def main():
# 入力データのshape定義
x = nn.variable.Variable(
[BATCH_SIZE, IMAGE_DEPTH * IMAGE_WIDTH * IMAGE_HEIGHT])
# ラベルのshape定義
t = nn.variable.Variable([BATCH_SIZE, LABEL_NUM])
pred = convolution(x)
loss_ = loss(pred, t)
solver = S.Adam()
solver.set_parameters(nn.get_parameters())
data = InputData()
for i in range(NUM_STEP):
# 100STEP毎にテスト実施
if i % 100 == 0:
l = 0
a = 0
for k, (t.d, x.d) in enumerate(data.test_data()):
loss_.forward()
l += loss_.d
a += accuracy(pred, t)
print("Step: %05d Test loss: %0.05f Test accuracy: %0.05f" %
(i, l / k, a / k))
t.d, x.d = data.next_batch()
loss_.forward()
solver.zero_grad()
loss_.backward()
solver.weight_decay(DECAY_RATE)
solver.update()
if i % 10 == 0:
print("Step: %05d Train loss: %0.05f Train accuracy: %0.05f" %
(i, loss_.d, accuracy(pred, t)))
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))