def _save_preprocessed_img(
self, sess, img_preprocessed, img_ph, img_np, img_name
):
"""Save preprocessed image when necessary
Parameters
----------
sess : tf.Session
Session is required to perform compute
img_preprocessed: tf.Tensor
Tensor graph for preprocessing
img_ph: tf.Tensor
Tensor input placeholder
img_np: np.ndarray
N-dimensional array with data
img_name: string
Image file name
"""
# Create a numpy array of the cropped image
img_cropped_resized_np = sess.run(
img_preprocessed, # graph for preprocessing images
feed_dict={img_ph: img_np}, # numpy input
)
output_path = os.path.join(self.output, '{}.jpg'.format(img_name))
image_utils.save_np_image(img_cropped_resized_np, output_path)
self.logger.debug('Image saved at {}'.format(output_path))
def main(unused_argv=None):
# Load image
image = np.expand_dims(image_utils.load_np_image(FLAGS.input_image), 0)
which_styles = ast.literal_eval(FLAGS.which_styles)
with tf.Graph().as_default(), tf.Session() as sess:
stylized_images = model.transform(
tf.concat(0, [image for _ in range(len(which_styles))]),
normalizer_params={
'labels': tf.constant(which_styles),
'num_categories': FLAGS.num_styles,
'center': True,
'scale': True
})
model_saver = tf.train.Saver(tf.all_variables())
checkpoint = FLAGS.checkpoint
if tf.gfile.IsDirectory(checkpoint):
checkpoint = tf.train.latest_checkpoint(checkpoint)
tf.logging.info(
'loading latest checkpoint file: {}'.format(checkpoint))
model_saver.restore(sess, checkpoint)
stylized_images = stylized_images.eval()
for which, stylized_image in zip(which_styles, stylized_images):
image_utils.save_np_image(
stylized_image[None, ...],
'{}/{}_{}.png'.format(FLAGS.output_dir, FLAGS.output_basename,
which))
def _multiple_images(input_image, which_styles, output_dir):
"""Stylizes an image into a set of styles and writes them to disk."""
with tf.Graph().as_default(), tf.Session() as sess:
stylized_images = model.transform(
tf.concat([input_image for _ in range(len(which_styles))], 0),
normalizer_params={
'labels': tf.constant(which_styles),
'num_categories': FLAGS.num_styles,
'center': True,
'scale': True})
_load_checkpoint(sess, FLAGS.checkpoint)
stylized_images = stylized_images.eval()
for which, stylized_image in zip(which_styles, stylized_images):
image_utils.save_np_image(
stylized_image[None, ...],
'{}/{}_{}.png'.format(output_dir, FLAGS.output_basename, which))
def _multiple_images(input_image, which_styles, output_dir):
"""Stylizes an image into a set of styles and writes them to disk."""
with tf.Graph().as_default(), tf.Session() as sess:
stylized_images = model.transform(
tf.concat_v2([input_image for _ in range(len(which_styles))], 0),
normalizer_params={
'labels': tf.constant(which_styles),
'num_categories': FLAGS.num_styles,
'center': True,
'scale': True})
_load_checkpoint(sess, FLAGS.checkpoint)
stylized_images = stylized_images.eval()
for which, stylized_image in zip(which_styles, stylized_images):
image_utils.save_np_image(
stylized_image[None, ...],
'{}/{}_{}.png'.format(output_dir, FLAGS.output_basename, which))
def _multiple_styles(input_image, which_styles, output_dir):
"""Stylizes image into a linear combination of styles and writes to disk."""
with tf.Graph().as_default(), tf.Session() as sess:
mixture = _style_mixture(which_styles, FLAGS.num_styles)
stylized_images = model.transform(
input_image,
normalizer_fn=ops.weighted_instance_norm,
normalizer_params={
'weights': tf.constant(mixture),
'num_categories': FLAGS.num_styles,
'center': True,
'scale': True})
_load_checkpoint(sess, FLAGS.checkpoint)
stylized_image = stylized_images.eval()
image_utils.save_np_image(
stylized_image,
os.path.join(output_dir, '%s_%s.png' % (
FLAGS.output_basename, _describe_style(which_styles))))
def _multiple_styles(input_image, which_styles, output_dir):
"""Stylizes image into a linear combination of styles and writes to disk."""
with tf.Graph().as_default(), tf.Session() as sess:
mixture = _style_mixture(which_styles, FLAGS.num_styles)
stylized_images = model.transform(
input_image,
normalizer_fn=ops.weighted_instance_norm,
normalizer_params={
'weights': tf.constant(mixture),
'num_categories': FLAGS.num_styles,
'center': True,
'scale': True})
_load_checkpoint(sess, FLAGS.checkpoint)
stylized_image = stylized_images.eval()
image_utils.save_np_image(
stylized_image,
os.path.join(output_dir, '%s_%s.png' % (
FLAGS.output_basename, _describe_style(which_styles))))
def main(unused_argv=None):
tf.logging.set_verbosity(tf.logging.INFO)
if not tf.gfile.Exists(FLAGS.output_dir):
tf.gfile.MkDir(FLAGS.output_dir)
with tf.Graph().as_default(), tf.Session() as sess:
# Defines place holder for the style image.
style_img_ph = tf.placeholder(tf.float32, shape=[None, None, 3])
if FLAGS.style_square_crop:
style_img_preprocessed = image_utils.center_crop_resize_image(
style_img_ph, FLAGS.style_image_size)
else:
style_img_preprocessed = image_utils.resize_image(style_img_ph,
FLAGS.style_image_size)
# Defines place holder for the content image.
content_img_ph = tf.placeholder(tf.float32, shape=[None, None, 3])
if FLAGS.content_square_crop:
content_img_preprocessed = image_utils.center_crop_resize_image(
content_img_ph, FLAGS.image_size)
else:
content_img_preprocessed = image_utils.resize_image(
content_img_ph, FLAGS.image_size)
# Defines the model.
stylized_images, _, _, bottleneck_feat = build_model.build_model(
content_img_preprocessed,
style_img_preprocessed,
trainable=False,
is_training=False,
inception_end_point='Mixed_6e',
style_prediction_bottleneck=100,
adds_losses=False)
if tf.gfile.IsDirectory(FLAGS.checkpoint):
checkpoint = tf.train.latest_checkpoint(FLAGS.checkpoint)
else:
checkpoint = FLAGS.checkpoint
tf.logging.info('loading latest checkpoint file: {}'.format(checkpoint))
init_fn = slim.assign_from_checkpoint_fn(checkpoint,
slim.get_variables_to_restore())
sess.run([tf.local_variables_initializer()])
init_fn(sess)
# Gets the list of the input style images.
style_img_list = tf.gfile.Glob(FLAGS.style_images_paths)
if len(style_img_list) > FLAGS.maximum_styles_to_evaluate:
np.random.seed(1234)
style_img_list = np.random.permutation(style_img_list)
style_img_list = style_img_list[:FLAGS.maximum_styles_to_evaluate]
# Gets list of input content images.
content_img_list = tf.gfile.Glob(FLAGS.content_images_paths)
for content_i, content_img_path in enumerate(content_img_list):
content_img_np = image_utils.load_np_image_uint8(content_img_path)[:, :, :
3]
content_img_name = os.path.basename(content_img_path)[:-4]
# Saves preprocessed content image.
inp_img_croped_resized_np = sess.run(
content_img_preprocessed, feed_dict={
content_img_ph: content_img_np
})
image_utils.save_np_image(inp_img_croped_resized_np,
os.path.join(FLAGS.output_dir,
'%s.jpg' % (content_img_name)))
# Computes bottleneck features of the style prediction network for the
# identity transform.
identity_params = sess.run(
bottleneck_feat, feed_dict={style_img_ph: content_img_np})
for style_i, style_img_path in enumerate(style_img_list):
if style_i > FLAGS.maximum_styles_to_evaluate:
break
style_img_name = os.path.basename(style_img_path)[:-4]
style_image_np = image_utils.load_np_image_uint8(style_img_path)[:, :, :
3]
if style_i % 10 == 0:
tf.logging.info('Stylizing (%d) %s with (%d) %s' %
(content_i, content_img_name, style_i,
style_img_name))
# Saves preprocessed style image.
style_img_croped_resized_np = sess.run(
style_img_preprocessed, feed_dict={
style_img_ph: style_image_np
})
image_utils.save_np_image(style_img_croped_resized_np,
os.path.join(FLAGS.output_dir,
'%s.jpg' % (style_img_name)))
# Computes bottleneck features of the style prediction network for the
# given style image.
style_params = sess.run(
bottleneck_feat, feed_dict={style_img_ph: style_image_np})
interpolation_weights = ast.literal_eval(FLAGS.interpolation_weights)
# Interpolates between the parameters of the identity transform and
# style parameters of the given style image.
for interp_i, wi in enumerate(interpolation_weights):
stylized_image_res = sess.run(
stylized_images,
feed_dict={
bottleneck_feat:
identity_params * (1 - wi) + style_params * wi,
content_img_ph:
content_img_np
})
# Saves stylized image.
image_utils.save_np_image(
stylized_image_res,
os.path.join(FLAGS.output_dir, '%s_stylized_%s_%d.jpg' %
(content_img_name, style_img_name, interp_i)))
def main(unused_argv=None):
print('timer start')
start = time.time()
words = [
'布', '植物', 'ガラス', '革', '金属', '紙', 'プラスチック', '石', '水', '木', '樹脂',
'アクリル', 'アルミニウム', '牛皮', 'レンガ', '絹'
]
config = tf.ConfigProto(gpu_options=tf.GPUOptions(allow_growth=True))
sess = tf.Session(config=config)
tf.logging.set_verbosity(tf.logging.INFO)
if not tf.gfile.Exists(FLAGS.output_dir):
tf.gfile.MkDir(FLAGS.output_dir)
with tf.Graph().as_default(), sess:
# Defines place holder for the style image.
style_img_ph = tf.placeholder(tf.float32, shape=[None, None, 3])
if FLAGS.style_square_crop:
style_img_preprocessed = image_utils.center_crop_resize_image(
style_img_ph, FLAGS.style_image_size)
else:
style_img_preprocessed = image_utils.resize_image(
style_img_ph, FLAGS.style_image_size)
# Defines place holder for the content image.
content_img_ph = tf.placeholder(tf.float32, shape=[None, None, 3])
if FLAGS.content_square_crop:
content_img_preprocessed = image_utils.center_crop_resize_image(
content_img_ph, FLAGS.image_size)
else:
content_img_preprocessed = image_utils.resize_image(
content_img_ph, FLAGS.image_size)
# Defines the model.
stylized_images, _, _, bottleneck_feat = build_model.build_model(
content_img_preprocessed,
style_img_preprocessed,
trainable=False,
is_training=False,
inception_end_point='Mixed_6e',
style_prediction_bottleneck=100,
adds_losses=False)
if tf.gfile.IsDirectory(FLAGS.checkpoint):
checkpoint = tf.train.latest_checkpoint(FLAGS.checkpoint)
else:
checkpoint = FLAGS.checkpoint
tf.logging.info(
'loading latest checkpoint file: {}'.format(checkpoint))
init_fn = slim.assign_from_checkpoint_fn(
checkpoint, slim.get_variables_to_restore())
sess.run([tf.local_variables_initializer()])
init_fn(sess)
# Gets the list of the input style images.
style_img_list = tf.gfile.Glob(FLAGS.style_images_paths)
if len(style_img_list) > FLAGS.maximum_styles_to_evaluate:
np.random.seed(1234)
style_img_list = np.random.permutation(style_img_list)
style_img_list = style_img_list[:FLAGS.maximum_styles_to_evaluate]
# Gets list of input content images.
content_img_list = tf.gfile.Glob(FLAGS.content_images_paths)
j = -1
for content_i, content_img_path in enumerate(content_img_list):
j += 1
content_img_np = image_utils.load_np_image_uint8(
content_img_path)[:, :, :3]
content_img_name = os.path.basename(content_img_path)[:-4]
# Saves preprocessed content image.
inp_img_croped_resized_np = sess.run(
content_img_preprocessed,
feed_dict={content_img_ph: content_img_np})
image_utils.save_np_image(
inp_img_croped_resized_np,
os.path.join(FLAGS.output_dir, '%s.jpg' % (content_img_name)))
if FLAGS.color_preserve is True:
print('color preserve mode!')
# convert content iamge to ycc from bgr
height, width, channels = inp_img_croped_resized_np[
0].shape[:3]
# print(inp_img_croped_resized_np)
wgap = 4 - (
width % 4
) # fuking translater made some gaps because of decoder
hgap = 4 - (height % 4)
inp_img_croped_resized_np = inp_img_croped_resized_np * 255
content_img_np_ycc = cv2.cvtColor(inp_img_croped_resized_np[0],
cv2.COLOR_RGB2YCR_CB)
# print(content_img_np_ycc)
zeros = np.zeros((height, width), content_img_np_ycc.dtype)
zeros = zeros + 128 # YCC's zero is center of 255
tmp = cv2.cvtColor(content_img_np_ycc, cv2.COLOR_YCR_CB2BGR)
cv2.imwrite("gray.jpg", tmp)
# print(zeros)
Ycontent, Crcontent, Cbcontent = cv2.split(content_img_np_ycc)
# print(Ycontent.shape, Crcontent.shape, Cbcontent.shape, zeros.shape)
# print(Crcontent)
# print(content_img_np_ycc)
# content_img_np_ycc_y = cv2.merge((Y, zeros, zeros))
# content_img_np_gry = cv2.cvtColor(content_img_np_ycc_y, cv2.COLOR_YCR_CB2RGB)
# print(content_img_np_gry)
# cv2.imwrite("gray.jpg", content_img_np_gry)
# print(np.shape(content_img_np))
# content_img_np = content_img_np_gry
# Computes bottleneck features of the style prediction network for the
# identity transform.
identity_params = sess.run(
bottleneck_feat, feed_dict={style_img_ph: content_img_np})
i = 0
for word in words:
# word = words[i]
print(word)
i += 1
# if style_i > FLAGS.maximum_styles_to_evaluate:
# break
# style_img_name = os.path.basename(style_img_path)[:-4]
# style_image_np = image_utils.load_np_image_uint8(style_img_path)[:, :, :
# 3]
# if style_i % 10 == 0:
# tf.logging.info('Stylizing (%d) %s with (%d) %s' %
# (content_i, content_img_name, style_i,
# style_img_name))
# Saves preprocessed style image.
# style_img_croped_resized_np = sess.run(
# style_img_preprocessed, feed_dict={
# style_img_ph: style_image_np
# })
# image_utils.save_np_image(style_img_croped_resized_np,
# os.path.join(FLAGS.output_dir,
# '%s.jpg' % (style_img_name)))
# Computes bottleneck features of the style prediction network for the
# given style image.
# style_params_ori = sess.run(
# bottleneck_feat, feed_dict={style_img_ph: style_image_np})
# print(np.shape(style_params))
picklename = 'params/{}_{}.pickle'.format(word, j)
f = open(picklename, 'r')
style_params = pickle.load(f)
# print(style_params)
# print('diff of original para and made para:')
# print(style_params_ori - style_params)
interpolation_weights = ast.literal_eval(
FLAGS.interpolation_weights)
# Interpolates between the parameters of the identity transform and
# style parameters of the given style image.
for interp_i, wi in enumerate(interpolation_weights):
stylized_image_res = sess.run(
stylized_images,
feed_dict={
bottleneck_feat:
identity_params * (1 - wi) + style_params * wi,
content_img_ph:
content_img_np
})
if FLAGS.color_preserve is True:
# print(stylized_image_res[0].shape)
stylized_image_res_ycc = cv2.cvtColor(
stylized_image_res[0], cv2.COLOR_RGB2YCR_CB)
Ystylized, Crstylized, Cbstylized = cv2.split(
stylized_image_res_ycc)
if wgap == 4: # if original image is just fit
Ystylized_crop = Ystylized * 255
else:
Ystylized_crop = Ystylized[:, :-1 * wgap] * 255
if hgap == 4:
Ystylized_crop = Ystylized_crop
else:
Ystylized_crop = Ystylized_crop[:-1 * hgap, :]
print(Ystylized_crop.shape, Cbcontent.shape)
# print(wgap)
swapped_ycc = cv2.merge(
(Ystylized_crop, Crcontent, Cbcontent))
# print(swapped_ycc)
stylized_image_res = cv2.cvtColor(
swapped_ycc, cv2.COLOR_YCR_CB2BGR)
# print(stylized_image_res)
cv2.imwrite(
os.path.join(
FLAGS.output_dir, '%s_stylized_%s_%d.jpg' %
(content_img_name, word, interp_i)),
stylized_image_res)
# Saves stylized image.
else:
image_utils.save_np_image(
stylized_image_res,
os.path.join(
FLAGS.output_dir, '%s_stylized_%s_%d.jpg' %
(content_img_name, word, interp_i)))
elapsed_time = time.time() - start
print("timer stop")
print(elapsed_time)
