def detect(self,image_path):
aligned = []
try:
img = misc.imread(image_path)
except (IOError, ValueError, IndexError) as e:
errorMessage = '{}: {}'.format(image_path, e)
logging.info(errorMessage)
else:
if img.ndim < 2:
logging.info('Unable to align "%s"' % image_path)
return []
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_all = bounding_boxes[:, 0:4]
img_size = np.asarray(img.shape)[0:2]
for boxindex in range(nrof_faces):
det = np.squeeze(det_all[boxindex, :])
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])
left, top, right, bottom = bb[0], bb[1], bb[2], bb[3]
aligned.append({'x': left,'y':top,'w':right-left,'h':bottom-top})
return aligned
def load_image(path):
image_size = 160
img = misc.imread(path)
if img.ndim == 2:
img = to_rgb(img)
img = prewhiten(img)
img = crop(img, False, image_size)
img = flip(img, False)
return img
def raw_process(img):
if img.ndim == 2:
img = to_rgb(img)
try:
img = prewhiten(img)
except:
pass
img = crop(img, False, 160)
img = flip(img, False)
return img
def align_dataset_mtcnn(target,
image_size=160,
margin=44,
random_order='store_true',
gpu_memory_fraction=1.0,
detect_multiple_faces=True,
text_counter=0):
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 = align.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
bounding_box_list = []
output_class_dir = os.path.join('tmp', target)
files = list(
filter(lambda x: 'DS_Store' not in x,
sorted(os.listdir(output_class_dir))))
if len(files) == 0:
print('fatal: no image in target folder')
filename = files[0]
filepath = os.path.join(output_class_dir, filename)
try:
img = misc.imread(filepath)
except (IOError, ValueError, IndexError) as e:
errorMessage = '{}: {}'.format(filepath, e)
print('fatal:', errorMessage)
return
if img.ndim < 2:
print('fatal:', 'Unable to align "%s"' % filepath)
return
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 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] - 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')
bounding_box_list.append(bb[:4])
else:
print('fatal:', 'Unable to align "%s"' % filepath)
return filename, bounding_box_list
def align(image_path):
print('Creating networks and loading parameters')
with 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))
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)
filename = os.path.splitext(os.path.split(image_path)[1])[0]
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)
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]
print('nrof_faces: %s' % nrof_faces)
n = 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,:]
for one in det:
one = np.squeeze(one)
bb = np.zeros(4, dtype=np.int32)
bb[0] = np.maximum(one[0] - 5.0 / 2, 0)
bb[1] = np.maximum(one[1] - 5.0 / 2, 0)
bb[2] = np.minimum(one[2] + 5.0 / 2, img_size[1])
bb[3] = np.minimum(one[3] + 5.0 / 2, img_size[0])
cropped = img[bb[1]:bb[3], bb[0]:bb[2], :]
scaled = misc.imresize(cropped, (128, 128),
interp='bilinear')
misc.imsave('/dl/' + str(n) + '.png', scaled)
n += 1
else:
print('Unable to align "%s"' % image_path)
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, _ = 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 RecognizeFace(frames, model=None, class_names=None):
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.6)
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 = 20 # minimum size of face
threshold = [0.6, 0.7, 0.7] # three steps's threshold
factor = 0.709 # scale factor
margin = 32
frame_interval = 3
batch_size = 1000
image_size = 160
input_image_size = 160
print('Loading feature extraction model')
facenet.load_model(modeldir)
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_filename)
if model == None or class_names == None:
with open(classifier_filename_exp, 'rb') as infile:
(model, class_names) = pickle.load(infile)
# video_capture = cv2.VideoCapture("akshay_mov.mp4")
c = 0
HumanNames = class_names
print(HumanNames)
print('Start Recognition!')
prevTime = 0
# ret, frame = video_capture.read()
#frame = cv2.imread(img_path,0)
#frame = cv2.resize(frame, (0,0), fx=0.5, fy=0.5) #resize frame (optional)
total_faces_detected = {}
for frame in frames:
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
curTime = time.time() + 1 # calc fps
timeF = frame_interval
if (c % timeF == 0):
find_results = []
if frame.ndim == 2:
frame = facenet.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]
img_size = np.asarray(frame.shape)[0:2]
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] = facenet.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] = facenet.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]
#plot result idx under box
text_x = bb[i][0]
text_y = bb[i][3] + 20
print('Result Indices: ',
best_class_indices[0])
print(HumanNames)
for H_i in HumanNames:
# print(H_i)
if HumanNames[best_class_indices[
0]] == H_i and best_class_probabilities >= 0.4:
result_names = HumanNames[
best_class_indices[0]]
if result_names in total_faces_detected:
if predictions[0][best_class_indices[
0]] > total_faces_detected[
result_names]:
total_faces_detected[
result_names] = predictions[
0][best_class_indices[
0]]
else:
total_faces_detected[
result_names] = predictions[0][
best_class_indices[0]]
else:
print("BHAKKK")
if len(total_faces_detected) == 0:
return None
else:
x = sorted(total_faces_detected.items(),
key=operator.itemgetter(1))
return [x[len(x) - 1][0]]