()
data = one_hot(data, self.hps.output_size)
data = data.reshape((-1, data.shape[2]))
#cost, grads = self.cost_and_grad(data, labels)
#self.check_grad(data, labels, grads, params_to_check=['Wih'], eps=0.01)
if back:
self.update_params(data, labels)
else:
cost, probs = self.cost_and_grad(data, labels, back=False)
return cost, probs
def run(self, back=True):
super(NNJM, self).run(back=back)
data, labels = self.dset.get_batch()
data = one_hot(data, self.hps.output_size)
data = data.reshape((-1, data.shape[2]))
source_data = self.ctc_loader.get_batch()
#cost, grads = self.cost_and_grad((data, source_data), labels)
#self.check_grad((data, source_data), labels, grads, params_to_check=['Wsh'], eps=0.01)
#print labels
#print np.argmax(source_data, axis=0)
if back:
self.update_params((data, source_data), labels)
else:
cost, probs = self.cost_and_grad((data, source_data), labels, back=False)
return cost, probs
def sample_continuation(s, model, order, alpha=1.0):
if MODEL_TYPE == 'rnn':
data = array(np.array([char_inds[w] for w in s[-1:]])).reshape(-1, 1)
else:
data = array(np.array([char_inds[w] for w in s[-order+1:]])).reshape(-1, 1)
data = one_hot(data, model.hps.output_size)
if MODEL_TYPE == 'rnn':
_, probs = model.cost_and_grad(data, None, prev_h0=model.last_h)
probs = np.squeeze(as_np(probs))
else:
data = data.reshape((-1, data.shape[2]))
_, probs = model.cost_and_grad(data, None)
probs = probs.ravel()
# Higher alpha -> more and more like most likely sequence
probs = probs ** alpha
probs = probs / sum(probs)
w = np.random.choice(range(model.hps.output_size), p=probs)
char = chars[w]
return char
