def get_style_features(FLAGS):
"""
For the "style_image", the preprocessing step is:
1. Resize the shorter side to FLAGS.image_size
2. Apply central crop
"""
config = tf.ConfigProto()
config.gpu_options.allow_growth=True
with tf.Graph().as_default(), tf.Session(config=config) as sess:
network_fn = nets_factory.get_network_fn(
FLAGS.loss_model,
num_classes=1,
is_training=False)
image_preprocessing_fn = preprocessing_factory.get_preprocessing(
FLAGS.loss_model,
is_training=False)
images = tf.expand_dims(utils.get_image(FLAGS.style_image, FLAGS.image_size, FLAGS.image_size, image_preprocessing_fn), 0)
_, endpoints_dict = network_fn(images)
features = []
for layer in FLAGS.style_layers:
feature = endpoints_dict[layer]
features.append(gram(feature))
init_func = utils._get_init_fn(FLAGS)
init_func(sess)
if os.path.exists('generated') is False:
os.makedirs('generated')
save_file = 'generated/target_style_' + FLAGS.naming + '.jpg'
with open(save_file, 'wb') as f:
target_image = unprocess_image(images[0, :])
value = tf.image.encode_jpeg(tf.cast(target_image, tf.uint8))
f.write(sess.run(value))
tf.logging.info('Target style pattern is saved to: %s.' % save_file)
return sess.run(features)
python类get_image()的实例源码
def _read_by_function(self, filename):
array = get_image(filename, 108, is_crop=True, resize_w=self.output_size,
is_grayscale=False)
real_images = np.array(array)
return real_images
def main():
parser = get_parser()
try:
args = parser.parse_args()
except:
sys.exit(0)
# if environment logging variable not set, make silent
if args.debug == False:
os.environ['MESSAGELEVEL'] = "CRITICAL"
# Tell the user what is going to be used, in case is incorrect
from logman import bot
from predict_image import Model
from utils import get_image, write_json
print("\n*** Starting Bone Age Prediction ****")
# Get the gender
is_male = True
if args.gender == "F":
is_male = False
# If the user has not provided an image, use an example
image = args.image
if image == None:
print("No image selected, will use provided example...")
from utils import select_example_image
image = select_example_image(start=0,end=9)
is_male = True # all examples male
# Print parameters for user
bot.logger.debug("is_male: %s", is_male)
bot.logger.debug("image: %s", image)
bot.logger.debug("height: %s", args.height)
bot.logger.debug("width: %s", args.width)
# Get the array of data (uint8) - H/W should be set to 256
image_path = image
image = get_image(image_path=image,
warped_height=args.height,
warped_width=args.width)
print("Building model, please wait.")
model = Model()
result = model.get_result(image=image,
image_path=image_path,
is_male=is_male)
print('Predicted Age : %d Months' %result['predicted_age'])
print('Weighted Prediction : %f Months' %result['predicted_weight'])
if args.output != None:
output = write_json(json_object=result,
filename=args.output)
bot.logger.debug('Result written to %s',args.output)
def main(argv):
pattern = "/home/ian/imagenet/ILSVRC2012_img_train_t1_t2/n*/*JPEG"
files = glob(pattern)
assert len(files) > 0
assert len(files) > 1000000, len(files)
dirs = glob("/home/ian/imagenet/ILSVRC2012_img_train_t1_t2/n*")
assert len(dirs) == 1000, len(dirs)
dirs = [d.split('/')[-1] for d in dirs]
dirs = sorted(dirs)
str_to_int = dict(zip(dirs, range(len(dirs))))
outfile = '/media/NAS_SHARED/imagenet/imagenet_train_labeled_' + str(IMSIZE) + '.tfrecords'
writer = tf.python_io.TFRecordWriter(outfile)
for i, f in enumerate(files):
print i
image = get_image(f, IMSIZE, is_crop=True, resize_w=IMSIZE)
image = colorize(image)
assert image.shape == (IMSIZE, IMSIZE, 3)
image += 1.
image *= (255. / 2.)
image = image.astype('uint8')
#print image.min(), image.max()
# from pylearn2.utils.image import save
# save('foo.png', (image + 1.) / 2.)
image_raw = image.tostring()
class_str = f.split('/')[-2]
label = str_to_int[class_str]
if i % 1 == 0:
print i, '\t',label
example = tf.train.Example(features=tf.train.Features(feature={
'height': _int64_feature(IMSIZE),
'width': _int64_feature(IMSIZE),
'depth': _int64_feature(3),
'image_raw': _bytes_feature(image_raw),
'label': _int64_feature(label)
}))
writer.write(example.SerializeToString())
writer.close()
def main(_):
config = tf.ConfigProto()
config.gpu_options.allow_growth=True
image = Image.open(FLAGS.image_file)
image = np.asarray(image)
height = image.shape[0]
width = image.shape[1]
channel = image.shape[2]
tf.logging.info('Image size: %dx%dx%d' % (width, height, channel))
with tf.Graph().as_default():
with tf.Session(config=config).as_default() as sess:
image_preprocessing_fn = preprocessing_factory.get_preprocessing(
FLAGS.loss_model,
is_training=False)
rawimage = utils.get_image(FLAGS.image_file, 256, 256, image_preprocessing_fn)
rawimage = tf.expand_dims(rawimage, 0)
rawimage = tf.to_float(rawimage)
if FLAGS.model_type == "transform":
generated = transform_model.net(rawimage, training=False)
elif FLAGS.model_type == "super":
generated = sr_model.net(rawimage, scale=FLAGS.image_scale, training=False)
elif FLAGS.model_type == "alipay":
generated = al_model.net(rawimage, training=False)
generated = tf.squeeze(generated, [0])
saver = tf.train.Saver(tf.global_variables())
sess.run([tf.global_variables_initializer(), tf.local_variables_initializer()])
FLAGS.model_file = os.path.abspath(FLAGS.model_file)
saver.restore(sess, FLAGS.model_file)
start_time = time.time()
generated = sess.run(generated)
print(generated.shape)
end_time = time.time()
tf.logging.info('Elapsed time: %fs' % (end_time - start_time))
if FLAGS.same_shape:
generated = tf.image.resize_images(generated, [height, width])
generated = tf.cast(generated, tf.uint8)
generated_file = 'generated/aares_%s.jpg' % (FLAGS.model_type)
if os.path.exists('generated') is False:
os.makedirs('generated')
with open(generated_file, 'wb') as img:
img.write(sess.run(tf.image.encode_jpeg(generated)))
tf.logging.info('generated Image size: %s' % (generated.get_shape()))
tf.logging.info('Done. Please check %s.' % generated_file)
