def main(args): output_dir = os.path.expanduser(args.output_dir) if not os.path.exists(output_dir): os.mkdir(output_dir) # Store some git revision info in a text file in the output directory src_path, _ = os.path.split(os.path.realpath(__file__)) fc.store_revision_info(src_path, output_dir, " ".join(sys.argv)) i = 0 for f in args.tsv_files: for line in f: fields = line.split("\t") class_dir = fields[0] img_name = fields[1] + "-" + fields[4] + "." + args.output_format img_string = fields[5] img_dec_string = base64.b64decode(img_string) img_data = np.fromstring(img_dec_string, dtype=np.uint8) img = cv2.imdecode(img_data, cv2.IMREAD_COLOR) # pylint: disable=maybe-no-member if args.size: img = misc.imresize(img, (args.size, args.size), interp="bilinear") full_class_dir = os.path.join(output_dir, class_dir) if not os.path.exists(full_class_dir): os.mkdir(full_class_dir) full_path = os.path.join(full_class_dir, img_name.replace("/", "_")) cv2.imwrite(full_path, img) # pylint: disable=maybe-no-member print("%8d: %s" % (i, full_path)) i += 1
def main(args): sleep(random.random()) output_dir = os.path.expanduser(args.output_dir) if not os.path.exists(output_dir): os.makedirs(output_dir) # Store some git revision info in a text file in the log directory src_path, _ = os.path.split(os.path.realpath(__file__)) facenet.store_revision_info(src_path, output_dir, ' '.join(sys.argv)) dataset = facenet.get_dataset(args.input_dir) print('Creating networks and loading parameters') with tf.Graph().as_default(): gpu_options = tf.GPUOptions( per_process_gpu_memory_fraction=args.gpu_memory_fraction) sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False)) with sess.as_default(): pnet, rnet, onet = detect_face.create_mtcnn(sess, None) minsize = 20 # minimum size of face threshold = [0.6, 0.7, 0.7] # three steps's threshold factor = 0.709 # scale factor # Add a random key to the filename to allow alignment using multiple processes random_key = np.random.randint(0, high=99999) bounding_boxes_filename = os.path.join( output_dir, 'bounding_boxes_%05d.txt' % random_key) with open(bounding_boxes_filename, "w") as text_file: nrof_images_total = 0 nrof_successfully_aligned = 0 if args.random_order: random.shuffle(dataset) for cls in dataset: output_class_dir = os.path.join(output_dir, cls.name) if not os.path.exists(output_class_dir): os.makedirs(output_class_dir) if args.random_order: random.shuffle(cls.image_paths) for image_path in cls.image_paths: nrof_images_total += 1 filename = os.path.splitext(os.path.split(image_path)[1])[0] output_filename = os.path.join(output_class_dir, filename + '.png') print(image_path) if not os.path.exists(output_filename): try: img = misc.imread(image_path) except (IOError, ValueError, IndexError) as e: errorMessage = '{}: {}'.format(image_path, e) print(errorMessage) else: if img.ndim < 2: print('Unable to align "%s"' % image_path) text_file.write('%s\n' % (output_filename)) continue if img.ndim == 2: img = facenet.to_rgb(img) img = img[:, :, 0:3] bounding_boxes, _ = align.detect_face.detect_face( img, minsize, pnet, rnet, onet, threshold, factor) nrof_faces = bounding_boxes.shape[0] if nrof_faces > 0: det = bounding_boxes[:, 0:4] det_arr = [] img_size = np.asarray(img.shape)[0:2] if nrof_faces > 1: if args.detect_multiple_faces: for i in range(nrof_faces): det_arr.append(np.squeeze(det[i])) else: bounding_box_size = ( det[:, 2] - det[:, 0]) * (det[:, 3] - det[:, 1]) img_center = img_size / 2 offsets = np.vstack([ (det[:, 0] + det[:, 2]) / 2 - img_center[1], (det[:, 1] + det[:, 3]) / 2 - img_center[0] ]) offset_dist_squared = np.sum( np.power(offsets, 2.0), 0) index = np.argmax( bounding_box_size - offset_dist_squared * 2.0 ) # some extra weight on the centering det_arr.append(det[index, :]) else: det_arr.append(np.squeeze(det)) for i, det in enumerate(det_arr): det = np.squeeze(det) bb = np.zeros(4, dtype=np.int32) bb[0] = np.maximum(det[0] - args.margin / 2, 0) bb[1] = np.maximum(det[1] - args.margin / 2, 0) bb[2] = np.minimum(det[2] + args.margin / 2, img_size[1]) bb[3] = np.minimum(det[3] + args.margin / 2, img_size[0]) cropped = img[bb[1]:bb[3], bb[0]:bb[2], :] scaled = misc.imresize( cropped, (args.image_size, args.image_size), interp='bilinear') nrof_successfully_aligned += 1 filename_base, file_extension = os.path.splitext( output_filename) if args.detect_multiple_faces: output_filename_n = "{}_{}{}".format( filename_base, i, file_extension) else: output_filename_n = "{}{}".format( filename_base, file_extension) misc.imsave(output_filename_n, scaled) text_file.write('%s %d %d %d %d\n' % (output_filename_n, bb[0], bb[1], bb[2], bb[3])) else: print('Unable to align "%s"' % image_path) text_file.write('%s\n' % (output_filename)) print('Total number of images: %d' % nrof_images_total) print('Number of successfully aligned images: %d' % nrof_successfully_aligned)
def main(args): network = importlib.import_module(args.model_def) image_size = (args.image_size, args.image_size) subdir = datetime.strftime(datetime.now(), "%Y%m%d-%H%M%S") log_dir = os.path.join(os.path.expanduser(args.logs_base_dir), subdir) if not os.path.isdir( log_dir): # Create the log directory if it doesn't exist os.makedirs(log_dir) model_dir = os.path.join(os.path.expanduser(args.models_base_dir), subdir) if not os.path.isdir( model_dir): # Create the model directory if it doesn't exist os.makedirs(model_dir) stat_file_name = os.path.join(log_dir, "stat.h5") # Write arguments to a text file fc.write_arguments_to_file(args, os.path.join(log_dir, "arguments.txt")) # Store some git revision info in a text file in the log directory src_path, _ = os.path.split(os.path.realpath(__file__)) fc.store_revision_info(src_path, log_dir, " ".join(sys.argv)) np.random.seed(seed=args.seed) random.seed(args.seed) dataset = fc.get_dataset(args.data_dir) if args.filter_filename: dataset = filter_dataset( dataset, os.path.expanduser(args.filter_filename), args.filter_percentile, args.filter_min_nrof_images_per_class, ) if args.validation_set_split_ratio > 0.0: train_set, val_set = fc.split_dataset( dataset, args.validation_set_split_ratio, args.min_nrof_val_images_per_class, "SPLIT_IMAGES") else: train_set, val_set = dataset, [] nrof_classes = len(train_set) print("Model directory: %s" % model_dir) print("Log directory: %s" % log_dir) pretrained_model = None if args.pretrained_model: pretrained_model = os.path.expanduser(args.pretrained_model) print("Pre-trained model: %s" % pretrained_model) if args.lfw_dir: print("LFW directory: %s" % args.lfw_dir) # Read the file containing the pairs used for testing pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs)) # Get the paths for the corresponding images lfw_paths, actual_issame = lfw.get_paths( os.path.expanduser(args.lfw_dir), pairs) with tf.Graph().as_default(): tf.set_random_seed(args.seed) global_step = tf.Variable(0, trainable=False) # Get a list of image paths and their labels image_list, label_list = fc.get_image_paths_and_labels(train_set) assert len(image_list) > 0, "The training set should not be empty" val_image_list, val_label_list = fc.get_image_paths_and_labels(val_set) # Create a queue that produces indices into the image_list and label_list labels = ops.convert_to_tensor(label_list, dtype=tf.int32) range_size = array_ops.shape(labels)[0] index_queue = tf.train.range_input_producer(range_size, num_epochs=None, shuffle=True, seed=None, capacity=32) index_dequeue_op = index_queue.dequeue_many( args.batch_size * args.epoch_size, "index_dequeue") learning_rate_placeholder = tf.placeholder(tf.float32, name="learning_rate") batch_size_placeholder = tf.placeholder(tf.int32, name="batch_size") phase_train_placeholder = tf.placeholder(tf.bool, name="phase_train") image_paths_placeholder = tf.placeholder(tf.string, shape=(None, 1), name="image_paths") labels_placeholder = tf.placeholder(tf.int32, shape=(None, 1), name="labels") control_placeholder = tf.placeholder(tf.int32, shape=(None, 1), name="control") nrof_preprocess_threads = 4 input_queue = data_flow_ops.FIFOQueue( capacity=2000000, dtypes=[tf.string, tf.int32, tf.int32], shapes=[(1, ), (1, ), (1, )], shared_name=None, name=None, ) enqueue_op = input_queue.enqueue_many( [image_paths_placeholder, labels_placeholder, control_placeholder], name="enqueue_op") image_batch, label_batch = fc.create_input_pipeline( input_queue, image_size, nrof_preprocess_threads, batch_size_placeholder) image_batch = tf.identity(image_batch, "image_batch") image_batch = tf.identity(image_batch, "input") label_batch = tf.identity(label_batch, "label_batch") print("Number of classes in training set: %d" % nrof_classes) print("Number of examples in training set: %d" % len(image_list)) print("Number of classes in validation set: %d" % len(val_set)) print("Number of examples in validation set: %d" % len(val_image_list)) print("Building training graph") # Build the inference graph prelogits, _ = network.inference( image_batch, args.keep_probability, phase_train=phase_train_placeholder, bottleneck_layer_size=args.embedding_size, weight_decay=args.weight_decay, ) logits = slim.fully_connected( prelogits, len(train_set), activation_fn=None, weights_initializer=slim.initializers.xavier_initializer(), weights_regularizer=slim.l2_regularizer(args.weight_decay), scope="Logits", reuse=False, ) embeddings = tf.nn.l2_normalize(prelogits, 1, 1e-10, name="embeddings") # Norm for the prelogits eps = 1e-4 prelogits_norm = tf.reduce_mean( tf.norm(tf.abs(prelogits) + eps, ord=args.prelogits_norm_p, axis=1)) tf.add_to_collection(tf.GraphKeys.REGULARIZATION_LOSSES, prelogits_norm * args.prelogits_norm_loss_factor) # Add center loss prelogits_center_loss, _ = fc.center_loss(prelogits, label_batch, args.center_loss_alfa, nrof_classes) tf.add_to_collection(tf.GraphKeys.REGULARIZATION_LOSSES, prelogits_center_loss * args.center_loss_factor) learning_rate = tf.train.exponential_decay( learning_rate_placeholder, global_step, args.learning_rate_decay_epochs * args.epoch_size, args.learning_rate_decay_factor, staircase=True, ) tf.summary.scalar("learning_rate", learning_rate) # Calculate the average cross entropy loss across the batch cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits( labels=label_batch, logits=logits, name="cross_entropy_per_example") cross_entropy_mean = tf.reduce_mean(cross_entropy, name="cross_entropy") tf.add_to_collection("losses", cross_entropy_mean) correct_prediction = tf.cast( tf.equal(tf.argmax(logits, 1), tf.cast(label_batch, tf.int64)), tf.float32) accuracy = tf.reduce_mean(correct_prediction) # Calculate the total losses regularization_losses = tf.get_collection( tf.GraphKeys.REGULARIZATION_LOSSES) total_loss = tf.add_n([cross_entropy_mean] + regularization_losses, name="total_loss") # Build a Graph that trains the model with one batch of examples and updates the model parameters train_op = fc.train( total_loss, global_step, args.optimizer, learning_rate, args.moving_average_decay, tf.global_variables(), args.log_histograms, ) # Create a saver saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=3) # Build the summary operation based on the TF collection of Summaries. summary_op = tf.summary.merge_all() # Start running operations on the Graph. gpu_options = tf.GPUOptions( per_process_gpu_memory_fraction=args.gpu_memory_fraction) sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False)) sess.run(tf.global_variables_initializer()) sess.run(tf.local_variables_initializer()) summary_writer = tf.summary.FileWriter(log_dir, sess.graph) coord = tf.train.Coordinator() tf.train.start_queue_runners(coord=coord, sess=sess) with sess.as_default(): if pretrained_model: print("Restoring pretrained model: %s" % pretrained_model) saver.restore(sess, pretrained_model) # Training and validation loop print("Running training") nrof_steps = args.max_nrof_epochs * args.epoch_size nrof_val_samples = int( math.ceil(args.max_nrof_epochs / args.validate_every_n_epochs) ) # Validate every validate_every_n_epochs as well as in the last epoch stat = { "loss": np.zeros((nrof_steps, ), np.float32), "center_loss": np.zeros((nrof_steps, ), np.float32), "reg_loss": np.zeros((nrof_steps, ), np.float32), "xent_loss": np.zeros((nrof_steps, ), np.float32), "prelogits_norm": np.zeros((nrof_steps, ), np.float32), "accuracy": np.zeros((nrof_steps, ), np.float32), "val_loss": np.zeros((nrof_val_samples, ), np.float32), "val_xent_loss": np.zeros((nrof_val_samples, ), np.float32), "val_accuracy": np.zeros((nrof_val_samples, ), np.float32), "lfw_accuracy": np.zeros((args.max_nrof_epochs, ), np.float32), "lfw_valrate": np.zeros((args.max_nrof_epochs, ), np.float32), "learning_rate": np.zeros((args.max_nrof_epochs, ), np.float32), "time_train": np.zeros((args.max_nrof_epochs, ), np.float32), "time_validate": np.zeros((args.max_nrof_epochs, ), np.float32), "time_evaluate": np.zeros((args.max_nrof_epochs, ), np.float32), "prelogits_hist": np.zeros((args.max_nrof_epochs, 1000), np.float32), } for epoch in range(1, args.max_nrof_epochs + 1): step = sess.run(global_step, feed_dict=None) # Train for one epoch t = time.time() cont = train( args, sess, epoch, image_list, label_list, index_dequeue_op, enqueue_op, image_paths_placeholder, labels_placeholder, learning_rate_placeholder, phase_train_placeholder, batch_size_placeholder, control_placeholder, global_step, total_loss, train_op, summary_op, summary_writer, regularization_losses, args.learning_rate_schedule_file, stat, cross_entropy_mean, accuracy, learning_rate, prelogits, prelogits_center_loss, args.random_rotate, args.random_crop, args.random_flip, prelogits_norm, args.prelogits_hist_max, args.use_fixed_image_standardization, ) stat["time_train"][epoch - 1] = time.time() - t if not cont: break t = time.time() if len(val_image_list) > 0 and ( (epoch - 1) % args.validate_every_n_epochs == args.validate_every_n_epochs - 1 or epoch == args.max_nrof_epochs): validate( args, sess, epoch, val_image_list, val_label_list, enqueue_op, image_paths_placeholder, labels_placeholder, control_placeholder, phase_train_placeholder, batch_size_placeholder, stat, total_loss, regularization_losses, cross_entropy_mean, accuracy, args.validate_every_n_epochs, args.use_fixed_image_standardization, ) stat["time_validate"][epoch - 1] = time.time() - t # Save variables and the metagraph if it doesn't exist already save_variables_and_metagraph(sess, saver, summary_writer, model_dir, subdir, epoch) # Evaluate on LFW t = time.time() if args.lfw_dir: evaluate( sess, enqueue_op, image_paths_placeholder, labels_placeholder, phase_train_placeholder, batch_size_placeholder, control_placeholder, embeddings, label_batch, lfw_paths, actual_issame, args.lfw_batch_size, args.lfw_nrof_folds, log_dir, step, summary_writer, stat, epoch, args.lfw_distance_metric, args.lfw_subtract_mean, args.lfw_use_flipped_images, args.use_fixed_image_standardization, ) stat["time_evaluate"][epoch - 1] = time.time() - t print("Saving statistics") with h5py.File(stat_file_name, "w") as f: for key, value in stat.iteritems(): f.create_dataset(key, data=value) return model_dir
def main(args): network = importlib.import_module(args.model_def) subdir = datetime.strftime(datetime.now(), "%Y%m%d-%H%M%S") log_dir = os.path.join(os.path.expanduser(args.logs_base_dir), subdir) if not os.path.isdir( log_dir): # Create the log directory if it doesn't exist os.makedirs(log_dir) model_dir = os.path.join(os.path.expanduser(args.models_base_dir), subdir) if not os.path.isdir( model_dir): # Create the model directory if it doesn't exist os.makedirs(model_dir) # Write arguments to a text file fc.write_arguments_to_file(args, os.path.join(log_dir, "arguments.txt")) # Store some git revision info in a text file in the log directory src_path, _ = os.path.split(os.path.realpath(__file__)) fc.store_revision_info(src_path, log_dir, " ".join(sys.argv)) np.random.seed(seed=args.seed) train_set = fc.get_dataset(args.data_dir) print("Model directory: %s" % model_dir) print("Log directory: %s" % log_dir) if args.pretrained_model: print("Pre-trained model: %s" % os.path.expanduser(args.pretrained_model)) if args.lfw_dir: print("LFW directory: %s" % args.lfw_dir) # Read the file containing the pairs used for testing pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs)) # Get the paths for the corresponding images lfw_paths, actual_issame = lfw.get_paths( os.path.expanduser(args.lfw_dir), pairs) with tf.Graph().as_default(): tf.set_random_seed(args.seed) global_step = tf.Variable(0, trainable=False) # Placeholder for the learning rate learning_rate_placeholder = tf.placeholder(tf.float32, name="learning_rate") batch_size_placeholder = tf.placeholder(tf.int32, name="batch_size") phase_train_placeholder = tf.placeholder(tf.bool, name="phase_train") image_paths_placeholder = tf.placeholder(tf.string, shape=(None, 3), name="image_paths") labels_placeholder = tf.placeholder(tf.int64, shape=(None, 3), name="labels") input_queue = data_flow_ops.FIFOQueue(capacity=100000, dtypes=[tf.string, tf.int64], shapes=[(3, ), (3, )], shared_name=None, name=None) enqueue_op = input_queue.enqueue_many( [image_paths_placeholder, labels_placeholder]) nrof_preprocess_threads = 4 images_and_labels = [] for _ in range(nrof_preprocess_threads): filenames, label = input_queue.dequeue() images = [] for filename in tf.unstack(filenames): file_contents = tf.read_file(filename) image = tf.image.decode_image(file_contents, channels=3) if args.random_crop: image = tf.random_crop( image, [args.image_size, args.image_size, 3]) else: image = tf.image.resize_image_with_crop_or_pad( image, args.image_size, args.image_size) if args.random_flip: image = tf.image.random_flip_left_right(image) # pylint: disable=no-member image.set_shape((args.image_size, args.image_size, 3)) images.append(tf.image.per_image_standardization(image)) images_and_labels.append([images, label]) image_batch, labels_batch = tf.train.batch_join( images_and_labels, batch_size=batch_size_placeholder, shapes=[(args.image_size, args.image_size, 3), ()], enqueue_many=True, capacity=4 * nrof_preprocess_threads * args.batch_size, allow_smaller_final_batch=True, ) image_batch = tf.identity(image_batch, "image_batch") image_batch = tf.identity(image_batch, "input") labels_batch = tf.identity(labels_batch, "label_batch") # Build the inference graph prelogits, _ = network.inference( image_batch, args.keep_probability, phase_train=phase_train_placeholder, bottleneck_layer_size=args.embedding_size, weight_decay=args.weight_decay, ) embeddings = tf.nn.l2_normalize(prelogits, 1, 1e-10, name="embeddings") # Split embeddings into anchor, positive and negative and calculate triplet loss anchor, positive, negative = tf.unstack( tf.reshape(embeddings, [-1, 3, args.embedding_size]), 3, 1) triplet_loss = fc.triplet_loss(anchor, positive, negative, args.alpha) learning_rate = tf.train.exponential_decay( learning_rate_placeholder, global_step, args.learning_rate_decay_epochs * args.epoch_size, args.learning_rate_decay_factor, staircase=True, ) tf.summary.scalar("learning_rate", learning_rate) # Calculate the total losses regularization_losses = tf.get_collection( tf.GraphKeys.REGULARIZATION_LOSSES) total_loss = tf.add_n([triplet_loss] + regularization_losses, name="total_loss") # Build a Graph that trains the model with one batch of examples and updates the model parameters train_op = fc.train(total_loss, global_step, args.optimizer, learning_rate, args.moving_average_decay, tf.global_variables()) # Create a saver saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=3) # Build the summary operation based on the TF collection of Summaries. summary_op = tf.summary.merge_all() # Start running operations on the Graph. gpu_options = tf.GPUOptions( per_process_gpu_memory_fraction=args.gpu_memory_fraction) sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options)) # Initialize variables sess.run(tf.global_variables_initializer(), feed_dict={phase_train_placeholder: True}) sess.run(tf.local_variables_initializer(), feed_dict={phase_train_placeholder: True}) summary_writer = tf.summary.FileWriter(log_dir, sess.graph) coord = tf.train.Coordinator() tf.train.start_queue_runners(coord=coord, sess=sess) with sess.as_default(): if args.pretrained_model: print("Restoring pretrained model: %s" % args.pretrained_model) saver.restore(sess, os.path.expanduser(args.pretrained_model)) # Training and validation loop epoch = 0 while epoch < args.max_nrof_epochs: step = sess.run(global_step, feed_dict=None) epoch = step // args.epoch_size # Train for one epoch train( args, sess, train_set, epoch, image_paths_placeholder, labels_placeholder, labels_batch, batch_size_placeholder, learning_rate_placeholder, phase_train_placeholder, enqueue_op, input_queue, global_step, embeddings, total_loss, train_op, summary_op, summary_writer, args.learning_rate_schedule_file, args.embedding_size, anchor, positive, negative, triplet_loss, ) # Save variables and the metagraph if it doesn't exist already save_variables_and_metagraph(sess, saver, summary_writer, model_dir, subdir, step) # Evaluate on LFW if args.lfw_dir: evaluate( sess, lfw_paths, embeddings, labels_batch, image_paths_placeholder, labels_placeholder, batch_size_placeholder, learning_rate_placeholder, phase_train_placeholder, enqueue_op, actual_issame, args.batch_size, args.lfw_nrof_folds, log_dir, step, summary_writer, args.embedding_size, ) return model_dir
def main(args): network = importlib.import_module(args.model_def) subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S') log_dir = os.path.join(os.path.expanduser(args.logs_base_dir), subdir) if not os.path.isdir( log_dir): # Create the log directory if it doesn't exist os.makedirs(log_dir) model_dir = os.path.join(os.path.expanduser(args.models_base_dir), subdir) if not os.path.isdir( model_dir): # Create the model directory if it doesn't exist os.makedirs(model_dir) # Write arguments to a text file facenet.write_arguments_to_file(args, os.path.join(log_dir, 'arguments.txt')) # Store some git revision info in a text file in the log directory src_path, _ = os.path.split(os.path.realpath(__file__)) facenet.store_revision_info(src_path, log_dir, ' '.join(sys.argv)) np.random.seed(seed=args.seed) random.seed(args.seed) train_set = facenet.get_dataset(args.data_dir) if args.filter_filename: train_set = filter_dataset(train_set, os.path.expanduser(args.filter_filename), args.filter_percentile, args.filter_min_nrof_images_per_class) nrof_classes = len(train_set) print('Model directory: %s' % model_dir) print('Log directory: %s' % log_dir) pretrained_model = None if args.pretrained_model: pretrained_model = os.path.expanduser(args.pretrained_model) print('Pre-trained model: %s' % pretrained_model) # Removed lfw dir. Using custom dataset # if args.lfw_dir: # print('LFW directory: %s' % args.lfw_dir) # # Read the file containing the pairs used for testing # pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs)) # # Get the paths for the corresponding images # lfw_paths, actual_issame = lfw.get_paths(os.path.expanduser(args.lfw_dir), pairs, args.lfw_file_ext) with tf.Graph().as_default(): tf.set_random_seed(args.seed) global_step = tf.Variable(0, trainable=False) # Get a list of image paths and their labels image_list, label_list = facenet.get_image_paths_and_labels(train_set) assert len(image_list) > 0, 'The dataset should not be empty' # Create a queue that produces indices into the image_list and label_list labels = ops.convert_to_tensor(label_list, dtype=tf.int32) range_size = array_ops.shape(labels)[0] index_queue = tf.train.range_input_producer(range_size, num_epochs=None, shuffle=True, seed=None, capacity=32) index_dequeue_op = index_queue.dequeue_many( args.batch_size * args.epoch_size, 'index_dequeue') learning_rate_placeholder = tf.placeholder(tf.float32, name='learning_rate') batch_size_placeholder = tf.placeholder(tf.int32, name='batch_size') phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train') image_paths_placeholder = tf.placeholder(tf.string, shape=(None, 1), name='image_paths') labels_placeholder = tf.placeholder(tf.int64, shape=(None, 1), name='labels') input_queue = data_flow_ops.FIFOQueue(capacity=100000, dtypes=[tf.string, tf.int64], shapes=[(1, ), (1, )], shared_name=None, name=None) enqueue_op = input_queue.enqueue_many( [image_paths_placeholder, labels_placeholder], name='enqueue_op') nrof_preprocess_threads = 4 images_and_labels = [] for _ in range(nrof_preprocess_threads): filenames, label = input_queue.dequeue() images = [] for filename in tf.unstack(filenames): file_contents = tf.read_file(filename) image = tf.image.decode_image(file_contents, channels=3) if args.random_rotate: image = tf.py_func(facenet.random_rotate_image, [image], tf.uint8) if args.random_crop: image = tf.random_crop( image, [args.image_size, args.image_size, 3]) else: image = tf.image.resize_image_with_crop_or_pad( image, args.image_size, args.image_size) if args.random_flip: image = tf.image.random_flip_left_right(image) #pylint: disable=no-member image.set_shape((args.image_size, args.image_size, 3)) images.append(tf.image.per_image_standardization(image)) images_and_labels.append([images, label]) image_batch, label_batch = tf.train.batch_join( images_and_labels, batch_size=batch_size_placeholder, shapes=[(args.image_size, args.image_size, 3), ()], enqueue_many=True, capacity=4 * nrof_preprocess_threads * args.batch_size, allow_smaller_final_batch=True) image_batch = tf.identity(image_batch, 'image_batch') image_batch = tf.identity(image_batch, 'input') label_batch = tf.identity(label_batch, 'label_batch') print('Total number of classes: %d' % nrof_classes) print('Total number of examples: %d' % len(image_list)) print('Building training graph') # Build the inference graph prelogits, _ = network.inference( image_batch, args.keep_probability, phase_train=phase_train_placeholder, bottleneck_layer_size=args.embedding_size, weight_decay=args.weight_decay) logits = slim.fully_connected( prelogits, len(train_set), activation_fn=None, weights_initializer=tf.truncated_normal_initializer(stddev=0.1), weights_regularizer=slim.l2_regularizer(args.weight_decay), scope='Logits', reuse=False) embeddings = tf.nn.l2_normalize(prelogits, 1, 1e-10, name='embeddings') # Add center loss if args.center_loss_factor > 0.0: prelogits_center_loss, _ = facenet.center_loss( prelogits, label_batch, args.center_loss_alfa, nrof_classes) tf.add_to_collection( tf.GraphKeys.REGULARIZATION_LOSSES, prelogits_center_loss * args.center_loss_factor) learning_rate = tf.train.exponential_decay( learning_rate_placeholder, global_step, args.learning_rate_decay_epochs * args.epoch_size, args.learning_rate_decay_factor, staircase=True) tf.summary.scalar('learning_rate', learning_rate) # Calculate the average cross entropy loss across the batch cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits( labels=label_batch, logits=logits, name='cross_entropy_per_example') cross_entropy_mean = tf.reduce_mean(cross_entropy, name='cross_entropy') tf.add_to_collection('losses', cross_entropy_mean) # Calculate the total losses regularization_losses = tf.get_collection( tf.GraphKeys.REGULARIZATION_LOSSES) total_loss = tf.add_n([cross_entropy_mean] + regularization_losses, name='total_loss') # Build a Graph that trains the model with one batch of examples and updates the model parameters train_op = facenet.train(total_loss, global_step, args.optimizer, learning_rate, args.moving_average_decay, tf.global_variables(), args.log_histograms) # Create a saver saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=3) # Build the summary operation based on the TF collection of Summaries. summary_op = tf.summary.merge_all() # Start running operations on the Graph. gpu_options = tf.GPUOptions( per_process_gpu_memory_fraction=args.gpu_memory_fraction) sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False)) sess.run(tf.global_variables_initializer()) sess.run(tf.local_variables_initializer()) summary_writer = tf.summary.FileWriter(log_dir, sess.graph) coord = tf.train.Coordinator() tf.train.start_queue_runners(coord=coord, sess=sess) with sess.as_default(): if pretrained_model: print('Restoring pretrained model: %s' % pretrained_model) # saver.restore(sess, pretrained_model) facenet.load_model(pretrained_model) # Training and validation loop print('Running training') epoch = 0 while epoch < args.max_nrof_epochs: step = sess.run(global_step, feed_dict=None) epoch = step // args.epoch_size # Train for one epoch train(args, sess, epoch, image_list, label_list, index_dequeue_op, enqueue_op, image_paths_placeholder, labels_placeholder, learning_rate_placeholder, phase_train_placeholder, batch_size_placeholder, global_step, total_loss, train_op, summary_op, summary_writer, regularization_losses, args.learning_rate_schedule_file) # Save variables and the metagraph if it doesn't exist already save_variables_and_metagraph(sess, saver, summary_writer, model_dir, subdir, step) # # Evaluate on LFW # if args.lfw_dir: # evaluate(sess, enqueue_op, image_paths_placeholder, labels_placeholder, phase_train_placeholder, batch_size_placeholder, # embeddings, label_batch, lfw_paths, actual_issame, args.lfw_batch_size, args.lfw_nrof_folds, log_dir, step, summary_writer) return model_dir
def align(input_dir='database', output_dir='database_aligned', image_size=182, margin=44, gpu_memory_fraction=1, random_order=False): sleep(random.random()) output_dir = os.path.expanduser(output_dir) if not os.path.exists(output_dir): os.makedirs(output_dir) # Store some git revision info in a text file in the log directory # src_path, _ = os.path.split(os.path.realpath(__file__)) cwd = os.getcwd() facenet.store_revision_info(cwd, output_dir, ' '.join(sys.argv)) dataset = facenet.get_dataset(input_dir) print(input_dir) print('Creating networks and loading parameters') with tf.Graph().as_default(): gpu_options = tf.GPUOptions( per_process_gpu_memory_fraction=gpu_memory_fraction) # noqa: E501 sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False)) with sess.as_default(): pnet, rnet, onet = detect_face.create_mtcnn(sess, None) minsize = 20 # minimum size of face threshold = [0.6, 0.7, 0.7] # three steps's threshold factor = 0.709 # scale factor # Add a random key to the filename to allow alignment using multiple # processes random_key = np.random.randint(0, high=99999) bounding_boxes_filename = os.path.join( output_dir, 'bounding_boxes_%05d.txt' % random_key) # noqa: E501 with open(bounding_boxes_filename, "w") as text_file: nrof_images_total = 0 nrof_successfully_aligned = 0 if random_order: random.shuffle(dataset) for cls in dataset: output_class_dir = os.path.join(output_dir, cls.name) if not os.path.exists(output_class_dir): os.makedirs(output_class_dir) if random_order: random.shuffle(cls.image_paths) for image_path in cls.image_paths: nrof_images_total += 1 filename = os.path.splitext(os.path.split(image_path)[1])[0] output_filename = os.path.join(output_class_dir, filename + '.png') print(image_path) if not os.path.exists(output_filename): try: img = imageio.imread(image_path) except (IOError, ValueError, IndexError) as e: errorMessage = '{}: {}'.format(image_path, e) print(errorMessage) else: if img.ndim < 2: print('Unable to align "%s"' % image_path) text_file.write('%s\n' % (output_filename)) continue if img.ndim == 2: img = facenet.to_rgb(img) img = img[:, :, 0:3] bounding_boxes, _ = detect_face.detect_face( img, minsize, pnet, rnet, onet, threshold, factor) # noqa: E501 nrof_faces = bounding_boxes.shape[0] if nrof_faces > 0: det = bounding_boxes[:, 0:4] img_size = np.asarray(img.shape)[0:2] if nrof_faces > 1: bounding_box_size = (det[:, 2] - det[:, 0]) * ( det[:, 3] - det[:, 1]) # noqa: E501 img_center = img_size / 2 offsets = np.vstack([ (det[:, 0] + det[:, 2]) / 2 - img_center[1], (det[:, 1] + det[:, 3]) / 2 - img_center[0] ]) # noqa: E501 offset_dist_squared = np.sum( np.power(offsets, 2.0), 0) # noqa: E501 index = np.argmax( bounding_box_size - offset_dist_squared * 2.0 ) # noqa: E501 # some extra weight on the centering det = det[index, :] det = np.squeeze(det) bb = np.zeros(4, dtype=np.int32) bb[0] = np.maximum(det[0] - margin / 2, 0) bb[1] = np.maximum(det[1] - margin / 2, 0) bb[2] = np.minimum(det[2] + margin / 2, img_size[1]) bb[3] = np.minimum(det[3] + margin / 2, img_size[0]) cropped = img[bb[1]:bb[3], bb[0]:bb[2], :] scaled = resize(cropped, (image_size, image_size), mode='constant') nrof_successfully_aligned += 1 # convert image to uint8 before saving imageio.imwrite(output_filename, img_as_ubyte(scaled)) text_file.write('%s %d %d %d %d\n' % (output_filename, bb[0], bb[1], bb[2], bb[3])) # noqa: E501 else: print('Unable to align "%s"' % image_path) text_file.write('%s\n' % (output_filename)) print('Total number of images: %d' % nrof_images_total) print('Number of successfully aligned images: %d' % nrof_successfully_aligned) # noqa: E501