def main(model_dir='20170512-110547', data_dir='database_aligned', is_aligned=True, image_size=160, margin=44, gpu_memory_fraction=1.0, image_batch=1000, embeddings_name='embeddings.npy', labels_name='labels.npy', labels_strings_name='label_strings.npy', return_image_list=False): train_set = facenet.get_dataset(data_dir) image_list, label_list = facenet.get_image_paths_and_labels(train_set) # fetch the classes (labels as strings) exactly as it's done in get_dataset path_exp = os.path.expanduser(data_dir) classes = [ path for path in os.listdir(path_exp) if os.path.isdir(os.path.join(path_exp, path)) ] # get the label strings label_strings = [ name for name in classes if os.path.isdir(os.path.join(path_exp, name)) ] with tf.Graph().as_default(): with tf.Session() as sess: # Load the model facenet.load_model(model_dir) # Get input and output tensors images_placeholder = tf.get_default_graph().get_tensor_by_name( "input:0") # noqa: E501 embeddings = tf.get_default_graph().get_tensor_by_name( "embeddings:0") # noqa: E501 phase_train_placeholder = tf.get_default_graph( ).get_tensor_by_name("phase_train:0") # noqa: E501 # Run forward pass to calculate embeddings nrof_images = len(image_list) print('Number of images: ', nrof_images) batch_size = image_batch if nrof_images % batch_size == 0: nrof_batches = nrof_images // batch_size else: nrof_batches = (nrof_images // batch_size) + 1 print('Number of batches: ', nrof_batches) embedding_size = embeddings.get_shape()[1] emb_array = np.zeros((nrof_images, embedding_size)) start_time = time.time() for i in range(nrof_batches): if i == nrof_batches - 1: n = nrof_images else: n = i * batch_size + batch_size # Get images for the batch if is_aligned is True: images = facenet.load_data(image_list[i * batch_size:n], False, False, image_size) else: images = load_and_align_data(image_list[i * batch_size:n], image_size, margin, gpu_memory_fraction) feed_dict = { images_placeholder: images, phase_train_placeholder: False } # Use the facenet model to calculate embeddings embed = sess.run(embeddings, feed_dict=feed_dict) emb_array[i * batch_size:n, :] = embed print('Completed batch', i + 1, 'of', nrof_batches) run_time = time.time() - start_time print('Run time: ', run_time) # export embeddings and labels label_list = np.array(label_list) np.save(embeddings_name, emb_array) if emb_array.size > 0: labels_final = (label_list) - np.min(label_list) np.save(labels_name, labels_final) label_strings = np.array(label_strings) np.save(labels_strings_name, label_strings[labels_final]) np.save('image_list.npy', image_list) if return_image_list: np.save('validation_image_list.npy', image_list) return image_list, emb_array
def main(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('Creating networks and loading parameters') with tf.Graph().as_default(): gpu_options = tf.GPUOptions( per_process_gpu_memory_fraction=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 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) 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]) 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 = 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 imageio.imwrite(output_filename, scaled) text_file.write( '%s %d %d %d %d\n' % (output_filename, 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 like_or_dislike_users(self, users): # automatically like or dislike users based on your previously trained # model on your historical preference. # facenet settings from export_embeddings.... model_dir = '20170512-110547' data_dir = 'temp_images_aligned' embeddings_name = 'temp_embeddings.npy' labels_name = 'temp_labels.npy' labels_strings_name = 'temp_label_strings.npy' is_aligned = True image_size = 160 margin = 44 gpu_memory_fraction = 1.0 image_batch = 1000 with tf.Graph().as_default(): with tf.Session() as sess: # Load the facenet model facenet.load_model(model_dir) for user in users: clean_temp_images() urls = user.get_photos(width='640') image_list = download_url_photos(urls, user.id, is_temp=True) # align the database tindetheus_align.main(input_dir='temp_images', output_dir='temp_images_aligned') # export the embeddinggs from the aligned database train_set = facenet.get_dataset(data_dir) image_list_temp, label_list = facenet.get_image_paths_and_labels( train_set) label_strings = [ name for name in os.listdir(os.path.expanduser(data_dir)) if os.path.isdir( os.path.join(os.path.expanduser(data_dir), name)) ] # Get input and output tensors images_placeholder = tf.get_default_graph( ).get_tensor_by_name("input:0") embeddings = tf.get_default_graph().get_tensor_by_name( "embeddings:0") phase_train_placeholder = tf.get_default_graph( ).get_tensor_by_name("phase_train:0") # Run forward pass to calculate embeddings nrof_images = len(image_list_temp) print('Number of images: ', nrof_images) batch_size = image_batch if nrof_images % batch_size == 0: nrof_batches = nrof_images // batch_size else: nrof_batches = (nrof_images // batch_size) + 1 print('Number of batches: ', nrof_batches) embedding_size = embeddings.get_shape()[1] emb_array = np.zeros((nrof_images, embedding_size)) start_time = time.time() for i in range(nrof_batches): if i == nrof_batches - 1: n = nrof_images else: n = i * batch_size + batch_size # Get images for the batch if is_aligned is True: images = facenet.load_data( image_list_temp[i * batch_size:n], False, False, image_size) else: images = load_and_align_data( image_list_temp[i * batch_size:n], image_size, margin, gpu_memory_fraction) feed_dict = { images_placeholder: images, phase_train_placeholder: False } # Use the facenet model to calcualte embeddings embed = sess.run(embeddings, feed_dict=feed_dict) emb_array[i * batch_size:n, :] = embed print('Completed batch', i + 1, 'of', nrof_batches) run_time = time.time() - start_time print('Run time: ', run_time) # export emedings and labels label_list = np.array(label_list) np.save(embeddings_name, emb_array) if emb_array.size > 0: # calculate the 128 average embedding per profiles X = calc_avg_emb_temp(emb_array) # ealuate on the model yhat = self.model.predict(X) if yhat[0] == 1: didILike = 'Like' else: didILike = 'Dislike' else: # there were no faces in this profile didILike = 'Dislike' print( '********************************************************' ) print(user.name, user.age, didILike) print( '********************************************************' ) dbase_names = move_images_temp(image_list, user.id) if didILike == 'Like': print(user.like()) self.likes_left -= 1 else: print(user.dislike()) userList = [ user.id, user.name, user.age, user.bio, user.distance_km, user.jobs, user.schools, user.get_photos(width='640'), dbase_names, didILike ] self.al_database.append(userList) np.save('al_database.npy', self.al_database) clean_temp_images_aligned()
def like_or_dislike_users(self, users): # automatically like or dislike users based on your previously trained # model on your historical preference. # facenet settings from export_embeddings.... data_dir = 'temp_images_aligned' embeddings_name = 'temp_embeddings.npy' # labels_name = 'temp_labels.npy' # labels_strings_name = 'temp_label_strings.npy' is_aligned = True image_size = 160 margin = 44 gpu_memory_fraction = 1.0 image_batch = 1000 prev_user = None for user in users: clean_temp_images() urls = user.get_photos(width='640') image_list = download_url_photos(urls, user.id, is_temp=True) # align the database tindetheus_align.main(input_dir='temp_images', output_dir='temp_images_aligned') # export the embeddings from the aligned database train_set = facenet.get_dataset(data_dir) image_list_temp, label_list = facenet.get_image_paths_and_labels(train_set) # noqa: E501 # Get input and output tensors images_placeholder = tf.get_default_graph().get_tensor_by_name("input:0") # noqa: E501 embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0") # noqa: E501 phase_train_placeholder = tf.get_default_graph().get_tensor_by_name("phase_train:0") # noqa: E501 # Run forward pass to calculate embeddings nrof_images = len(image_list_temp) print('Number of images: ', nrof_images) batch_size = image_batch if nrof_images % batch_size == 0: nrof_batches = nrof_images // batch_size else: nrof_batches = (nrof_images // batch_size) + 1 print('Number of batches: ', nrof_batches) embedding_size = embeddings.get_shape()[1] emb_array = np.zeros((nrof_images, embedding_size)) start_time = time.time() for i in range(nrof_batches): if i == nrof_batches - 1: n = nrof_images else: n = i*batch_size + batch_size # Get images for the batch if is_aligned is True: images = facenet.load_data(image_list_temp[i*batch_size:n], # noqa: E501 False, False, image_size) else: images = load_and_align_data(image_list_temp[i*batch_size:n], # noqa: E501 image_size, margin, gpu_memory_fraction) feed_dict = {images_placeholder: images, phase_train_placeholder: False} # Use the facenet model to calculate embeddings embed = self.sess.run(embeddings, feed_dict=feed_dict) emb_array[i*batch_size:n, :] = embed print('Completed batch', i+1, 'of', nrof_batches) run_time = time.time() - start_time print('Run time: ', run_time) # export embeddings and labels label_list = np.array(label_list) np.save(embeddings_name, emb_array) if emb_array.size > 0: # calculate the n average embedding per profiles X = calc_avg_emb_temp(emb_array) # evaluate on the model yhat = self.model.predict(X) if yhat[0] == 1: didILike = 'Like' # check to see if this is the same user as before if prev_user == user.id: clean_temp_images_aligned() print('\n\n You have already liked this user!!! \n \n') print('This typically means you have used all of your' ' free likes. Exiting program!!! \n\n') self.likes_left = -1 return else: prev_user = user.id else: didILike = 'Dislike' else: # there were no faces in this profile didILike = 'Dislike' print('**************************************************') print(user.name, user.age, didILike) print('**************************************************') dbase_names = move_images_temp(image_list, user.id) if didILike == 'Like': print(user.like()) self.likes_left -= 1 else: print(user.dislike()) userList = [user.id, user.name, user.age, user.bio, user.distance_km, user.jobs, user.schools, user.get_photos(width='640'), dbase_names, didILike] self.al_database.append(userList) np.save('al_database.npy', self.al_database) clean_temp_images_aligned()