def test_classifier(sess, classifier):
rand_batch = rand_batch_gen(sentence_int, label, length, 640)
input_vec, onehot_label, lenth = next(rand_batch)
batch_label = np.argmax(onehot_label, axis=1)
out = classifier.predict_batch(input_vec)
loss = classifier.batch_loss(input_vec, batch_label)
correct = np.argmax(out, axis=1) == batch_label
acc = np.sum(correct) / 640
ave_loss = np.sum(loss) / 640
return acc, ave_loss
def get_simplify(sess, actor):
rand_batch = rand_batch_gen(sentence_int, label, length, 640)
input_vec, onehot_label, lenth = next(rand_batch)
actions, states, Rinput, Rlenth = sampling_RL(sess,
actor,
input_vec,
lenth,
epsilon,
Random=False)
text = ''
for i in range(len(input_vec)):
text += 'example: \n'
text += 'after simplifying: \n'
simplify = Rinput
text += ''.join(simplify) + '\n\n\n'
with open('./data/example.txt', 'w') as f:
f.write(text)
def test(sess, actor, classifier, RL=True):
rand_batch = rand_batch_gen(sentence_int, label, length, 640)
input_vec, onehot_label, lenth = next(rand_batch)
batch_label = np.argmax(onehot_label, axis=1)
if RL:
actions, states, Rinput, Rlenth = sampling_RL(sess,
actor,
input_vec,
lenth,
epsilon,
Random=False)
out = classifier.predict_batch(Rinput)
loss = classifier.batch_loss(Rinput, batch_label)
for i in range(5):
print('\nexample:')
input_i = i
print(input_vec[input_i])
print('label: ', np.min(input_vec[input_i]))
print('\nafter Simplifying:')
print(Rinput[input_i])
print()
keep_ratio = np.mean(Rlenth / lenth)
print('keep ratio: {:.2f}%'.format(keep_ratio * 100))
else:
out = classifier.predict_batch(input_vec, lenth)
loss = classifier.batch_loss(input_vec, lenth, batch_label)
correct = (np.argmax(out, axis=1) == np.argmax(onehot_label, axis=1))
acc = np.sum(correct) / 640
ave_loss = np.sum(loss) / 640
return acc, ave_loss
def train(sess, actor, classifier, batchsize, classifier_trainable=True):
for b in range(1000):
acc_test, loss = test(sess, actor, classifier)
print("batch", b, " --batch accuracy: {:.2f}%".format(acc_test * 100))
print("\t", "--batch loss: {:.2f}".format(loss))
rand_batch = rand_batch_gen(sentence_int, label, length, batchsize)
input_vec, onehot_label, lenth = next(rand_batch)
batch_label = np.argmax(onehot_label, axis=1)
actionlist, statelist, losslist = [], [], []
for i in range(samplecnt):
actions, states, Rinput, Rlenth = sampling_RL(sess,
actor,
input_vec,
lenth,
epsilon,
Random=True)
actionlist.append(actions)
statelist.append(states)
loss = classifier.batch_loss(Rinput, batch_label)
length_loss = np.maximum(Rlenth - 10, 0)**2 / (50)**2 * 0.2
# length_loss = (Rlenth / lenth) ** 2 * 0.2
loss += length_loss
losslist.append(loss)
if i % 20 == 0:
print('lenth loss:{:.2f}'.format(np.mean(length_loss)))
keep_ratio = np.mean(Rlenth / lenth)
print('random keep ratio: {:.2f}%'.format(keep_ratio * 100))
if classifier_trainable:
if i % 20 == 0:
actions, states, Rinput, Rlenth = sampling_RL(sess,
actor,
input_vec,
lenth,
epsilon,
Random=False)
classifier.train_batch(Rinput, batch_label)
keep_ratio = np.mean(Rlenth / lenth)
print('argmax keep ratio: {:.2f}%'.format(keep_ratio *
100))
loss_array = np.array(losslist)
aveloss = np.mean(loss_array, axis=0)
for i in range(samplecnt):
reward = -(losslist[i] - aveloss)
actions = actionlist[i]
states = statelist[i]
total_time = len(states)
batchsize = len(reward)
for time in range(total_time):
rr = np.zeros((batchsize, 2))
action = actions[time]
for i in range(batchsize):
rr[i, action[i]] = reward[i]
actor.train(states[time][0], states[time][1], rr)
import json
from actor import ActorNetwork
from self_att_rnn import SelfAttRNN
from model_api import ModelAPI
from integration_func import generate_embedding_mat
from data_helper import get_data, rand_batch_gen
os.environ["CUDA_VISIBLE_DEVICES"] = "2"
metadata_pkl = './data/post_metadata.pkl'
max_length = 200
word_to_int, int_to_word, sentence_int, label, length = get_data(
metadata_pkl, max_length)
rand_batch = rand_batch_gen(sentence_int, label, length, 64)
vocab_size = len(word_to_int)
embed_size = 128
options = {"context_lstm_dims": 100, "highway_layer_num": 1}
class_list = [
u"投递质量", u"延误", u"信息质量", u"破损", u"丢失", u"服务态度", u"收寄质量", u"需求建议", u"售后服务"
]
config = {
"options": options,
"vocab_size": vocab_size,
"max_length": max_length,
"emb_size": embed_size,
"extra_symbol": ["<PAD>", "<UNK>"],