def setUp(self):
self.train_data, self.validation_data = \
prepare_data.load_data(
self.IMAGE_DIR,
self.SEG_DIR,
n_class=2,
train_val_rate=0.9
)
self.data = prepare_data.generate_data(self.IMAGE_DIR, self.SEG_DIR, 1)
def test_generate_test_dataset(self):
test_data, _ = prepare_data.load_data(self.IMAGE_DIR,
None,
n_class=2,
train_val_rate=0.9)
test_images = prepare_data.generate_data(*test_data, 1)
for img, seg in test_images:
self.assertEqual(len(seg), 0)
break
def validation(self, sess, output):
val_image = prepare_data.load_data(self.VALIDATION_DIR,
None,
n_class=2,
train_val_rate=1)[0]
data = prepare_data.generate_data(*val_image, batch_size=1)
for Input, _ in data:
result = sess.run(output,
feed_dict={
self.X: Input,
self.is_training: None
})
break
result = np.argmax(result[0], axis=2)
ident = np.identity(3, dtype=np.int8)
result = ident[result] * 255
plt.imshow((Input[0] * 255).astype(np.int16))
plt.imshow(result, alpha=0.2)
plt.show()
def test_batch_generation(self):
batch_data = prepare_data.generate_data(*self.train_data, 5)
for img, seg in batch_data:
self.assertEqual(len(img), 5)
self.assertEqual(len(seg), 5)
break
def train(self, parser):
"""
training operation
argument of this function are given by functions in prepare_data.py
Parameters
----------
parser:
the paser that has some options
"""
epoch = parser.epoch
l2 = parser.l2
batch_size = parser.batch_size
train_val_rate = parser.train_rate
output = self.UNet(l2_reg=l2, is_training=self.is_training)
loss = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits_v2(labels=self.y,
logits=output))
update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
with tf.control_dependencies(update_ops):
train_ops = tf.train.AdamOptimizer(
parser.learning_rate).minimize(loss)
init = tf.global_variables_initializer()
saver = tf.train.Saver(max_to_keep=100)
all_train, all_val = prepare_data.load_data(
self.IMAGE_DIR,
self.SEGMENTED_DIR,
n_class=2,
train_val_rate=train_val_rate)
with tf.Session() as sess:
init.run()
for e in range(epoch):
data = prepare_data.generate_data(*all_train, batch_size)
val_data = prepare_data.generate_data(*all_val,
len(all_val[0]))
for Input, Teacher in data:
sess.run(train_ops,
feed_dict={
self.X: Input,
self.y: Teacher,
self.is_training: True
})
ls = loss.eval(feed_dict={
self.X: Input,
self.y: Teacher,
self.is_training: None
})
for val_Input, val_Teacher in val_data:
val_loss = loss.eval(
feed_dict={
self.X: val_Input,
self.y: val_Teacher,
self.is_training: None
})
print(f'epoch #{e + 1}, loss = {ls}, val loss = {val_loss}')
if e % 100 == 0:
saver.save(sess, f"./params/model_{e + 1}epochs.ckpt")
self.validation(sess, output)