label = np.zeros(5)
sim = labels[i]
ceil = math.ceil(sim)
floor = math.floor(sim)
if ceil == floor:
label[int(ceil-1)]=1
else:
label[int(ceil-1)]=sim-floor
label[int(floor - 1)]=ceil-sim
labelsbatch.append(label)
return (data1batch,linverse, data2batch,rinverse, labelsbatch)
if __name__=="__main__":
emb = tf.convert_to_tensor(common.getEmb(), dtype="float")
(trainleft, trainright, trainscore) = common.getTrainSet()
(testleft, testright, testscore) = common.getTestSet()
(testlbatch, testllength,testrbatch, testrlength, testscores) = next_batch(len(testleft), testleft, testright, testscore, random=False)
lenth = len(trainleft)
embedding = emb
W = tf.Variable(emb,
trainable=False, name="W")
pivot = tf.placeholder(tf.float32, shape=[None, 5], name="pivot")
leftseqs=tf.placeholder(tf.int32, shape=[None, None], name="leftseqs")
leftlength=tf.placeholder(tf.float32, shape=[None], name="leftlength")
rightseqs=tf.placeholder(tf.int32, shape=[None, None], name='rightseqs')
rightlength=tf.placeholder(tf.float32, shape=[None], name="rightlength")
leftEmbedding = tf.nn.embedding_lookup(W, leftseqs)
rightEmbedding = tf.nn.embedding_lookup(W, rightseqs)
leftSum = tf.reduce_sum(leftEmbedding, axis=1)
class Batcher(object):
batch_size = 25
(trainleft, trainright, trainscore) = common.getTrainSet()
(testleft, testright, testscore) = common.getTestSet()
def __init__(self):
pass
def numOfBatchPerEpoch(self):
return len(self.trainright) / self.batch_size
def next_train_batch(self):
return self.next_batch(self.batch_size,
self.trainleft,
self.trainright,
self.trainscore,
random=True)
def next_test_batch(self):
return self.next_batch(len(self.testleft),
self.testleft,
self.testright,
self.testscore,
random=False)
def test_score(self):
return self.testscore
def batch_one_side(self, data, idx):
databatch = []
maxlength = 0
masks = []
for i in idx:
maxlength = max(maxlength, len(data[i]))
for i in idx:
d = []
mask = []
senLen = len(data[i])
for j in range(maxlength):
mask.append(0)
if j < senLen:
if j == senLen - 1:
mask[j] = 1
d.append(data[i][j])
else:
d.append(2302)
databatch.append(d)
masks.append(mask)
return (databatch, masks)
def bach_labels(self, scores, idx):
labelsbatch = []
for i in idx:
label = np.zeros(5)
sim = scores[i]
ceil = math.ceil(sim)
floor = math.floor(sim)
if ceil == floor:
label[int(ceil - 1)] = 1
else:
label[int(ceil - 1)] = sim - floor
label[int(floor - 1)] = ceil - sim
labelsbatch.append(label)
return labelsbatch
def next_batch(self, num, data1, data2, scores, random=True):
idx = np.arange(0, len(data1))
if random == True:
np.random.shuffle(idx)
idx = idx[:num]
(databatch1, masks1) = self.batch_one_side(data1, idx)
(databatch2, masks2) = self.batch_one_side(data2, idx)
labelsbatch = self.bach_labels(scores, idx)
return (databatch1, masks1, databatch2, masks2, labelsbatch)