def main(unused_argv=None): with tf.Graph().as_default(): # Force all input processing onto CPU in order to reserve the GPU for the # forward inference and back-propagation. device = '/cpu:0' if not FLAGS.ps_tasks else '/job:worker/cpu:0' with tf.device( tf.train.replica_device_setter(FLAGS.ps_tasks, worker_device=device)): inputs, _ = image_utils.imagenet_inputs(FLAGS.batch_size, FLAGS.image_size) # Load style images and select one at random (for each graph execution, a # new random selection occurs) style_images, style_labels, \ style_gram_matrices = image_utils.style_image_inputs( os.path.expanduser(FLAGS.style_dataset_file), batch_size=FLAGS.batch_size, image_size=FLAGS.image_size, square_crop=True, shuffle=True) with tf.device(tf.train.replica_device_setter(FLAGS.ps_tasks)): # Process style and weight flags num_styles = FLAGS.num_styles if FLAGS.style_coefficients is None: style_coefficients = [1.0 for _ in range(num_styles)] else: style_coefficients = ast.literal_eval(FLAGS.style_coefficients) if len(style_coefficients) != num_styles: raise ValueError( 'number of style coefficients differs from number of styles' ) content_weights = ast.literal_eval(FLAGS.content_weights) style_weights = ast.literal_eval(FLAGS.style_weights) # Rescale style weights dynamically based on the current style image style_coefficient = tf.gather(tf.constant(style_coefficients), style_labels) style_weights = dict((key, style_coefficient * style_weights[key]) for key in style_weights) # Define the model stylized_inputs = model.transform(inputs, alpha=FLAGS.alpha, normalizer_params={ 'labels': style_labels, 'num_categories': num_styles, 'center': True, 'scale': True }) # Compute losses. total_loss, loss_dict = learning.total_loss( inputs, stylized_inputs, style_gram_matrices, content_weights, style_weights) for key in loss_dict: tf.summary.scalar(key, loss_dict[key]) # Adding Image summaries to the tensorboard. tf.summary.image('image/0_inputs', inputs, 3) tf.summary.image('image/1_styles', style_images, 3) tf.summary.image('image/2_styled_inputs', stylized_inputs, 3) # Set up training optimizer = tf.train.AdamOptimizer(FLAGS.learning_rate) train_op = slim.learning.create_train_op( total_loss, optimizer, clip_gradient_norm=FLAGS.clip_gradient_norm, summarize_gradients=False) # Function to restore VGG16 parameters. init_fn_vgg = slim.assign_from_checkpoint_fn( vgg.checkpoint_file(), slim.get_variables('vgg_16')) # Run training slim.learning.train(train_op=train_op, logdir=os.path.expanduser(FLAGS.train_dir), master=FLAGS.master, is_chief=FLAGS.task == 0, number_of_steps=FLAGS.train_steps, init_fn=init_fn_vgg, save_summaries_secs=FLAGS.save_summaries_secs, save_interval_secs=FLAGS.save_interval_secs)
def main(unused_argv=None): tf.logging.set_verbosity(tf.logging.INFO) with tf.Graph().as_default(): # Forces all input processing onto CPU in order to reserve the GPU for the # forward inference and back-propagation. device = '/cpu:0' if not FLAGS.ps_tasks else '/job:worker/cpu:0' with tf.device( tf.train.replica_device_setter(FLAGS.ps_tasks, worker_device=device)): # Load content images content_inputs_, _ = image_utils.imagenet_inputs( FLAGS.batch_size, FLAGS.image_size) # Loads style images. [style_inputs_, _, style_inputs_orig_] = image_utils.arbitrary_style_image_inputs( FLAGS.style_dataset_file, batch_size=FLAGS.batch_size, image_size=FLAGS.image_size, shuffle=True, center_crop=FLAGS.center_crop, augment_style_images=FLAGS.augment_style_images, random_style_image_size=FLAGS.random_style_image_size) with tf.device(tf.train.replica_device_setter(FLAGS.ps_tasks)): # Process style and content weight flags. content_weights = ast.literal_eval(FLAGS.content_weights) style_weights = ast.literal_eval(FLAGS.style_weights) # Define the model stylized_images, \ true_loss, \ _, \ bottleneck_feat = build_mobilenet_model.build_mobilenet_model( content_inputs_, style_inputs_, mobilenet_trainable=True, style_params_trainable=False, style_prediction_bottleneck=100, adds_losses=True, content_weights=content_weights, style_weights=style_weights, total_variation_weight=FLAGS.total_variation_weight, ) _, inception_bottleneck_feat = build_model.style_prediction( style_inputs_, [], [], is_training=False, trainable=False, inception_end_point='Mixed_6e', style_prediction_bottleneck=100, reuse=None, ) print('PRINTING TRAINABLE VARIABLES') for x in tf.trainable_variables(): print(x) mse_loss = tf.losses.mean_squared_error(inception_bottleneck_feat, bottleneck_feat) total_loss = mse_loss if FLAGS.use_true_loss: true_loss = FLAGS.true_loss_weight * true_loss total_loss += true_loss if FLAGS.use_true_loss: tf.summary.scalar('mse', mse_loss) tf.summary.scalar('true_loss', true_loss) tf.summary.scalar('total_loss', total_loss) tf.summary.image('image/0_content_inputs', content_inputs_, 3) tf.summary.image('image/1_style_inputs_orig', style_inputs_orig_, 3) tf.summary.image('image/2_style_inputs_aug', style_inputs_, 3) tf.summary.image('image/3_stylized_images', stylized_images, 3) mobilenet_variables_to_restore = slim.get_variables_to_restore( include=['MobilenetV2'], exclude=['global_step']) optimizer = tf.train.AdamOptimizer(FLAGS.learning_rate) train_op = slim.learning.create_train_op( total_loss, optimizer, clip_gradient_norm=FLAGS.clip_gradient_norm, summarize_gradients=False) init_fn = slim.assign_from_checkpoint_fn( FLAGS.initial_checkpoint, slim.get_variables_to_restore( exclude=['MobilenetV2', 'mobilenet_conv', 'global_step'])) init_pretrained_mobilenet = slim.assign_from_checkpoint_fn( FLAGS.mobilenet_checkpoint, mobilenet_variables_to_restore) def init_sub_networks(session): init_fn(session) init_pretrained_mobilenet(session) slim.learning.train(train_op=train_op, logdir=os.path.expanduser(FLAGS.train_dir), master=FLAGS.master, is_chief=FLAGS.task == 0, number_of_steps=FLAGS.train_steps, init_fn=init_sub_networks, save_summaries_secs=FLAGS.save_summaries_secs, save_interval_secs=FLAGS.save_interval_secs)
def main(unused_argv=None): with tf.Graph().as_default(): # Force all input processing onto CPU in order to reserve the GPU for the # forward inference and back-propagation. device = '/cpu:0' if not FLAGS.ps_tasks else '/job:worker/cpu:0' with tf.device( tf.train.replica_device_setter(FLAGS.ps_tasks, worker_device=device)): inputs, _ = image_utils.imagenet_inputs(FLAGS.batch_size, FLAGS.image_size) # Load style images and select one at random (for each graph execution, a # new random selection occurs) _, style_labels, style_gram_matrices = image_utils.style_image_inputs( os.path.expanduser(FLAGS.style_dataset_file), batch_size=FLAGS.batch_size, image_size=FLAGS.image_size, square_crop=True, shuffle=True) with tf.device(tf.train.replica_device_setter(FLAGS.ps_tasks)): # Process style and weight flags num_styles = FLAGS.num_styles if FLAGS.style_coefficients is None: style_coefficients = [1.0 for _ in range(num_styles)] else: style_coefficients = ast.literal_eval(FLAGS.style_coefficients) if len(style_coefficients) != num_styles: raise ValueError( 'number of style coefficients differs from number of styles' ) content_weights = ast.literal_eval(FLAGS.content_weights) style_weights = ast.literal_eval(FLAGS.style_weights) # Rescale style weights dynamically based on the current style image style_coefficient = tf.gather(tf.constant(style_coefficients), style_labels) style_weights = dict((key, style_coefficient * value) for key, value in style_weights.items()) # Define the model stylized_inputs = model.transform(inputs, normalizer_params={ 'labels': style_labels, 'num_categories': num_styles, 'center': True, 'scale': True }) # Compute losses. total_loss, loss_dict = learning.total_loss( inputs, stylized_inputs, style_gram_matrices, content_weights, style_weights) for key, value in loss_dict.items(): tf.summary.scalar(key, value) instance_norm_vars = [ var for var in slim.get_variables('transformer') if 'InstanceNorm' in var.name ] other_vars = [ var for var in slim.get_variables('transformer') if 'InstanceNorm' not in var.name ] # Function to restore VGG16 parameters. # TODO(iansimon): This is ugly, but assign_from_checkpoint_fn doesn't # exist yet. saver_vgg = tf.train.Saver(slim.get_variables('vgg_16')) def init_fn_vgg(session): saver_vgg.restore(session, vgg.checkpoint_file()) # Function to restore N-styles parameters. # TODO(iansimon): This is ugly, but assign_from_checkpoint_fn doesn't # exist yet. saver_n_styles = tf.train.Saver(other_vars) def init_fn_n_styles(session): saver_n_styles.restore(session, os.path.expanduser(FLAGS.checkpoint)) def init_fn(session): init_fn_vgg(session) init_fn_n_styles(session) # Set up training. optimizer = tf.train.AdamOptimizer(FLAGS.learning_rate) train_op = slim.learning.create_train_op( total_loss, optimizer, clip_gradient_norm=FLAGS.clip_gradient_norm, variables_to_train=instance_norm_vars, summarize_gradients=False) # Run training. slim.learning.train(train_op=train_op, logdir=os.path.expanduser(FLAGS.train_dir), master=FLAGS.master, is_chief=FLAGS.task == 0, number_of_steps=FLAGS.train_steps, init_fn=init_fn, save_summaries_secs=FLAGS.save_summaries_secs, save_interval_secs=FLAGS.save_interval_secs)
def main(_): tf.logging.set_verbosity(tf.logging.INFO) with tf.Graph().as_default(): # Loads content images. eval_content_inputs_, _ = image_utils.imagenet_inputs( FLAGS.batch_size, FLAGS.image_size) # Process style and content weight flags. content_weights = ast.literal_eval(FLAGS.content_weights) style_weights = ast.literal_eval(FLAGS.style_weights) # Loads evaluation style images. eval_style_inputs_, _, _ = image_utils.arbitrary_style_image_inputs( FLAGS.eval_style_dataset_file, batch_size=FLAGS.batch_size, image_size=FLAGS.image_size, center_crop=True, shuffle=True, augment_style_images=False, random_style_image_size=False) # Computes stylized noise. stylized_noise, _, _, _ = build_model.build_model( tf.random_uniform([ min(4, FLAGS.batch_size), FLAGS.image_size, FLAGS.image_size, 3 ]), tf.slice(eval_style_inputs_, [0, 0, 0, 0], [min(4, FLAGS.batch_size), -1, -1, -1]), trainable=False, is_training=False, reuse=None, inception_end_point='Mixed_6e', style_prediction_bottleneck=100, adds_losses=False) # Computes stylized images. stylized_images, _, loss_dict, _ = build_model.build_model( eval_content_inputs_, eval_style_inputs_, trainable=False, is_training=False, reuse=True, inception_end_point='Mixed_6e', style_prediction_bottleneck=100, adds_losses=True, content_weights=content_weights, style_weights=style_weights, total_variation_weight=FLAGS.total_variation_weight) # Adds Image summaries to the tensorboard. tf.summary.image( 'image/{}/0_eval_content_inputs'.format(FLAGS.eval_name), eval_content_inputs_, 3) tf.summary.image( 'image/{}/1_eval_style_inputs'.format(FLAGS.eval_name), eval_style_inputs_, 3) tf.summary.image( 'image/{}/2_eval_stylized_images'.format(FLAGS.eval_name), stylized_images, 3) tf.summary.image('image/{}/3_stylized_noise'.format(FLAGS.eval_name), stylized_noise, 3) metrics = {} for key, value in loss_dict.items(): metrics[key] = tf.metrics.mean(value) names_values, names_updates = slim.metrics.aggregate_metric_map( metrics) for name, value in names_values.items(): slim.summaries.add_scalar_summary(value, name, print_summary=True) eval_op = list(names_updates.values()) num_evals = FLAGS.num_evaluation_styles / FLAGS.batch_size slim.evaluation.evaluation_loop( master=FLAGS.master, checkpoint_dir=FLAGS.checkpoint_dir, logdir=FLAGS.eval_dir, eval_op=eval_op, num_evals=num_evals, eval_interval_secs=FLAGS.eval_interval_secs)
def main(unused_argv=None): tf.logging.set_verbosity(tf.logging.INFO) with tf.Graph().as_default(): # Forces all input processing onto CPU in order to reserve the GPU for the # forward inference and back-propagation. device = '/cpu:0' if not FLAGS.ps_tasks else '/job:worker/cpu:0' with tf.device( tf.train.replica_device_setter(FLAGS.ps_tasks, worker_device=device)): # Loads content images. content_inputs_, _ = image_utils.imagenet_inputs( FLAGS.batch_size, FLAGS.image_size) # Loads style images. [style_inputs_, _, _] = image_utils.arbitrary_style_image_inputs( FLAGS.style_dataset_file, batch_size=FLAGS.batch_size, image_size=FLAGS.image_size, shuffle=True, center_crop=FLAGS.center_crop, augment_style_images=FLAGS.augment_style_images, random_style_image_size=FLAGS.random_style_image_size) with tf.device(tf.train.replica_device_setter(FLAGS.ps_tasks)): # Process style and content weight flags. content_weights = ast.literal_eval(FLAGS.content_weights) style_weights = ast.literal_eval(FLAGS.style_weights) # Define the model stylized_images, total_loss, loss_dict, \ _ = build_mobilenet_model.build_mobilenet_model( content_inputs_, style_inputs_, mobilenet_trainable=False, style_params_trainable=True, transformer_trainable=True, mobilenet_end_point='layer_19', transformer_alpha=FLAGS.alpha, style_prediction_bottleneck=100, adds_losses=True, content_weights=content_weights, style_weights=style_weights, total_variation_weight=FLAGS.total_variation_weight, ) # Adding scalar summaries to the tensorboard. for key in loss_dict: tf.summary.scalar(key, loss_dict[key]) # Adding Image summaries to the tensorboard. tf.summary.image('image/0_content_inputs', content_inputs_, 3) tf.summary.image('image/1_style_inputs_aug', style_inputs_, 3) tf.summary.image('image/2_stylized_images', stylized_images, 3) # Set up training optimizer = tf.train.AdamOptimizer(FLAGS.learning_rate) train_op = slim.learning.create_train_op( total_loss, optimizer, clip_gradient_norm=FLAGS.clip_gradient_norm, summarize_gradients=False) # Function to restore VGG16 parameters. init_fn_vgg = slim.assign_from_checkpoint_fn( vgg.checkpoint_file(), slim.get_variables('vgg_16')) # Function to restore Mobilenet V2 parameters. mobilenet_variables_dict = { var.op.name: var for var in slim.get_model_variables('MobilenetV2') } init_fn_mobilenet = slim.assign_from_checkpoint_fn( FLAGS.mobilenet_checkpoint, mobilenet_variables_dict) # Function to restore VGG16 and Mobilenet V2 parameters. def init_sub_networks(session): init_fn_vgg(session) init_fn_mobilenet(session) # Run training slim.learning.train(train_op=train_op, logdir=os.path.expanduser(FLAGS.train_dir), master=FLAGS.master, is_chief=FLAGS.task == 0, number_of_steps=FLAGS.train_steps, init_fn=init_sub_networks, save_summaries_secs=FLAGS.save_summaries_secs, save_interval_secs=FLAGS.save_interval_secs)
def main(_): tf.logging.set_verbosity(tf.logging.INFO) with tf.Graph().as_default(): # Loads content images. eval_content_inputs_, _ = image_utils.imagenet_inputs( FLAGS.batch_size, FLAGS.image_size) # Process style and content weight flags. content_weights = ast.literal_eval(FLAGS.content_weights) style_weights = ast.literal_eval(FLAGS.style_weights) # Loads evaluation style images. eval_style_inputs_, _, _ = image_utils.arbitrary_style_image_inputs( FLAGS.eval_style_dataset_file, batch_size=FLAGS.batch_size, image_size=FLAGS.image_size, center_crop=True, shuffle=True, augment_style_images=False, random_style_image_size=False) # Computes stylized noise. stylized_noise, _, _, _ = build_model.build_model( tf.random_uniform( [min(4, FLAGS.batch_size), FLAGS.image_size, FLAGS.image_size, 3]), tf.slice(eval_style_inputs_, [0, 0, 0, 0], [min(4, FLAGS.batch_size), -1, -1, -1]), trainable=False, is_training=False, reuse=None, inception_end_point='Mixed_6e', style_prediction_bottleneck=100, adds_losses=False) # Computes stylized images. stylized_images, _, loss_dict, _ = build_model.build_model( eval_content_inputs_, eval_style_inputs_, trainable=False, is_training=False, reuse=True, inception_end_point='Mixed_6e', style_prediction_bottleneck=100, adds_losses=True, content_weights=content_weights, style_weights=style_weights, total_variation_weight=FLAGS.total_variation_weight) # Adds Image summaries to the tensorboard. tf.summary.image('image/{}/0_eval_content_inputs'.format(FLAGS.eval_name), eval_content_inputs_, 3) tf.summary.image('image/{}/1_eval_style_inputs'.format(FLAGS.eval_name), eval_style_inputs_, 3) tf.summary.image('image/{}/2_eval_stylized_images'.format(FLAGS.eval_name), stylized_images, 3) tf.summary.image('image/{}/3_stylized_noise'.format(FLAGS.eval_name), stylized_noise, 3) metrics = {} for key, value in loss_dict.iteritems(): metrics[key] = tf.metrics.mean(value) names_values, names_updates = slim.metrics.aggregate_metric_map(metrics) for name, value in names_values.iteritems(): slim.summaries.add_scalar_summary(value, name, print_summary=True) eval_op = names_updates.values() num_evals = FLAGS.num_evaluation_styles / FLAGS.batch_size slim.evaluation.evaluation_loop( master=FLAGS.master, checkpoint_dir=FLAGS.checkpoint_dir, logdir=FLAGS.eval_dir, eval_op=eval_op, num_evals=num_evals, eval_interval_secs=FLAGS.eval_interval_secs)
def main(_): with tf.Graph().as_default(): # Create inputs in [0, 1], as expected by vgg_16. inputs, _ = image_utils.imagenet_inputs(FLAGS.batch_size, FLAGS.image_size) evaluation_images = image_utils.load_evaluation_images( FLAGS.image_size) # Process style and weight flags if FLAGS.style_coefficients is None: style_coefficients = [1.0 for _ in range(FLAGS.num_styles)] else: style_coefficients = ast.literal_eval(FLAGS.style_coefficients) if len(style_coefficients) != FLAGS.num_styles: raise ValueError( 'number of style coefficients differs from number of styles') content_weights = ast.literal_eval(FLAGS.content_weights) style_weights = ast.literal_eval(FLAGS.style_weights) # Load style images. style_images, labels, style_gram_matrices = image_utils.style_image_inputs( os.path.expanduser(FLAGS.style_dataset_file), batch_size=FLAGS.num_styles, image_size=FLAGS.image_size, square_crop=True, shuffle=False) labels = tf.unstack(labels) def _create_normalizer_params(style_label): """Creates normalizer parameters from a style label.""" return { 'labels': tf.expand_dims(style_label, 0), 'num_categories': FLAGS.num_styles, 'center': True, 'scale': True } # Dummy call to simplify the reuse logic model.transform(inputs, reuse=False, normalizer_params=_create_normalizer_params(labels[0])) def _style_sweep(inputs): """Transfers all styles onto the input one at a time.""" inputs = tf.expand_dims(inputs, 0) stylized_inputs = [ model.transform( inputs, reuse=True, normalizer_params=_create_normalizer_params(style_label)) for _, style_label in enumerate(labels) ] return tf.concat_v2([inputs] + stylized_inputs, 0) if FLAGS.style_grid: style_row = tf.concat_v2([ tf.ones([1, FLAGS.image_size, FLAGS.image_size, 3]), style_images ], 0) stylized_training_example = _style_sweep(inputs[0]) stylized_evaluation_images = [ _style_sweep(image) for image in tf.unstack(evaluation_images) ] stylized_noise = _style_sweep( tf.random_uniform([FLAGS.image_size, FLAGS.image_size, 3])) stylized_style_images = [ _style_sweep(image) for image in tf.unstack(style_images) ] if FLAGS.style_crossover: grid = tf.concat_v2( [style_row, stylized_training_example, stylized_noise] + stylized_evaluation_images + stylized_style_images, 0) else: grid = tf.concat_v2( [style_row, stylized_training_example, stylized_noise] + stylized_evaluation_images, 0) tf.summary.image( 'Style Grid', tf.cast( image_utils.form_image_grid(grid, ([ 3 + evaluation_images.get_shape().as_list()[0] + FLAGS.num_styles, 1 + FLAGS.num_styles ] if FLAGS.style_crossover else [ 3 + evaluation_images.get_shape().as_list()[0], 1 + FLAGS.num_styles ]), [FLAGS.image_size, FLAGS.image_size], 3) * 255.0, tf.uint8)) if FLAGS.learning_curves: metrics = {} for i, label in enumerate(labels): gram_matrices = dict([ (key, value[i:i + 1]) for key, value in style_gram_matrices.iteritems() ]) stylized_inputs = model.transform( inputs, reuse=True, normalizer_params=_create_normalizer_params(label)) _, loss_dict = learning.total_loss(inputs, stylized_inputs, gram_matrices, content_weights, style_weights, reuse=i > 0) for key, value in loss_dict.iteritems(): metrics['{}_style_{}'.format( key, i)] = slim.metrics.streaming_mean(value) names_values, names_updates = slim.metrics.aggregate_metric_map( metrics) for name, value in names_values.iteritems(): summary_op = tf.summary.scalar(name, value, []) print_op = tf.Print(summary_op, [value], name) tf.add_to_collection(tf.GraphKeys.SUMMARIES, print_op) eval_op = names_updates.values() num_evals = FLAGS.num_evals else: eval_op = None num_evals = 1 slim.evaluation.evaluation_loop( master=FLAGS.master, checkpoint_dir=os.path.expanduser(FLAGS.train_dir), logdir=os.path.expanduser(FLAGS.eval_dir), eval_op=eval_op, num_evals=num_evals, eval_interval_secs=FLAGS.eval_interval_secs)
def main(_): with tf.Graph().as_default(): # Create inputs in [0, 1], as expected by vgg_16. inputs, _ = image_utils.imagenet_inputs( FLAGS.batch_size, FLAGS.image_size) evaluation_images = image_utils.load_evaluation_images(FLAGS.image_size) # Process style and weight flags if FLAGS.style_coefficients is None: style_coefficients = [1.0 for _ in range(FLAGS.num_styles)] else: style_coefficients = ast.literal_eval(FLAGS.style_coefficients) if len(style_coefficients) != FLAGS.num_styles: raise ValueError( 'number of style coefficients differs from number of styles') content_weights = ast.literal_eval(FLAGS.content_weights) style_weights = ast.literal_eval(FLAGS.style_weights) # Load style images. style_images, labels, style_gram_matrices = image_utils.style_image_inputs( os.path.expanduser(FLAGS.style_dataset_file), batch_size=FLAGS.num_styles, image_size=FLAGS.image_size, square_crop=True, shuffle=False) labels = tf.unstack(labels) def _create_normalizer_params(style_label): """Creates normalizer parameters from a style label.""" return {'labels': tf.expand_dims(style_label, 0), 'num_categories': FLAGS.num_styles, 'center': True, 'scale': True} # Dummy call to simplify the reuse logic model.transform(inputs, reuse=False, normalizer_params=_create_normalizer_params(labels[0])) def _style_sweep(inputs): """Transfers all styles onto the input one at a time.""" inputs = tf.expand_dims(inputs, 0) stylized_inputs = [ model.transform( inputs, reuse=True, normalizer_params=_create_normalizer_params(style_label)) for _, style_label in enumerate(labels)] return tf.concat([inputs] + stylized_inputs, 0) if FLAGS.style_grid: style_row = tf.concat( [tf.ones([1, FLAGS.image_size, FLAGS.image_size, 3]), style_images], 0) stylized_training_example = _style_sweep(inputs[0]) stylized_evaluation_images = [ _style_sweep(image) for image in tf.unstack(evaluation_images)] stylized_noise = _style_sweep( tf.random_uniform([FLAGS.image_size, FLAGS.image_size, 3])) stylized_style_images = [ _style_sweep(image) for image in tf.unstack(style_images)] if FLAGS.style_crossover: grid = tf.concat( [style_row, stylized_training_example, stylized_noise] + stylized_evaluation_images + stylized_style_images, 0) else: grid = tf.concat( [style_row, stylized_training_example, stylized_noise] + stylized_evaluation_images, 0) if FLAGS.style_crossover: grid_shape = [ 3 + evaluation_images.get_shape().as_list()[0] + FLAGS.num_styles, 1 + FLAGS.num_styles] else: grid_shape = [ 3 + evaluation_images.get_shape().as_list()[0], 1 + FLAGS.num_styles] tf.summary.image( 'Style Grid', tf.cast( image_utils.form_image_grid( grid, grid_shape, [FLAGS.image_size, FLAGS.image_size], 3) * 255.0, tf.uint8)) if FLAGS.learning_curves: metrics = {} for i, label in enumerate(labels): gram_matrices = dict( (key, value[i: i + 1]) for key, value in style_gram_matrices.items()) stylized_inputs = model.transform( inputs, reuse=True, normalizer_params=_create_normalizer_params(label)) _, loss_dict = learning.total_loss( inputs, stylized_inputs, gram_matrices, content_weights, style_weights, reuse=i > 0) for key, value in loss_dict.items(): metrics['{}_style_{}'.format(key, i)] = slim.metrics.streaming_mean( value) names_values, names_updates = slim.metrics.aggregate_metric_map(metrics) for name, value in names_values.items(): summary_op = tf.summary.scalar(name, value, []) print_op = tf.Print(summary_op, [value], name) tf.add_to_collection(tf.GraphKeys.SUMMARIES, print_op) eval_op = names_updates.values() num_evals = FLAGS.num_evals else: eval_op = None num_evals = 1 slim.evaluation.evaluation_loop( master=FLAGS.master, checkpoint_dir=os.path.expanduser(FLAGS.train_dir), logdir=os.path.expanduser(FLAGS.eval_dir), eval_op=eval_op, num_evals=num_evals, eval_interval_secs=FLAGS.eval_interval_secs)
def main(_): with tf.Graph().as_default(): # Create inputs in [0, 1], as expected by vgg_16. inputs, _ = image_utils.imagenet_inputs(FLAGS.batch_size, FLAGS.image_size) evaluation_images = image_utils.load_evaluation_images( FLAGS.image_size) # Load style images. style_images, labels, style_gram_matrices = image_utils.style_image_inputs( os.path.expanduser(FLAGS.style_dataset_file), batch_size=FLAGS.num_styles, image_size=FLAGS.image_size, square_crop=True, shuffle=False) labels = tf.unstack(labels) def _create_normalizer_params(style_label): """Creates normalizer parameters from a style label.""" return { 'labels': tf.expand_dims(style_label, 0), 'num_categories': FLAGS.num_styles, 'center': True, 'scale': True } # Dummy call to simplify the reuse logic model.transform(inputs, alpha=FLAGS.alpha, reuse=False, normalizer_params=_create_normalizer_params(labels[0])) def _style_sweep(inputs): """Transfers all styles onto the input one at a time.""" inputs = tf.expand_dims(inputs, 0) stylized_inputs = [] for _, style_label in enumerate(labels): stylized_input = model.transform( inputs, alpha=FLAGS.alpha, reuse=True, normalizer_params=_create_normalizer_params(style_label)) stylized_inputs.append(stylized_input) return tf.concat([inputs] + stylized_inputs, 0) style_row = tf.concat([ tf.ones([1, FLAGS.image_size, FLAGS.image_size, 3]), style_images ], 0) stylized_training_example = _style_sweep(inputs[0]) stylized_evaluation_images = [ _style_sweep(image) for image in tf.unstack(evaluation_images) ] stylized_noise = _style_sweep( tf.random_uniform([FLAGS.image_size, FLAGS.image_size, 3])) stylized_style_images = [ _style_sweep(image) for image in tf.unstack(style_images) ] if FLAGS.style_crossover: grid = tf.concat( [style_row, stylized_training_example, stylized_noise] + stylized_evaluation_images + stylized_style_images, 0) else: grid = tf.concat( [style_row, stylized_training_example, stylized_noise] + stylized_evaluation_images, 0) if FLAGS.style_crossover: grid_shape = [ 3 + evaluation_images.get_shape().as_list()[0] + FLAGS.num_styles, 1 + FLAGS.num_styles ] else: grid_shape = [ 3 + evaluation_images.get_shape().as_list()[0], 1 + FLAGS.num_styles ] style_grid = tf.cast( image_utils.form_image_grid( grid, grid_shape, [FLAGS.image_size, FLAGS.image_size], 3) * 255.0, tf.uint8) sess = tf.Session() with sess.as_default(): np_array = tf.squeeze(style_grid).eval() im = Image.fromarray(np_array) im.save('matrix.png')
def main(unused_argv=None): with tf.Graph().as_default(): # Force all input processing onto CPU in order to reserve the GPU for the # forward inference and back-propagation. device = '/cpu:0' if not FLAGS.ps_tasks else '/job:worker/cpu:0' with tf.device(tf.train.replica_device_setter(FLAGS.ps_tasks, worker_device=device)): inputs, _ = image_utils.imagenet_inputs(FLAGS.batch_size, FLAGS.image_size) # Load style images and select one at random (for each graph execution, a # new random selection occurs) _, style_labels, style_gram_matrices = image_utils.style_image_inputs( os.path.expanduser(FLAGS.style_dataset_file), batch_size=FLAGS.batch_size, image_size=FLAGS.image_size, square_crop=True, shuffle=True) with tf.device(tf.train.replica_device_setter(FLAGS.ps_tasks)): # Process style and weight flags num_styles = FLAGS.num_styles if FLAGS.style_coefficients is None: style_coefficients = [1.0 for _ in range(num_styles)] else: style_coefficients = ast.literal_eval(FLAGS.style_coefficients) if len(style_coefficients) != num_styles: raise ValueError( 'number of style coefficients differs from number of styles') content_weights = ast.literal_eval(FLAGS.content_weights) style_weights = ast.literal_eval(FLAGS.style_weights) # Rescale style weights dynamically based on the current style image style_coefficient = tf.gather( tf.constant(style_coefficients), style_labels) style_weights = dict([(key, style_coefficient * value) for key, value in style_weights.iteritems()]) # Define the model stylized_inputs = model.transform( inputs, normalizer_params={ 'labels': style_labels, 'num_categories': num_styles, 'center': True, 'scale': True}) # Compute losses. total_loss, loss_dict = learning.total_loss( inputs, stylized_inputs, style_gram_matrices, content_weights, style_weights) for key, value in loss_dict.iteritems(): tf.summary.scalar(key, value) instance_norm_vars = [var for var in slim.get_variables('transformer') if 'InstanceNorm' in var.name] other_vars = [var for var in slim.get_variables('transformer') if 'InstanceNorm' not in var.name] # Function to restore VGG16 parameters. # TODO(iansimon): This is ugly, but assign_from_checkpoint_fn doesn't # exist yet. saver_vgg = tf.train.Saver(slim.get_variables('vgg_16')) def init_fn_vgg(session): saver_vgg.restore(session, vgg.checkpoint_file()) # Function to restore N-styles parameters. # TODO(iansimon): This is ugly, but assign_from_checkpoint_fn doesn't # exist yet. saver_n_styles = tf.train.Saver(other_vars) def init_fn_n_styles(session): saver_n_styles.restore(session, os.path.expanduser(FLAGS.checkpoint)) def init_fn(session): init_fn_vgg(session) init_fn_n_styles(session) # Set up training. optimizer = tf.train.AdamOptimizer(FLAGS.learning_rate) train_op = slim.learning.create_train_op( total_loss, optimizer, clip_gradient_norm=FLAGS.clip_gradient_norm, variables_to_train=instance_norm_vars, summarize_gradients=False) # Run training. slim.learning.train( train_op=train_op, logdir=os.path.expanduser(FLAGS.train_dir), master=FLAGS.master, is_chief=FLAGS.task == 0, number_of_steps=FLAGS.train_steps, init_fn=init_fn, save_summaries_secs=FLAGS.save_summaries_secs, save_interval_secs=FLAGS.save_interval_secs)
def main(unused_argv=None): tf.logging.set_verbosity(tf.logging.INFO) with tf.Graph().as_default(): # Forces all input processing onto CPU in order to reserve the GPU for the # forward inference and back-propagation. device = '/cpu:0' if not FLAGS.ps_tasks else '/job:worker/cpu:0' with tf.device( tf.train.replica_device_setter(FLAGS.ps_tasks, worker_device=device)): # Loads content images. content_inputs_, _ = image_utils.imagenet_inputs(FLAGS.batch_size, FLAGS.image_size) # Loads style images. [style_inputs_, _, style_inputs_orig_] = image_utils.arbitrary_style_image_inputs( FLAGS.style_dataset_file, batch_size=FLAGS.batch_size, image_size=FLAGS.image_size, shuffle=True, center_crop=FLAGS.center_crop, augment_style_images=FLAGS.augment_style_images, random_style_image_size=FLAGS.random_style_image_size) with tf.device(tf.train.replica_device_setter(FLAGS.ps_tasks)): # Process style and content weight flags. content_weights = ast.literal_eval(FLAGS.content_weights) style_weights = ast.literal_eval(FLAGS.style_weights) # Define the model stylized_images, total_loss, loss_dict, _ = build_model.build_model( content_inputs_, style_inputs_, trainable=True, is_training=True, inception_end_point='Mixed_6e', style_prediction_bottleneck=100, adds_losses=True, content_weights=content_weights, style_weights=style_weights, total_variation_weight=FLAGS.total_variation_weight) # Adding scalar summaries to the tensorboard. for key, value in loss_dict.iteritems(): tf.summary.scalar(key, value) # Adding Image summaries to the tensorboard. tf.summary.image('image/0_content_inputs', content_inputs_, 3) tf.summary.image('image/1_style_inputs_orig', style_inputs_orig_, 3) tf.summary.image('image/2_style_inputs_aug', style_inputs_, 3) tf.summary.image('image/3_stylized_images', stylized_images, 3) # Set up training optimizer = tf.train.AdamOptimizer(FLAGS.learning_rate) train_op = slim.learning.create_train_op( total_loss, optimizer, clip_gradient_norm=FLAGS.clip_gradient_norm, summarize_gradients=False) # Function to restore VGG16 parameters. init_fn_vgg = slim.assign_from_checkpoint_fn(vgg.checkpoint_file(), slim.get_variables('vgg_16')) # Function to restore Inception_v3 parameters. inception_variables_dict = { var.op.name: var for var in slim.get_model_variables('InceptionV3') } init_fn_inception = slim.assign_from_checkpoint_fn( FLAGS.inception_v3_checkpoint, inception_variables_dict) # Function to restore VGG16 and Inception_v3 parameters. def init_sub_networks(session): init_fn_vgg(session) init_fn_inception(session) # Run training slim.learning.train( train_op=train_op, logdir=os.path.expanduser(FLAGS.train_dir), master=FLAGS.master, is_chief=FLAGS.task == 0, number_of_steps=FLAGS.train_steps, init_fn=init_sub_networks, save_summaries_secs=FLAGS.save_summaries_secs, save_interval_secs=FLAGS.save_interval_secs)
def main(unused_argv=None): tf.logging.set_verbosity(tf.logging.INFO) with tf.Graph().as_default(): # Forces all input processing onto CPU in order to reserve the GPU for the # forward inference and back-propagation. device = '/cpu:0' if not FLAGS.ps_tasks else '/job:worker/cpu:0' with tf.device( tf.train.replica_device_setter(FLAGS.ps_tasks, worker_device=device)): # Load content images content_inputs_, _ = image_utils.imagenet_inputs(FLAGS.batch_size, FLAGS.image_size) # Loads style images. [style_inputs_, _, style_inputs_orig_] = image_utils.arbitrary_style_image_inputs( FLAGS.style_dataset_file, batch_size=FLAGS.batch_size, image_size=FLAGS.image_size, shuffle=True, center_crop=FLAGS.center_crop, augment_style_images=FLAGS.augment_style_images, random_style_image_size=FLAGS.random_style_image_size) with tf.device(tf.train.replica_device_setter(FLAGS.ps_tasks)): # Process style and content weight flags. content_weights = ast.literal_eval(FLAGS.content_weights) style_weights = ast.literal_eval(FLAGS.style_weights) # Define the model stylized_images, \ true_loss, \ _, \ bottleneck_feat = build_mobilenet_model.build_mobilenet_model( content_inputs_, style_inputs_, mobilenet_trainable=True, style_params_trainable=False, style_prediction_bottleneck=100, adds_losses=True, content_weights=content_weights, style_weights=style_weights, total_variation_weight=FLAGS.total_variation_weight, ) _, inception_bottleneck_feat = build_model.style_prediction( style_inputs_, [], [], is_training=False, trainable=False, inception_end_point='Mixed_6e', style_prediction_bottleneck=100, reuse=None, ) print('PRINTING TRAINABLE VARIABLES') for x in tf.trainable_variables(): print(x) mse_loss = tf.losses.mean_squared_error( inception_bottleneck_feat, bottleneck_feat) total_loss = mse_loss if FLAGS.use_true_loss: true_loss = FLAGS.true_loss_weight*true_loss total_loss += true_loss if FLAGS.use_true_loss: tf.summary.scalar('mse', mse_loss) tf.summary.scalar('true_loss', true_loss) tf.summary.scalar('total_loss', total_loss) tf.summary.image('image/0_content_inputs', content_inputs_, 3) tf.summary.image('image/1_style_inputs_orig', style_inputs_orig_, 3) tf.summary.image('image/2_style_inputs_aug', style_inputs_, 3) tf.summary.image('image/3_stylized_images', stylized_images, 3) mobilenet_variables_to_restore = slim.get_variables_to_restore( include=['MobilenetV2'], exclude=['global_step']) optimizer = tf.train.AdamOptimizer(FLAGS.learning_rate) train_op = slim.learning.create_train_op( total_loss, optimizer, clip_gradient_norm=FLAGS.clip_gradient_norm, summarize_gradients=False ) init_fn = slim.assign_from_checkpoint_fn( FLAGS.initial_checkpoint, slim.get_variables_to_restore( exclude=['MobilenetV2', 'mobilenet_conv', 'global_step'])) init_pretrained_mobilenet = slim.assign_from_checkpoint_fn( FLAGS.mobilenet_checkpoint, mobilenet_variables_to_restore) def init_sub_networks(session): init_fn(session) init_pretrained_mobilenet(session) slim.learning.train( train_op=train_op, logdir=os.path.expanduser(FLAGS.train_dir), master=FLAGS.master, is_chief=FLAGS.task == 0, number_of_steps=FLAGS.train_steps, init_fn=init_sub_networks, save_summaries_secs=FLAGS.save_summaries_secs, save_interval_secs=FLAGS.save_interval_secs)