def align_face(pic_path): if os.path.exists(pic_path): try: img = misc.imread(pic_path) except (IOError, ValueError, IndexError) as e: errorMessage = '{}: {}'.format(pic_path, e) print(errorMessage) if img.ndim < 2: print('Unable to align "%s"' % pic_path) return 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 = misc.imresize(cropped, (image_size, image_size), interp='bilinear') misc.imsave(pic_path, scaled)
def align_face(pic_path): if os.path.exists(pic_path): try: img = misc.imread(pic_path) except (IOError, ValueError, IndexError) as e: errorMessage = '{}: {}'.format(pic_path, e) print(errorMessage) if img.ndim < 2: print('Unable to align "%s"' % pic_path) return 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 = misc.imresize(cropped, (image_size, image_size), interp='bilinear') misc.imsave(pic_path, scaled)
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 process_data(self, class_name, image_paths, text_file, result_file): output_class_dir = os.path.join(self.out_image_dir, class_name) tf.io.gfile.mkdir(output_class_dir) if self.random_order: random.shuffle(image_paths) for image_path in image_paths: file = os.path.split(image_path)[1] filename = os.path.splitext(file)[0] output_filename = os.path.join(output_class_dir, filename + '.png') tmp_path = os.path.join(self.tmp_dir, file) tf.io.gfile.copy(image_path, tmp_path, True) try: # img = misc.imread(tmp_path) img = imread(tmp_path) except (IOError, ValueError, IndexError) as e: error_message = '{}: {}\n'.format(image_path, e) result_file.write(error_message) else: if img.ndim < 2: result_file.write('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, self.minsize, self.pnet, self.rnet, self.onet, self.threshold, self.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 self.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) 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] - self.margin / 2, 0) bb[1] = np.maximum(det[1] - self.margin / 2, 0) bb[2] = np.minimum(det[2] + self.margin / 2, img_size[1]) bb[3] = np.minimum(det[3] + self.margin / 2, img_size[0]) cropped = img[bb[1]:bb[3], bb[0]:bb[2], :] # scaled = misc.imresize(cropped, (self.image_size, self.image_size), interp='bilinear') scaled = np.array( Image.fromarray(cropped).resize( (self.image_size, self.image_size), resample=Image.BILINEAR)) filename_base, file_extension = os.path.splitext( tmp_path) if self.detect_multiple_faces: tmp_filename_n = "{}_{}{}".format( filename_base, i, file_extension) else: tmp_filename_n = "{}{}".format( filename_base, file_extension) # misc.imsave(tmp_filename_n, scaled) imsave(tmp_filename_n, scaled) output_filename_n = os.path.join( output_class_dir, os.path.split(tmp_filename_n)[1]) tf.io.gfile.copy(tmp_filename_n, output_filename_n, True) text_file.write( '%s %d %d %d %d\n' % (output_filename_n, bb[0], bb[1], bb[2], bb[3])) else: result_file.write('Unable to align "%s"' % image_path) text_file.write('%s\n' % (output_filename))
def gen(camera): sess = tf.Session() with sess.as_default(): pnet, rnet, onet = detect_face.create_mtcnn(sess, None) facenet.load_model( '/home/rohitner/models/facenet/20180402-114759/20180402-114759.pb') 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") classifier_filename_exp = '/home/rohitner/models/lfw_classifier.pkl' with open(classifier_filename_exp, 'rb') as infile: (model, class_names) = pickle.load(infile) print('Loaded classifier model from file "%s"' % classifier_filename_exp) minsize = 20 # minimum size of face threshold = [0.6, 0.7, 0.7] # three steps's threshold factor = 0.709 # scale factor file_index = 0 while True: success, img = camera.read() results = tfnet.return_predict(img) for result in results: cv2.rectangle( img, (result["topleft"]["x"], result["topleft"]["y"]), (result["bottomright"]["x"], result["bottomright"]["y"]), (255, 0, 0), 4) text_x, text_y = result["topleft"]["x"] - 10, result[ "topleft"]["y"] - 10 cv2.putText(img, result["label"], (text_x, text_y), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 255, 0), 2, cv2.LINE_AA) if img.ndim < 2: print('Unable to align') 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] det_arr = [] img_size = np.asarray(img.shape)[0:2] if nrof_faces > 1: if True: # 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] - 44 / 2, 0) bb[1] = np.maximum(det[1] - 44 / 2, 0) bb[2] = np.minimum(det[2] + 44 / 2, img_size[1]) bb[3] = np.minimum(det[3] + 44 / 2, img_size[0]) cropped = img[bb[1]:bb[3], bb[0]:bb[2], :] scaled = misc.imresize(cropped, (160, 160), interp='bilinear') scaled = prewhiten_and_expand(scaled) emb = sess.run(embeddings, feed_dict={ images_placeholder: scaled, phase_train_placeholder: False }) predictions = model.predict_proba(emb) best_class_indices = np.argmax(predictions) best_class_probabilities = predictions[0, best_class_indices] font = cv2.FONT_HERSHEY_SIMPLEX cv2.rectangle(img, (bb[0], bb[1]), (bb[2], bb[3]), (0, 255, 0), 5) cv2.putText(img, class_names[best_class_indices], (bb[0], bb[1] - 10), font, 0.5, (255, 0, 0), 2, cv2.LINE_AA) else: print('No face detected') ret, jpeg = cv2.imencode('.jpg', img) frame = jpeg.tobytes() yield (b'--frame\r\n' b'Content-Type: image/jpeg\r\n\r\n' + frame + b'\r\n\r\n')
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