def evaluate():
'''テストデータに対する評価を実施する関数
'''
data = InputData(test_data_path=FLAGS.test_data, train=False)
input_ph = tf.placeholder(tf.int32, [None, data.max_len])
training_ph = tf.placeholder(tf.bool, [])
label_ph = tf.placeholder(tf.float32, [None, data.num_category])
with tf.Session() as sess:
output = convolution(input_ph, training_ph, data.num_chars,
data.num_category)
values, indices = tf.nn.top_k(output, k=10)
saver = tf.train.Saver()
load_checkpoint(sess, saver)
with open(FLAGS.output_dir + '/evaluate.tsv', 'w') as f:
writer = csv.writer(f, delimiter='\t')
for test_labels, test_texts, unique_ids, item_names in data.next_batch_evaluation_data(
):
values_, indices_ = sess.run([values, indices],
feed_dict={
input_ph: test_texts,
training_ph: False
})
for (value, index, test_label, unique_id,
item_name) in zip(values_, indices_, test_labels,
unique_ids, item_names):
row = [unique_id] + [
data.category_dict[np.argmax(test_label)]
] + [data.chars_to_unknown(item_name)
] + list(value) + list(
map(lambda x: data.category_dict[x], index)) + [
index[0] == np.argmax(test_label)
] + [np.argmax(test_label) in index[0:3]]
writer.writerow(row)
num_records = len(
open(FLAGS.output_dir + '/evaluate.tsv', 'r').readlines())
with open(FLAGS.output_dir + '/evaluate.tsv', 'r') as f:
reader = csv.reader(f, delimiter='\t')
accuracy_count = [(line[23], line[24]) for line in reader]
accuracy_top1 = len(
list(filter(lambda x: x[0] == 'True',
accuracy_count))) / num_records
accuracy_top3 = len(
list(filter(lambda x: x[1] == 'True',
accuracy_count))) / num_records
with open(FLAGS.output_dir + '/test_accuracy.tsv', 'w') as f:
writer = csv.writer(f, delimiter='\t')
writer.writerow([accuracy_top1, accuracy_top3])
def train():
'''訓練を実施する関数
'''
with tf.Graph().as_default():
print('Loading data...')
data = InputData(train_data_path=FLAGS.train_data,
validation_data_path=FLAGS.validation_data,
batch_size=FLAGS.batch_size)
input_ph = tf.placeholder(tf.int32, [None, data.max_len])
training_ph = tf.placeholder(tf.bool, [])
label_ph = tf.placeholder(tf.float32, [None, data.num_category])
# summary用のplace holder
summary_ph = tf.placeholder(tf.float32, [3])
config = tf.ConfigProto(gpu_options=tf.GPUOptions(allow_growth=True))
with tf.Session(config=config) as sess:
convolution_op = convolution(input_ph, training_ph, data.num_chars,
data.num_category)
loss_op = loss(convolution_op, label_ph)
train_op = minimize(loss_op)
accuracy_op = accuracy(convolution_op, label_ph)
top_3_accuracy_op = top_3_accuracy(convolution_op, label_ph)
summary_writer = tf.summary.FileWriter(FLAGS.log_dir, sess.graph)
write_validation_summary_op = write_validation_summary(summary_ph)
for vals in tf.trainable_variables():
tf.summary.histogram(vals.name, vals)
summary_op = tf.summary.merge_all()
saver = tf.train.Saver()
load_checkpoint(sess, saver)
for i in range(FLAGS.max_step):
label_, text_ = data.next_batch()
_ = sess.run(train_op,
feed_dict={
input_ph: text_,
label_ph: label_,
training_ph: True
})
if i % 100 == 0:
loss_, accuracy_, top_3_accuracy_ = sess.run(
[loss_op, accuracy_op, top_3_accuracy_op],
feed_dict={
input_ph: text_,
label_ph: label_,
training_ph: False
})
print(
'global step: %04d, train loss: %01.7f, train accuracy_top_1 %01.5f train accuracy_top_3 %01.5f'
% (i, loss_, accuracy_, top_3_accuracy_))
if i % 1000 == 0:
validation_loss = []
validation_top_3_accuracy = []
validation_top_1_accuracy = []
for validation_label, validation_text in data.next_batch_evaluation_data(
):
loss_, top_3_accuracy_, accuracy_ = sess.run(
[loss_op, top_3_accuracy_op, accuracy_op],
feed_dict={
input_ph: validation_text,
label_ph: validation_label,
training_ph: False
})
validation_loss.append(loss_)
validation_top_1_accuracy.append(accuracy_)
validation_top_3_accuracy.append(top_3_accuracy_)
loss_ = sum(validation_loss) / len(validation_loss)
accuracy_ = sum(validation_top_1_accuracy) / len(
validation_top_1_accuracy)
top_3_accuracy_ = sum(validation_top_3_accuracy) / len(
validation_top_3_accuracy)
print(
'Validation loss: %s validation accuracy_top_1: %01.5f validation accuracy_top_3: %01.5f'
% (loss_, accuracy_, top_3_accuracy_))
saver.save(sess, FLAGS.checkpoint_dir, global_step=i)
# サマリー出力
_, summary_str = sess.run(
[write_validation_summary_op, summary_op],
feed_dict={
input_ph: text_,
label_ph: label_,
training_ph: False,
summary_ph: [loss_, accuracy_, top_3_accuracy_]
})
summary_writer.add_summary(summary_str, i)
ru = resource.getrusage(resource.RUSAGE_SELF)
print('Max memory usage(byte): ' + str(ru.ru_maxrss))