max_gamma_Avg_prec = 0
max_beta_Avg_prec = 0
APK = []
ASK = []
APK1 = []
ASK1 = []
min_one_err = 1000000
min_gamma_one_err = 0
min_beta_one_err = 0
max_S_2_train = 0
max_S_2_test = 0
with tf.Session(config=config) as sess:
han = HAN(vocab_size=FLAGS.vocab_size,
vocab_dict=vocab,
A_matrix=A_matrix,
num_classes=FLAGS.num_classes,
num_classes_8=FLAGS.num_classes_8,
sess=sess,
embedding_size=FLAGS.embedding_size,
hidden_size=FLAGS.hidden_size)
regularizer = tf.contrib.layers.l2_regularizer(0.1)
reg_term = tf.contrib.layers.apply_regularization(regularizer)
loss = tf.reduce_mean(
tf.nn.sigmoid_cross_entropy_with_logits(
labels=han.input_y, logits=han.out)) + reg_term
predict = tf.argmax(han.out, axis=1, name='predict')
label = tf.argmax(han.input_y, axis=1, name='label')
acc = tf.reduce_mean(tf.cast(tf.equal(predict, label), tf.float32))
global_step = tf.Variable(0, trainable=False)
FLAGS = tf.flags.FLAGS
print(FLAGS.max_sent_in_doc)
print(FLAGS.max_word_in_sent)
train_x, train_y, dev_x, dev_y, vocab = load_dataset(FLAGS.yelp_json_path,
FLAGS.labels_json_path,
FLAGS.max_sent_in_doc,
FLAGS.max_word_in_sent)
print("data load finished")
#print(train_x)
with tf.Session() as sess:
han = HAN(vocab_size=FLAGS.vocab_size,
num_classes=FLAGS.num_classes,
embedding_size=FLAGS.embedding_size,
hidden_size=FLAGS.hidden_size)
with tf.name_scope('loss'):
loss = tf.reduce_mean(
tf.nn.sigmoid_cross_entropy_with_logits(labels=han.input_y,
logits=han.out,
name='loss'))
with tf.name_scope('accuracy'):
predict = tf.argmax(han.out, axis=1, name='predict')
label = tf.argmax(han.input_y, axis=1, name='label')
acc = tf.reduce_mean(tf.cast(tf.equal(predict, label), tf.float32))
timestamp = str(int(time.time()))
out_dir = os.path.abspath(os.path.join(os.path.curdir, "runs", timestamp))
print("Writing to {}\n".format(out_dir))
y_train = to_categorical(y_train)
y_test = to_categorical(y_test)
#add one extra dimention as the sentence (1 sentence per doc!)
X_train = np.expand_dims(X_train, axis=1)
X_test = np.expand_dims(X_test, axis=1)
print('X_train shape:', X_train.shape)
print('X_test shape:', X_test.shape)
##########----------字典的大小-----
vocabulary_size = np.max([np.max(X_train[i]) for i in range(X_train.shape[0])])+1
print("vocab_size,--字典大小 ",vocabulary_size)
nn = HAN(
vocab_size=vocabulary_size,
num_classes=y_train.shape[1],
embedding_size=embedding_dim,
hidden_size=rnn_size
)
########--------使用SGD梯度下降最小loss
optimizer = tf.train.AdamOptimizer(learning_rate=1e-3).minimize(nn.loss)
tf.summary.scalar('loss',nn.loss)
tf.summary.scalar("accuracy",nn.accuracy)
merged = tf.summary.merge_all()
# Batch generators
# batch_size = 256
# num_epochs = 3