def train_rnn():
rng = numpy.random.RandomState(1234)
q = T.lvector("q")
pos = T.lscalar("pos")
neg = T.lscalar("neg")
inputs = [q, pos, neg]
embLayer = emb_layer(None, 100, 5)
rnn = rnn_layer(input=inputs, emb_layer=embLayer, nh=5)
cost = rnn.loss()
gradient = T.grad(cost, rnn.params)
lr = 0.001
updates = OrderedDict((p, p - lr * g) for p, g in zip(rnn.params, gradient))
train = theano.function(inputs=[q, pos, neg], outputs=cost, updates=updates)
print rnn.emb.eval()[0]
e0 = rnn.emb.eval()
for i in range(0, 3):
idq = rng.randint(size=10, low=0, high=100)
idpos = rng.random_integers(100)
idneg = rng.random_integers(100)
train(idq, idpos, idneg)
rnn.normalize()
print rnn.emb.eval() - e0
def test(model):
dim = 128
v_size = 7810
margin = 1.0
#load model
f = open(model, 'rb')
input_params = cPickle.load(f)
emb, wx, wh, bh, wa = input_params
f.close()
embLayer = emb_layer(pre_train=emb, v = v_size, dim = dim)
rnnLayer = rnn_layer(input=None, wx=wx, wh=wh, bh=bh, emb_layer = embLayer, nh = dim)
att = attention_layer(input=None, rnn_layer=rnnLayer, margin = margin)
q = T.lvector('q')
a = T.lscalar('a')
p = T.lvector('p')
t = T.lscalar('t')
inputs = [q,a,p,t]
score = att.predict(inputs)
pred = theano.function(inputs=inputs,outputs=score)
pool = ThreadPool()
f = open('./data/test-small.id','r')
count = 1
print 'time_b:%s' %time.clock()
to_pred = []
for line in f:
if count % 10000 == 0:
print count / 10000
count += 1
#print 'time_b:%s' %time.clock()
line = line[:-1]
tmp = line.split('\t')
in_q = numpy.array(tmp[0].split(' ')).astype(numpy.int) - 1
in_a = int(tmp[1].split(' ')[2]) - 1
in_p = numpy.array(tmp[1].split(' ')).astype(numpy.int) - 1
in_t = int(tmp[2]) - 1
lis = (in_q, in_a, in_p, in_t)
to_pred.append(lis)
#print 'time_load:%s' %time.clock()
#print 'time_score:%s' %time.clock()
f.close()
ay = numpy.asarray(to_pred)
#results = map(pred, list(ay[:,0]), list(ay[:,1]),list(ay[:,2]),list(ay[:,3]))
results = pool.map(pred, to_pred)
#results = []
#for p in to_pred:
# results.append(att.predict(p,params))
print 'time_e:%s' %time.clock()
#print results
pool.close()
pool.join()
def test(model):
dim = 128
v_size = 7810
margin = 1.0
#load model
f = open(model, 'rb')
input_params = cPickle.load(f)
emb, wx, wh, bh, wa = input_params
f.close()
embLayer = emb_layer(pre_train=emb, v = v_size, dim = dim)
rnnLayer = rnn_layer(input=None, wx=wx, wh=wh, bh=bh, emb_layer = embLayer, nh = dim)
att = attention_layer(input=None, rnn_layer=rnnLayer, margin = margin)
q = T.lvector('q')
a = T.lscalar('a')
p = T.lvector('p')
t = T.lscalar('t')
inputs = [q,a,p,t]
#emb_num = T.lscalar('emb_num')
#nh = T.scalar('nh')
#dim = T.scalar('dim')
score = att.predict(inputs)
pred = theano.function(inputs=inputs,outputs=score)
wf = open('./data/res','w')
f = open('./data/test.id','r')
count = 1
print 'time_b:%s' %time.clock()
for line in f:
if count % 10000 == 0:
print count / 10000
print 'time_1w:%s' %time.clock()
count += 1
#print 'time_b:%s' %time.clock()
line = line[:-1]
tmp = line.split('\t')
in_q = numpy.array(tmp[0].split(' ')).astype(numpy.int) - 1
#x = emb[q].reshape((q.shape[0], emb.shape[1]))
in_a = int(tmp[1].split(' ')[2]) - 1
in_p = numpy.array(tmp[1].split(' ')).astype(numpy.int) - 1
in_t = int(tmp[2]) - 1
#in_lis = [in_q, in_a, in_p, in_t]
#print 'time_load:%s' %time.clock()
s = pred(in_q, in_a, in_p, in_t)
#print s
wf.write(str(s) + '\n')
#print 'time_score:%s' %time.clock()
f.close()
wf.close()
def train_rnn():
rng = numpy.random.RandomState(1234)
q = T.lvector('q')
pa = T.lscalar('pa')
pp = T.lvector('pp')
pt = T.lscalar('pt')
na = T.lscalar('na')
np = T.lvector('np')
nt = T.lscalar('nt')
inputs = [q, pa, pp, pt, na, np, nt]
dim = 128
v_size = 7810
embLayer = emb_layer(pre_train=None, v = v_size, dim = dim)
rnnLayer = rnn_layer(input=None, wx=None, wh=None, bh=None, emb_layer = embLayer, nh = dim)
margin = 1.0
att = attention_layer(input = inputs, rnn_layer=rnnLayer, margin = margin)
cost = att.loss()
print att.params
gradient = T.grad(cost, att.params)
lr = 0.001
updates = OrderedDict((p,p-lr*g) for p,g in zip(att.params, gradient))
train = theano.function(inputs=[q, pa, pp, pt, na, np, nt], outputs=cost, updates = updates)
#theano.printing.pydotprint(train, outfile="pic_train.png", compact=True, var_with_name_simple=True)
#print rnnLayer.emb.eval()[0]
#Training process
e0 = rnnLayer.emb.eval()
train_list = load_train('./data/train_5neg.id')
epoch = 1
while True:
for t in train_list:
q, pa, pp, pt, na, np, nt = t
train(q, pa, pp, pt, na, np, nt)
rnnLayer.normalize()
att.normalize()
att.savemodel('./model/epoch' + str(epoch) + '.model')
print rnnLayer.emb.eval()[0] - e0[0]
print 'training epoch ' + str(epoch) + ' done.'
epoch += 1
