def main(_):
if not os.path.exists(ckpt_path + 'checkpoint'):
print('there is not saved model, please check the ckpt path')
exit()
print('Loading model...')
W_embedding = np.load(embedding_path)
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
model = network.HCNN(W_embedding, settings)
model.saver.restore(sess, tf.train.latest_checkpoint(ckpt_path))
print('Local predicting...')
local_predict(sess, model)
print('Test predicting...')
predict(sess, model)
def main(_):
if not os.path.exists(ckpt_path + 'checkpoint'):
print('there is not saved model, please check the ckpt path')
exit()
print('Loading model...')
W_embedding = np.load(embedding_path)
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
log_path = scores_path + settings.model_name + '/'
if not os.path.exists(log_path):
os.makedirs(log_path)
logger = get_logger(log_path + 'predict.log')
with tf.Session(config=config) as sess:
model = network.HCNN(W_embedding, settings)
# ckpt_path: /ckpt/wd_BiGRU/checkpoint
model.saver.restore(sess, tf.train.latest_checkpoint(ckpt_path))
print('Valid predicting...')
predict_valid(sess, model, logger)
print('Test predicting...')
predict(sess, model, logger)
def main(_):
##summary and ckpt path
global ckpt_path
global last_f1
if not os.path.exists(ckpt_path):
os.makedirs(ckpt_path)
if not os.path.exists(summary_path):
os.makedirs(summary_path)
elif FLAGS.is_retrain:
shutil.rmtree(summary_path)
os.makedirs(summary_path)
print('start to import embeddings...')
W_embedding = np.load(embedding_path)
print('embedding imported.')
print('Building the model')
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
#引入模型
model = network.HCNN(settings, W_embedding)
##optimizer tf.train.AdamOptimizer(lr=..).minimize(loss)
with tf.variable_scope('training_ops') as vs:
learning_rate = tf.train.exponential_decay(FLAGS.lr,
model.global_step,
FLAGS.decay_step,
FLAGS.decay_rate,
staircase=True)
#two optimizer, one updates the embedding, one not
with tf.variable_scope('optimizer1'):
tvar1 = tf.trainable_variables()
grads1 = tf.gradients(model.loss, tvar1)
optimizer1 = tf.train.AdamOptimizer(
learning_rate=learning_rate)
op1 = optimizer1.apply_gradients(zip(grads1, tvar1),
global_step=model.global_step)
with tf.variable_scope('optimizer2'):
#
tvar2 = [
tvar for tvar in tvar1 if 'embedding' not in tvar.name
]
grads2 = tf.gradients(model.loss, tvar2)
optimizer2 = tf.train.AdamOptimizer(
learning_rate=learning_rate)
op2 = optimizer2.apply_gradients(zip(grads2, tvar2),
global_step=model.global_step)
update_op = tf.group(*model.update_emas)
merged = tf.summary.merge_all()
train_writer = tf.summary.FileWriter(summary_path + 'train',
sess.graph)
test_writer = tf.summary.FileWriter(summary_path + 'test')
#感觉这句是多余的，它收集不到training_ops变量名下的其它变量啊，换句话说这是个空列表。
training_ops = [
v for v in tf.global_variables()
if v.name.startswith(vs.name + '/')
]
##如果已经保存模型导入上次的模型，初始化相关变量
if os.path.exists(ckpt_path + 'checkpoint'):
print('Restoring Variables from checkpoint...')
model.saver.restore(sess, tf.train.latest_checkpoint(ckpt_path))
last_valid_cost, precision, recall, last_f1 = valid_epoch(
data_valid_path, sess, model)
print('valid_cost=%g, p=%g, r=%g, f1=%g' %
(last_valid_cost, precision, recall, last_f1))
sess.run(tf.variables_initializer(training_ops))
train_op2 = train_op1
else:
print('start to initialize the variables...')
sess.run(tf.global_variables_initializer())
#开始epoch循环训练
print('3.begin training...')
print('max_epoch=%d, max_max_epoch=%d' %
(FLAGS.max_epoch, FLAGS.max_max_epoch))
for epoch in range(FLAGS.max_max_epoch):
global_step = sess.run(model.global_step)
print('global step d%, lr=%g' %
(global_step, sess.run(learning_rate)))
if epoch == FLAGS.max_epoch:
train_op = op1
else:
train_op = op2
train_fetches = [merged, model.loss, train_op, update_op]
valid_fetches = [merged, model.loss]
train_epoch(data_train_path, sess, model, train_fetches,
valid_fetches, train_writer, test_writer)
##满足条件则保存模型
valid_cost, precision, recall, f1 = valid_epoch(
data_valid_path, sess, model)
print('END.Global_step=%d: valid cost=%g; p=%g, r=%g, f1=%g' %
(sess.run(model.global_step), valid_cost, precision, recall, f1))
if f1 > last_f1:
saving_path = model.saver.save(sess, model_path,
sess.run(model.global_step) + 1)
print('saved new model to:%s' % saving_path)
def main(_):
global ckpt_path
global last_f1
if not os.path.exists(ckpt_path):
os.makedirs(ckpt_path)
if not os.path.exists(summary_path):
os.makedirs(summary_path)
elif not FLAGS.is_retrain: # 重新训练本模型，删除以前的 summary
shutil.rmtree(summary_path)
os.makedirs(summary_path)
if not os.path.exists(summary_path):
os.makedirs(summary_path)
print('1.Loading data...')
W_embedding = np.load(embedding_path)
print('training sample_num = %d' % n_tr_batches)
print('valid sample_num = %d' % n_va_batches)
# Initial or restore the model
print('2.Building model...')
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
model = network.HCNN(W_embedding, settings)
with tf.variable_scope('training_ops') as vs:
learning_rate = tf.train.exponential_decay(FLAGS.lr,
model.global_step,
FLAGS.decay_step,
FLAGS.decay_rate,
staircase=True)
# two optimizer: op1, update embedding; op2, do not update embedding.
with tf.variable_scope('Optimizer1'):
tvars1 = tf.trainable_variables()
grads1 = tf.gradients(model.loss, tvars1)
optimizer1 = tf.train.AdamOptimizer(
learning_rate=learning_rate)
train_op1 = optimizer1.apply_gradients(
zip(grads1, tvars1), global_step=model.global_step)
with tf.variable_scope('Optimizer2'):
tvars2 = [
tvar for tvar in tvars1 if 'embedding' not in tvar.name
]
grads2 = tf.gradients(model.loss, tvars2)
optimizer2 = tf.train.AdamOptimizer(
learning_rate=learning_rate)
train_op2 = optimizer2.apply_gradients(
zip(grads2, tvars2), global_step=model.global_step)
update_op = tf.group(*model.update_emas)
merged = tf.summary.merge_all() # summary
train_writer = tf.summary.FileWriter(summary_path + 'train',
sess.graph)
test_writer = tf.summary.FileWriter(summary_path + 'test')
training_ops = [
v for v in tf.global_variables()
if v.name.startswith(vs.name + '/')
]
# 如果已经保存过模型，导入上次的模型
if os.path.exists(ckpt_path + "checkpoint"):
print("Restoring Variables from Checkpoint...")
model.saver.restore(sess, tf.train.latest_checkpoint(ckpt_path))
last_valid_cost, precision, recall, last_f1 = valid_epoch(
data_valid_path, sess, model)
print(' valid cost=%g; p=%g, r=%g, f1=%g' %
(last_valid_cost, precision, recall, last_f1))
sess.run(tf.variables_initializer(training_ops))
train_op2 = train_op1
else:
print('Initializing Variables...')
sess.run(tf.global_variables_initializer())
print('3.Begin training...')
print('max_epoch=%d, max_max_epoch=%d' %
(FLAGS.max_epoch, FLAGS.max_max_epoch))
for epoch in xrange(FLAGS.max_max_epoch):
global_step = sess.run(model.global_step)
print('Global step %d, lr=%g' %
(global_step, sess.run(learning_rate)))
if epoch == FLAGS.max_epoch: # update the embedding
train_op = train_op1
else:
train_op = train_op2
train_fetches = [merged, model.loss, train_op, update_op]
valid_fetches = [merged, model.loss]
train_epoch(data_train_path, sess, model, train_fetches,
valid_fetches, train_writer, test_writer)
# 最后再做一次验证
valid_cost, precision, recall, f1 = valid_epoch(
data_valid_path, sess, model)
print('END.Global_step=%d: valid cost=%g; p=%g, r=%g, f1=%g' %
(sess.run(model.global_step), valid_cost, precision, recall, f1))
if f1 > last_f1: # save the better model
saving_path = model.saver.save(sess, model_path,
sess.run(model.global_step) + 1)
print('saved new model to %s ' % saving_path)