1,
processor=data_processor,
randomize=True,
augment=False)
data_loader.start()
config = tf.ConfigProto()
config.gpu_options.allow_growth = False
config.allow_soft_placement = False
config.log_device_placement = False
with tf.Session(config=config) as sess:
saver = tf.train.Saver(write_version=tf.train.SaverDef.V1)
saver.restore(sess, saved_model)
batch = data_loader.get_batch(1)
filenames = batch[0]
input_images = batch[1]
result = sess.run([m.result],
feed_dict={
m.input_image: input_images,
m.is_train: False
})
self.filename = os.path.splitext(
os.path.basename(filename))[0] + '_' + type + '_' + model + '.jpg'
result = result[0].reshape((1500, 1500))
misc.imsave("segmentations/{0}".format(self.filename), result)
data_loader.stop()
label_image = tiff.imread('label_images/{0}'.format(filename[:-1]))
label_image = label_image[:, :, :1] / 255
if config.augment:
angle = randint(0, 360)
input_image = ndimage.rotate(input_image, angle, reshape=False)
label_image = ndimage.rotate(label_image, angle, reshape=False)
input_image = (input_image - np.mean(input_image)) / np.std(input_image)
return (filename, input_image, label_image)
test_label_files = label_files[:5]
test_loader = Loader(test_label_files, 5, processor=data_processor)
test_loader.start()
test_batch = test_loader.get_batch(5)
test_loader.stop()
batch_size = 2
train_label_files = label_files[5:]
train_loader = Loader(train_label_files,
batch_size * 4,
processor=data_processor,
randomize=True,
augment=True)
train_loader.start()
shouldLoad = False
modelName = m.modelName + "-x2-msr"
config = tf.ConfigProto()
type = FLAGS.type
if FLAGS.type == 'building':
label_files = [filename for filename in listdir('building_input_images')]
else:
label_files = [filename for filename in listdir('road_input_images')]
if os.path.isdir("test-results-{0}-{1}".format(type, modelName)) == False:
os.mkdir("test-results-{0}-{1}".format(type, modelName))
label_files.sort()
test_label_files = label_files[:5]
test = Loader(test_label_files, 5, processor=data_processor)
test.start()
test_batch = test.get_batch(1)
test.stop()
batch_size = FLAGS.batch_size
train_label_files = label_files[batch_size:]
train = Loader(train_label_files,
batch_size * 5,
processor=data_processor,
randomize=True,
rotate=True)
train.start()
config = tf.ConfigProto()
config.gpu_options.allow_growth = False
config.allow_soft_placement = False
config.log_device_placement = False
