def main(data_dir, min_size): with tf.Graph().as_default(): gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.0) 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, npy) minsize = min_size # minimum size of face threshold = [0.6, 0.7, 0.7] # three steps's threshold factor = 0.709 # scale factor dataset = face_net.get_dataset(data_dir) number_sample = 0 number_face_detected = 0 for cls in dataset: for image_path in cls.image_paths: number_sample = number_sample + 1 img = cv2.imread(image_path, cv2.IMREAD_UNCHANGED) if img.ndim == 2: img = face_net.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): print('{0} face detected : {1}'.format( nrof_faces, image_path)) elif (nrof_faces == 2): print('{0} face detected : {1}'.format( nrof_faces, image_path)) number_face_detected = number_face_detected + 1 else: number_face_detected = number_face_detected + 1 print("Finish!!!!") print('Number face detected {0}'.format(number_face_detected))
while True: ret, frame = video_capture.read() if ret == False: break # frame = cv2.resize(frame, (650, 650), fx=0.5, fy=0.5) # resize frame (optional) number_frame += 1 # curTime = time.time() + 1 # calc fps timeF = frame_interval if (c % timeF == 0): find_results = [] if frame.ndim == 2: frame = face_net.to_rgb(frame) frame = frame[:, :, 0:3] bounding_boxes, _ = detect_face.detect_face( frame, minsize, pnet, rnet, onet, threshold, factor) nrof_faces = bounding_boxes.shape[0] # if nrof_faces > 0: # print('Detected_FaceNum: %d' % nrof_faces) output_filename = os.path.expanduser( output_dir + '/{0}_{1}_{2}.jpg'.format( nrof_faces, number_frame, datetime.strftime(datetime.now(), '%Y%m%d%H%M%S%f'))) cv2.imwrite(output_filename, frame) if nrof_faces > 0: det = bounding_boxes[:, 0:4] det_arr = []
def main(data_dir, output_dir): sleep(random.random()) 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('argument default')) dataset = face_net.get_dataset(data_dir) print('Creating networks and loading parameters') with tf.Graph().as_default(): gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=constants.GPU_MEMORY_FRACTION_DEFAULT) 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 = constants.FACE_REG_MINSIZE # minimum size of face threshold = constants.ALIGN_THRESHOLD # three steps's threshold factor = constants.ALIGN_FACTOR # scale factor # Add a random key to the filename to allow alignment using multiple processes random_key = np.random.randint(0, high=99999) face_detected_list = [] nrof_images_total = 0 nrof_successfully_aligned = 0 if constants.ALIGN_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 constants.ALIGN_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') if not os.path.exists(output_filename): try: img = misc.imread(image_path) except (IOError, ValueError, IndexError) as e: error_message = '{}: {}'.format(image_path, e) print(error_message) else: if img.ndim < 2: print('Unable to align "%s"' % image_path) face_detected_list.append('Unable to align {0}'.format(image_path)) # text_file.write('%s\n' % (output_filename)) continue if img.ndim == 2: img = face_net.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 constants.ALIGN_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] - constants.COMPARE_MARGIN_DEFAULT / 2, 0) bb[1] = np.maximum(det[1] - constants.COMPARE_MARGIN_DEFAULT / 2, 0) bb[2] = np.minimum(det[2] + constants.COMPARE_MARGIN_DEFAULT / 2, img_size[1]) bb[3] = np.minimum(det[3] + constants.COMPARE_MARGIN_DEFAULT / 2, img_size[0]) cropped = img[bb[1]:bb[3], bb[0]:bb[2], :] scaled = misc.imresize(cropped, (constants.ALIGN_IMAGE_SIZE, constants.ALIGN_IMAGE_SIZE), interp='bilinear') nrof_successfully_aligned += 1 filename_base, file_extension = os.path.splitext(output_filename) if constants.ALIGN_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) face_detected_list.append('%s --- BOX [%d , %d , %d , %d]\n' % (output_filename_n, bb[0], bb[1], bb[2], bb[3])) else: face_detected_list.append('Unable to align {0}'.format(image_path)) print('Total number of images: %d' % nrof_images_total) print('Number of successfully aligned images: %d' % nrof_successfully_aligned) return nrof_images_total, nrof_successfully_aligned, face_detected_list
def main(image_path, data_dir, model_dir, classifier_file): npy = '' with tf.Graph().as_default(): gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=constants. GPU_MEMORY_FRACTION_DEFAULT) 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 = constants.FACE_REG_MINSIZE # minimum size of face threshold = constants.ALIGN_THRESHOLD # three steps's threshold factor = constants.ALIGN_FACTOR # scale factor frame_interval = 3 image_size = 160 input_image_size = 160 human_names = os.listdir(data_dir) human_names.sort() print('Loading feature extraction model') face_net.load_model(model_dir) 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") embedding_size = embeddings.get_shape()[1] classifier_filename_exp = os.path.expanduser(classifier_file) with open(classifier_filename_exp, 'rb') as infile: (model, class_names) = pickle.load(infile) c = 0 print('Start Recognition!') frame = cv2.imread(image_path, 0) time_f = frame_interval if c % time_f == 0: if frame.ndim == 2: frame = face_net.to_rgb(frame) frame = frame[:, :, 0:3] bounding_boxes, _ = detect_face.detect_face( frame, minsize, pnet, rnet, onet, threshold, factor) nrof_faces = bounding_boxes.shape[0] print('Face Detected: %d' % nrof_faces) if nrof_faces > 0: det = bounding_boxes[:, 0:4] cropped = [] scaled = [] scaled_reshape = [] bb = np.zeros((nrof_faces, 4), dtype=np.int32) for i in range(nrof_faces): emb_array = np.zeros((1, embedding_size)) bb[i][0] = det[i][0] bb[i][1] = det[i][1] bb[i][2] = det[i][2] bb[i][3] = det[i][3] # inner exception if bb[i][0] <= 0 or bb[i][1] <= 0 or bb[i][2] >= len( frame[0]) or bb[i][3] >= len(frame): print('face is too close') break cropped.append(frame[bb[i][1]:bb[i][3], bb[i][0]:bb[i][2], :]) cropped[i] = face_net.flip(cropped[i], False) scaled.append( misc.imresize(cropped[i], (image_size, image_size), interp='bilinear')) scaled[i] = cv2.resize( scaled[i], (input_image_size, input_image_size), interpolation=cv2.INTER_CUBIC) scaled[i] = face_net.prewhiten(scaled[i]) scaled_reshape.append(scaled[i].reshape( -1, input_image_size, input_image_size, 3)) feed_dict = { images_placeholder: scaled_reshape[i], phase_train_placeholder: False } emb_array[0, :] = sess.run(embeddings, feed_dict=feed_dict) predictions = model.predict_proba(emb_array) print(predictions) best_class_indices = np.argmax(predictions, axis=1) # print(best_class_indices) best_class_probabilities = predictions[ np.arange(len(best_class_indices)), best_class_indices] print(best_class_probabilities) cv2.rectangle(frame, (bb[i][0], bb[i][1]), (bb[i][2], bb[i][3]), (0, 255, 0), 2) # boxing face # plot result idx under box text_x = bb[i][0] text_y = bb[i][3] - 10 print( i, 'Result Indices: ', best_class_indices[0], ' : ', 'Face detected of : {0}'.format( human_names[best_class_indices[0]])) print(human_names) for H_i in human_names: # print(H_i) if human_names[best_class_indices[ 0]] == H_i and best_class_probabilities >= constants.FACE_REG_POSSIBILITY: result_names = human_names[ best_class_indices[0]] cv2.putText(frame, str(i) + ': ' + result_names, (text_x, text_y), cv2.FONT_HERSHEY_PLAIN, 1, (0, 0, 255), thickness=1, lineType=1) print('------------------') else: print('Unable to align') frame = cv2.resize(frame, (0, 0), fx=0.5, fy=0.5) # resize frame (optional) cv2.imshow('Image', frame) cv2.imwrite('output/' + image_path.split('/')[-1], frame) if cv2.waitKey(1000000) & 0xFF == ord('q'): sys.exit("Thanks")
def main(test_dir, data_dir, model_dir, classifier_file): with tf.Graph().as_default(): gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=constants. GPU_MEMORY_FRACTION_DEFAULT) 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 = constants.FACE_REG_MINSIZE # minimum size of face threshold = constants.ALIGN_THRESHOLD # three steps's threshold factor = constants.ALIGN_FACTOR # scale factor image_size = 160 input_image_size = 160 human_names = os.listdir(data_dir) human_names.sort() print('Loading feature extraction model') face_net.load_model(model_dir) 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") embedding_size = embeddings.get_shape()[1] classifier_filename_exp = os.path.expanduser(classifier_file) with open(classifier_filename_exp, 'rb') as infile: (model, class_names) = pickle.load(infile) c = 0 print('Start Recognition!') dataset = face_net.get_dataset(test_dir) number_of_face_recognition = 0 for cls in dataset: for image_path in cls.image_paths: frame = cv2.imread(image_path, 0) if frame.ndim == 2: frame = face_net.to_rgb(frame) frame = frame[:, :, 0:3] bounding_boxes, _ = detect_face.detect_face( frame, minsize, pnet, rnet, onet, threshold, factor) nrof_faces = bounding_boxes.shape[0] if nrof_faces > 0: det = bounding_boxes[:, 0:4] cropped = [] scaled = [] scaled_reshape = [] bb = np.zeros((nrof_faces, 4), dtype=np.int32) for i in range(nrof_faces): emb_array = np.zeros((1, embedding_size)) bb[i][0] = det[i][0] bb[i][1] = det[i][1] bb[i][2] = det[i][2] bb[i][3] = det[i][3] # inner exception if bb[i][0] <= 0 or bb[i][1] <= 0 or bb[i][ 2] >= len( frame[0]) or bb[i][3] >= len(frame): print( 'Face is too close {0}'.format(image_path)) break cropped.append(frame[bb[i][1]:bb[i][3], bb[i][0]:bb[i][2], :]) cropped[i] = face_net.flip(cropped[i], False) scaled.append( misc.imresize(cropped[i], (image_size, image_size), interp='bilinear')) scaled[i] = cv2.resize( scaled[i], (input_image_size, input_image_size), interpolation=cv2.INTER_CUBIC) scaled[i] = face_net.prewhiten(scaled[i]) scaled_reshape.append(scaled[i].reshape( -1, input_image_size, input_image_size, 3)) feed_dict = { images_placeholder: scaled_reshape[i], phase_train_placeholder: False } emb_array[0, :] = sess.run(embeddings, feed_dict=feed_dict) predictions = model.predict_proba(emb_array) best_class_indices = np.argmax(predictions, axis=1) # print(best_class_indices) best_class_probabilities = predictions[ np.arange(len(best_class_indices)), best_class_indices] # plot result idx under box for H_i in human_names: # print(H_i) if human_names[best_class_indices[0]] == H_i \ and H_i in image_path: print('{0} : {1}'.format( best_class_probabilities, image_path)) number_of_face_recognition = number_of_face_recognition + 1 else: print('Unable to recognition {0}'.format(image_path)) print("Finish!!!!") print('Number face detected {0}'.format(number_of_face_recognition))