111
# -*- coding: utf-8 -*- # CLASSWORLDS # 2018/11/25 from __future__ import absolute_import from __future__ import division from __future__ import print_function import copy import os import numpy as np import tensorflow as tf from facenet.src import align from facenet.src import facenet from facenet.src.align import detect_face from scipy import misc tf.Graph().as_default() gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=1.0) sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False)) facenet.load_model("model/20180408-102900.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") pnet, rnet, onet = align.detect_face.create_mtcnn(sess, None) print("model loaded successfully.") def compute(image_files,image_size=160,margin=44): images = load_and_align_data(image_files, image_size, margin) feed_dict = {images_placeholder: images, phase_train_placeholder: False} emb = sess.run(embeddings, feed_dict=feed_dict) return emb[0,:] def load_and_align_data(image_paths, image_size, margin): minsize = 20 # minimum size of face threshold = [0.6, 0.7, 0.7] # three steps's threshold factor = 0.709 # scale factor print('Creating networks and loading parameters') tmp_image_paths = copy.copy(image_paths) img_list = [] for image in tmp_image_paths: img = misc.imread(os.path.expanduser(image), mode='RGB') img_size = np.asarray(img.shape)[0:2] bounding_boxes, _ = align.detect_face.detect_face(img, minsize, pnet, rnet, onet, threshold, factor) if len(bounding_boxes) < 1: image_paths.remove(image) print("can't detect face, remove ", image) continue det = np.squeeze(bounding_boxes[0, 0:4]) 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], :] aligned = misc.imresize(cropped, (image_size, image_size), interp='bilinear') # misc.imsave("oops", aligned) prewhitened = facenet.prewhiten(aligned) img_list.append(prewhitened) images = np.stack(img_list) return images def bulk_detect_face(image_paths, image_size=160, margin=16): minsize = 0.01 # minimum size of face threshold = [0.6, 0.7, 0.7] # three steps's threshold factor = 0.3 # scale factor print('Creating networks and loading parameters') tmp_image_paths = copy.copy(image_paths) img_list = [] for index,image in enumerate(tmp_image_paths): img = misc.imread(os.path.expanduser(image), mode='RGB') img_size = np.asarray(img.shape)[0:2] for (bounding_boxes, _) in align.detect_face.bulk_detect_face([img], minsize, pnet, rnet, onet, threshold, factor): #bounding_boxes, _ = align.detect_face.bulk_detect_face(img, minsize, pnet, rnet, onet, threshold, factor) if len(bounding_boxes) < 1: image_paths.remove(image) print("can't detect face, remove ", image) continue det = np.squeeze(bounding_boxes[0, 0:4]) 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], :] aligned = misc.imresize(cropped, (image_size, image_size), interp='bilinear') misc.imsave("oops"+str(index)+".png", aligned) prewhitened = facenet.prewhiten(aligned) img_list.append(prewhitened) images = np.stack(img_list) return images def transform(faceImagePath): return compute([faceImagePath])
posted on 2018-12-15 18:33 michaelchan 阅读(68) 评论(0) 编辑 收藏 举报