def calculate_loss(logits, labels):
""" The total loss is defined as the cross entropy loss plus all of the weight decay terms (L2 loss).
Args:
logits: Logits from inference(), 2D tensor of [None, NUM_CLASSES].
labels: 2D tensor of [None, NUM_CLASSES].
Returns:
Loss: 0D tensor of type float.
"""
myTF.calculate_cross_entropy_loss(logits, labels)
return tf.add_n(tf.get_collection('losses'), name='loss_total')
def evaluate(evalDataSet, ckpt_value, eval_value, time_list):
with tf.Graph().as_default() as g, tf.device('/gpu:0'):
# Placeholders for input, output and dropout
feature_size = FLAGS.num_filters * len(FLAGS.filter_sizes.split(','))
# Placeholders for input, output and dropout
input_x = tf.placeholder(tf.int32, [None, OPTION.SEQUENCE_LEN],
name="input_x")
input_y = tf.placeholder(tf.int32, [None, OPTION.NUM_CLASSES],
name="input_y")
feature_size = feature_size * min(time_list[-1] - 0, OPTION.DP_DEPTH)
if feature_size > 0:
features_before = tf.placeholder(tf.float32, [None, feature_size],
name="features_before")
else:
features_before = None
textcnn = TextCNNpn_model.Model(
sequence_length=OPTION.SEQUENCE_LEN,
num_classes=OPTION.NUM_CLASSES,
vocab_size=None,
embedding_size=OPTION.EMEBEDDING_DIMENSION,
filter_sizes=list(map(int, FLAGS.filter_sizes.split(","))),
num_filters=FLAGS.num_filters,
Word2vec=True,
Trainable=False)
# inference model.
logits, _ = textcnn.inference(input_x,
features_before,
OPTION.EVAL_BATCH_SIZE,
eval_data=True)
# Calculate loss.
loss = myTF.calculate_cross_entropy_loss(logits, input_y)
logits = tf.nn.softmax(logits)
# Restore the moving average version of the learned variables for eval. # ?????????????????????????
variable_averages = tf.train.ExponentialMovingAverage(
OPTION.MOVING_AVERAGE_DECAY)
variables_to_restore = variable_averages.variables_to_restore()
saver = tf.train.Saver(variables_to_restore)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.summary.merge_all()
summary_writer = tf.summary.FileWriter(OPTION.EVAL_DIR, g)
last_eval_ckpt = ckpt_value
best_eval_value = eval_value
config = tf.ConfigProto(allow_soft_placement=True,
log_device_placement=False)
# config.gpu_options.per_process_gpu_memory_fraction = 0.5 # 程序最多只能占用指定gpu50%的显存
config.gpu_options.allow_growth = True # 程序按需申请内存
while True:
# Start running operations on the Graph. allow_soft_placement must be set to
# True to build towers on GPU, as some of the ops do not have GPU implementations.
with tf.Session(config=config) as sess:
ckpt = tf.train.get_checkpoint_state(OPTION.CHECKPOINT_DIR)
if ckpt and ckpt.model_checkpoint_path:
# extract global_step
global_step_for_restore = int(
ckpt.model_checkpoint_path.split('/')[-1].split('-')
[-1])
if global_step_for_restore > last_eval_ckpt:
# Restores from checkpoint
saver.restore(sess, ckpt.model_checkpoint_path)
else:
if tf.gfile.Exists("TRAIN_SUCCEED"):
print("Train terminated, eval terminating...")
return
else:
print('No checkpoint file found')
time.sleep(FLAGS.eval_interval_secs)
continue
if global_step_for_restore > last_eval_ckpt:
max_steps_per_epoch = int(
math.ceil(evalDataSet.get_dataset_size() /
float(OPTION.EVAL_BATCH_SIZE)))
start_time = time.time()
total_predicted_value = []
total_true_value = []
total_loss = []
for step in range(max_steps_per_epoch):
test_data, test_label, test_features = evalDataSet.next_batch(
OPTION.EVAL_BATCH_SIZE)
if feature_size > 0:
feed_dict = {
input_x: test_data,
input_y: test_label,
features_before: test_features
}
else:
feed_dict = {
input_x: test_data,
input_y: test_label
}
predicted_value, true_value, loss_value = sess.run(
[logits, input_y, loss], feed_dict=feed_dict)
total_predicted_value.append(predicted_value)
total_true_value.append(true_value)
total_loss.append(loss_value)
duration = time.time() - start_time
# test_data, test_label = evalDataSet.next_batch(OPTION.EVAL_BATCH_SIZE)
summary = tf.Summary()
# summary.ParseFromString(sess.run(summary_op, feed_dict={input_x: test_data, input_y: test_label}))
total_predicted_value = np.concatenate(
total_predicted_value, axis=0)
total_true_value = np.concatenate(total_true_value, axis=0)
total_loss = np.concatenate(total_loss, axis=0)
total_predicted_value = total_predicted_value[
0:evalDataSet.get_dataset_size()]
total_true_value = total_true_value[0:evalDataSet.
get_dataset_size()]
total_loss = total_loss[0:evalDataSet.get_dataset_size()]
assert evalDataSet.get_dataset_size(
) == total_predicted_value.shape[0], 'sample_count error!'
best_eval_value = evaluation_result(
OPTION.EVAL_DIR, total_predicted_value,
total_true_value, total_loss, global_step_for_restore,
best_eval_value, summary)
summary_writer.add_summary(summary,
global_step_for_restore)
last_eval_ckpt = global_step_for_restore
if FLAGS.run_once:
break
time.sleep(FLAGS.eval_interval_secs)
def evaluate(trainDataSet,time,model_time):
with tf.Graph().as_default() as g, tf.device('/cpu:0'):
# Placeholders for input, output and dropout
input_x = tf.placeholder(tf.int32, [None, OPTION.SEQUENCE_LEN, OPTION.SENT_LEN], name="input_x")
input_y = tf.placeholder(tf.int32, [None, OPTION.NUM_CLASSES], name="input_y")
han = MODEL.Model(sequence_length = OPTION.SEQUENCE_LEN, sent_length = OPTION.SENT_LEN,
num_classes=OPTION.NUM_CLASSES,
vocab_size=None,
embedding_size=OPTION.EMEBEDDING_DIMENSION,
Word2vec=True, Trainable=False)
# inference model.
logits, _ = han.inference(input_x, eval_data=True)
# Calculate loss.
loss = myTF.calculate_cross_entropy_loss(logits, input_y)
# get model paramaters
# paramaters_list_reshape = han.get_paramaters_list_reshape()
# Restore the moving average version of the learned variables for eval. # ?????????????????????????
variable_averages = tf.train.ExponentialMovingAverage(OPTION.MOVING_AVERAGE_DECAY)
variables_to_restore = variable_averages.variables_to_restore()
saver = tf.train.Saver(variables_to_restore)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.summary.merge_all()
summary_writer = tf.summary.FileWriter(OPTION.EVAL_DIR, g)
# Start running operations on the Graph. allow_soft_placement must be set to
# True to build towers on GPU, as some of the ops do not have GPU implementations.
with tf.Session(config=tf.ConfigProto(
allow_soft_placement=FLAGS.allow_soft_placement,
log_device_placement=FLAGS.log_device_placement)) as sess:
if os.path.exists(os.path.join(OPTION.EVAL_DIR, 'model.ckpt-best.index')):
# new_saver = tf.train.import_meta_graph(
# os.path.join(OPTION.TRAIN_DIR, 'model.ckpt-' + checkpoint + '.meta'))
saver.restore(sess,
os.path.join(OPTION.EVAL_DIR, 'model.ckpt-best'))
else:
print('No checkpoint file found')
return
max_steps_per_epoch = int(math.ceil( trainDataSet.get_dataset_size() / float(OPTION.EVAL_BATCH_SIZE)))
total_predicted_value = []
for step in range(max_steps_per_epoch):
train_data, train_label = trainDataSet.next_batch(OPTION.EVAL_BATCH_SIZE)
predicted_value = sess.run(loss,
feed_dict={input_x: train_data, input_y: train_label})
total_predicted_value.append(predicted_value)
# test_data, test_label = evalDataSet.next_batch(OPTION.EVAL_BATCH_SIZE)
summary = tf.Summary()
# summary.ParseFromString(sess.run(summary_op, feed_dict={input_x: test_data, input_y: test_label}))
total_predicted_value = np.concatenate(total_predicted_value,axis=0)
assert trainDataSet.get_dataset_size() == total_predicted_value.shape[0], 'sample_count error!'
detail_filename = os.path.join(OPTION.MODELPARA_DIR, 'loss_%d_%d' %(time,model_time))
if os.path.exists(detail_filename):
os.remove(detail_filename)
np.savetxt(detail_filename, total_predicted_value, fmt='%f')