def parse(self, filename):
self.sample_size = self.file_len(filename) // NUM_ROWS
f = open(filename, "r") #opens trainingimages
retlist = []
# parsing
for i in xrange (0, self.sample_size):
currList = [] #the array of lines for each Digit
curr_digit = Face()
for i in xrange(NUM_ROWS):
currline = f.readline()
currList.append(currline)
curr_digit.number = currList
curr_digit.processFeatures()
retlist.append(curr_digit)
f.close()
return retlist
def iterateNetThroughPath(path, trans, speed, network, center, win, updateTime ):
for i in range(len(trans)):
plt.scatter(path[i][0],path[i][1],label="Posisjon")
plt.draw()
faceParam = network.activate(trans[i])
smileDeg, pupilx, pupily, eyebrow = faceParam
Face.drawFace(center,smileDeg, pupilx, pupily, 0, eyebrow, win )
win.update()
printNetInOut(trans[i],faceParam, path[i],speed)
time.sleep(updateTime)
inText = contents(filename)
tempname = "HFacer.tmp"
out = open(tempname, "w")
hfile = open(filename)
CopyWithInsertion(hfile, out, genfn, definition)
out.close()
hfile.close()
outText = contents(tempname)
if inText == outText:
os.unlink(tempname)
else:
os.unlink(filename)
os.rename(tempname, filename)
f = Face.Face()
try:
f.ReadFromFile("Scintilla.iface")
findEnumValues(f)
with open("ScintillaWrapperGenerated.cpp", 'w') as cpp:
writeCppFile(f, cpp)
Regenerate("ScintillaWrapper.h", writeHFile, f)
Regenerate("ScintillaPython.cpp", writeBoostWrapFile, f)
Regenerate("Enums.h", writeEnumsHFile, f)
Regenerate("EnumsWrapper.cpp", writeEnumsWrapperFile, f)
Regenerate(r"..\..\docs\source\scintilla.rst", writeScintillaDoc, f)
Regenerate(r"..\..\docs\source\enums.rst", writeScintillaEnums, f)
#Regenerate("SciLexer.h", printLexHFile, f)
#print("Maximum ID is %s" % max([x for x in f.values if int(x) < 3000]))
except:
def RegenerateAll(root):
f = Face.Face()
f.ReadFromFile(root + "include/SciLexer.iface")
Regenerate(root + "include/SciLexer.h", "/* ", printLexHFile(f))
def understoodType(t):
return t in understoodTypes or Face.IsEnumeration(t)
def main(args):
videoLink = args.video_link
print('Creating networks and loading parameters')
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, None)
minsize = 20 # minimum size of face
threshold = [0.6, 0.7, 0.7] # three steps's threshold
factor = 0.709 # scale factor
margin = 44
frame_interval = args.frame_interval
batch_size = 1000
image_size = 182
input_image_size = 160
max_age = args.max_age
print('Loading feature extraction model')
modeldir = args.modeldir
debug = args.debug
print("Debug: ", debug)
if debug == 'True':
debug = True
else:
debug = False
if debug:
print("videoLink: ", args.video_link)
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 = args.classifier_filename
classifier_filename_exp = os.path.expanduser(classifier_filename)
with open(classifier_filename_exp, 'rb') as infile:
(model, class_names) = pickle.load(infile)
print('load classifier file-> %s' % classifier_filename_exp)
# video_capture = cv2.VideoCapture(0) #webcam
video_capture = cv2.VideoCapture(args.video_link)
c = 0
fid = 0
faces = []
target_distance = args.target_distance
print('Start Recognition!')
prevTime = 0
while True:
ret, frame = video_capture.read()
frame = cv2.resize(frame, (0, 0), fx=0.5,
fy=0.5) # resize frame (optional)
curTime = time.time() + 1 # calc fps
timeF = frame_interval
new = True
show = False
for i in faces:
i.age_one()
if (c % timeF == 0):
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]
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):
if debug:
print('face is inner of range!')
continue
cropped.append(frame[bb[i][1]:bb[i][3],
bb[i][0]:bb[i][2], :])
try:
cropped[i] = facenet.flip(cropped[i], False)
except:
continue
if debug:
print('Processing Status: PROCESSING FRAME')
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)
best_class_indices = np.argmax(predictions, axis=1)
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
if debug:
print('frame_interval: ', frame_interval)
# track faces
result_names = class_names[best_class_indices[0]]
for k in faces:
# print(best_class_probabilities[0])
if abs(bb[i][0]-k.getX()) <= target_distance\
and abs(bb[i][1] - k.getY())\
<= target_distance and k.getDone() is False:
if debug:
print(k.getAge(), 'X Diff: ',
abs(bb[i][0] - k.getX()),
'Y Diff: ',
abs(bb[i][1] - k.getY()))
new = False
if best_class_probabilities[0] > 0.20:
k.updateCoords(bb[i][0], bb[i][1])
k.updateConfidence(
best_class_probabilities[0])
result_names = class_names[
best_class_indices[0]]
k.updateStaffID(
result_names.split(' ')[0])
k.updateName(
result_names.split(' ')[1])
if k.getAge() > 1:
show = True
color = k.getRGB()
counter = Counter(k.getName())
most_common = counter.most_common()
if debug:
print('Show: ', show)
print(most_common)
if show:
if len(most_common) >= 2:
f_n, f_v = most_common[0]
s_n, s_v = most_common[1]
if f_n != 'Unk':
name_to_show = f_n
# name_to_show = name_mode
else:
name_to_show = s_n
if len(most_common) == 1:
f_n, f_v = most_common[0]
name_to_show = f_n
# print(name_to_show)
if new:
f = Face.MyFace(fid, bb[i][0], bb[i][1],
max_age)
f.updateConfidence(best_class_probabilities[0])
result_names = class_names[
best_class_indices[0]]
f.updateStaffID(result_names.split(' ')[0])
name = result_names.split(' ')[1]
f.updateName(name)
color = f.getRGB()
faces.append(f)
fid += 1
name_to_show = ''
cv2.rectangle(frame, (bb[i][0], bb[i][1]),
(bb[i][2], bb[i][3]), color,
2) # boxing face
if name_to_show == 'Unk':
name_to_show = 'Unknown'
if debug:
print('Detected As: ', name_to_show)
cv2.putText(frame,
name_to_show, (text_x, text_y),
cv2.FONT_HERSHEY_COMPLEX_SMALL,
1,
color,
thickness=1,
lineType=2)
else:
if debug:
print('Unable to align')
else:
if debug:
print('Processing Status: NOT PROCESSING FRAME')
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]
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):
if debug:
print('face is inner of range!')
continue
for k in faces:
# print(best_class_probabilities[0])
if abs(bb[i][0]-k.getX()) <= target_distance\
and abs(bb[i][1] - k.getY())\
<= target_distance and k.getDone() is False:
if debug:
print(k.getAge(), 'X Diff: ',
abs(bb[i][0] - k.getX()),
'Y Diff: ',
abs(bb[i][1] - k.getY()))
if k.getAge() > 1:
show = True
color = k.getRGB()
counter = Counter(k.getName())
most_common = counter.most_common()
text_x = bb[i][0]
text_y = bb[i][3] + 20
if debug:
print('Show: ', show)
print(most_common)
if show:
if len(most_common) >= 2:
f_n, f_v = most_common[0]
s_n, s_v = most_common[1]
if f_n != 'Unk':
name_to_show = f_n
# name_to_show = name_mode
else:
name_to_show = s_n
elif len(most_common) == 1:
f_n, f_v = most_common[0]
name_to_show = f_n
else:
name_to_show = 'Unknown'
cv2.rectangle(frame,
(bb[i][0], bb[i][1]),
(bb[i][2], bb[i][3]),
color, 2) # boxing face
if name_to_show == 'Unk':
name_to_show = 'Unknown'
if debug:
print('Detected As: ',
name_to_show)
cv2.putText(
frame,
name_to_show, (text_x, text_y),
cv2.FONT_HERSHEY_COMPLEX_SMALL,
1,
color,
thickness=1,
lineType=2)
sec = curTime - prevTime
prevTime = curTime
fps = 1 / (sec)
str = 'FPS: %2.3f' % fps
text_fps_x = len(frame[0]) - 150
text_fps_y = 20
cv2.putText(frame,
str, (text_fps_x, text_fps_y),
cv2.FONT_HERSHEY_COMPLEX_SMALL,
1, (0, 0, 0),
thickness=1,
lineType=2)
c += 1
if frame.shape[0] < 1000:
frame = cv2.resize(frame, (0, 0), fx=1.5, fy=1.5)
cv2.imshow('Video', frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
video_capture.release()
# #video writer
# out.release()
cv2.destroyAllWindows()
class LocalPrefixDiscovery:
#private:
__slots__ = [
"_subscribers", "_currentPrefix", "_needStopDiscovery", "_scheduler",
"_timeouts", "_face", "_evenLoop", "_eventLoopThread", "_periodicity"
]
# public:
def __init__(self, periodicity=30): # 30 seconds
self._periodicity = periodicity
self._subscribers = {}
self._currentPrefix = Name()
self._needStopDiscovery = True
self._scheduler = Scheduler()
self._scheduler.start()
self._timeouts = 0
self._face = Face()
self._eventLoop = Face.EventLoop(self._face)
def subscribe(self, tag, callback):
self._subscribers[tag] = callback
if (len(self._subscribers.values()) == 1):
self._start()
def unsubscribe(self, tag):
del self._subscribers[tag]
if (len(self._subscribers.values()) == 0):
self._stop()
def shutdown(self):
self._stop()
self._scheduler.shutdown()
#private:
def _start(self):
self._needStopDiscovery = False
self._eventLoopThread = threading.Thread(
target=self._pyndn_loop_ignoring_errors)
self._eventLoopThread.start()
nextDiscovery = datetime.datetime.now() + datetime.timedelta(seconds=1)
self._scheduler.add_date_job(self._requestLocalPrefix, nextDiscovery)
def _stop(self):
self._needStopDiscovery = True
self._eventLoop.stop()
self._eventLoopThread.join()
def _pyndn_loop_ignoring_errors(self):
while not self._needStopDiscovery:
try:
self._eventLoop.run()
except:
if not self._needStopDiscovery:
self._face.disconnect()
time.sleep(self._periodicity)
self._face.connect()
def _requestLocalPrefix(self):
self._timeouts = 0
self._face.expressInterestForLatest(Name("/local/ndn/prefix"),
self._onLocalPrefix,
self._onTimeout)
def _onLocalPrefix(self, baseName, interest, data, kind):
try:
name = Name(str(data.content).strip(' \t\n\r'))
except:
pass
if (name != self._currentPrefix):
for subscriber in self._subscribers.values():
subscriber(self._currentPrefix, name)
self._currentPrefix = name
if not self._needStopDiscovery:
nextDiscovery = datetime.datetime.now() + datetime.timedelta(
seconds=self._periodicity)
self._scheduler.add_date_job(self._requestLocalPrefix,
nextDiscovery)
return Closure.RESULT_OK
def _onTimeout(self, baseName, interest):
if self._timeouts < 3:
self._timeouts = self._timeouts + 1
return Closure.RESULT_REEXPRESS
else:
# do stuff
name = Name()
if (name != self._currentPrefix):
for subscriber in self._subscribers.values():
subscriber(self._currentPrefix, name)
self._currentPrefix = name
if not self._needStopDiscovery:
nextDiscovery = datetime.datetime.now() + datetime.timedelta(
seconds=self._periodicity)
self._scheduler.add_date_job(self._requestLocalPrefix,
nextDiscovery)
return Closure.RESULT_OK
def readInterface(cleanGenerated):
f = Face.Face()
if not cleanGenerated:
f.ReadFromFile("../../include/Scintilla.iface")
return f
def readIn(self):
with open(self.filename) as f:
content = f.readlines()
content = [x.strip("\n") for x in content]
for c in content:
if len(c) > 0 and c[0] == '#':
# It's a comment, ignore it
continue
line = c.split(' ')
if len(line) < 2:
# TODO: maybe throw an error?
continue
if line[0] == "v":
# Vertex
x = float(line[1])
y = float(line[2])
z = float(line[3])
self.vertices.append(Vertex(x, y, z))
# Figure out bounding boxes
if x < self.minx:
self.minx = x
if x > self.maxx:
self.maxx = x
if y < self.miny:
self.miny = y
if y > self.maxy:
self.maxy = y
if z < self.minz:
self.minz = z
if z > self.maxz:
self.maxz = z
elif line[0] == "vn":
# Vector normal
if line[1] == "nan" or line[2] == "nan" or line[3] == "nan":
self.vertexNormals.append(VertexNormal(0, 0, 0))
self.vertexNormals.append(
VertexNormal(float(line[1]), float(line[2]),
float(line[3])))
elif line[0] == "f":
# Face
x = line[1].split('/')
y = line[2].split('/')
z = line[3].split('/')
if len(x) < 3 or len(y) < 3 or len(z) < 3:
raise Exception("Invalid Face Format")
self.faces.append(
Face(
int(x[0]) - 1,
int(x[2]) - 1,
int(y[0]) - 1,
int(y[2]) - 1,
int(z[0]) - 1,
int(z[2]) - 1))
def RegenerateAll(root, _showMaxID):
f = Face.Face()
f.ReadFromFile(root / "include/LexicalStyles.iface")
FileGenerator.Regenerate(root / "include/SciLexer.h", "/* ",
printLexHFile(f))
def addnew():
if request.method == 'POST' and request.headers[
'Content-Type'] == 'application/octet-stream' and request.headers[
'Name'] != '':
try:
image = open('./images/image.jpg', 'wb')
image.write(request.data)
image.close()
image = open('./images/image.jpg', 'rb')
response = Face.who_is_it(image)
image.close()
if isinstance(response, dict):
if 0 in response and response[0]['Name'] == 'Unknown':
name = response[0]['Date'] + '-' + response[0][
'Time'] + '-' + request.headers['Name']
name = name.replace("/", "")
name = name.replace(":", "")
os.rename('./images/image.jpg',
'./images/' + name + '.jpg')
time.sleep(1)
image = open('./images/' + name + '.jpg', 'rb')
result = {
0: {
'Status':
Face.add_new(image, name=request.headers['Name'])
}
}
image.close()
print(result)
return jsonify(result)
elif 0 in response and response[0]['Name'] == request.headers[
'Name']:
name = response[0]['Date'] + '-' + response[0][
'Time'] + '-' + request.headers['Name']
name = name.replace("/", "")
name = name.replace(":", "")
os.rename('./images/image.jpg',
'./images/' + name + '.jpg')
time.sleep(1)
image = open('./images/' + name + '.jpg', 'rb')
result = {
0: {
'Status':
Face.add_new(image,
human_id=response[0]['Person ID'])
}
}
image.close()
print(result)
return jsonify(result)
elif 0 in response and response[0]['Name'] != request.headers[
'Name']:
name = response[0]['Date'] + '-' + response[0][
'Time'] + '-' + request.headers['Name']
name = name.replace("/", "")
name = name.replace(":", "")
os.rename('./images/image.jpg',
'./images/' + name + '.jpg')
time.sleep(1)
image = open('./images/' + name + '.jpg', 'rb')
result = {
0: {
'Status':
Face.add_new(image,
name=request.headers['Name'],
human_id=response[0]['Person ID'])
}
}
image.close()
print(result)
return jsonify(result)
return {0: 'Error'}
except FileNotFoundError as error:
print(error)
return {0: 'FileNotFoundError'}
except FileExistsError as error:
print(error)
return {0: 'FileExistsError'}
except PermissionError as error:
print(error)
return {0: 'PermissionError'}
else:
return redirect(url_for('static', filename='add.html'))
def main():
f = Face.Face()
f.ReadFromFile("Scintilla.iface")
Regenerate("../{{cookiecutter.plugin_slug}}/src/ScintillaEditor.h", "/* ",
printLexGatewayFile(f))
def RegenerateAll():
f = Face.Face()
f.ReadFromFile("Scintilla.iface")
#idsInOrder = idsFromDocumentation(srcRoot + "/scintilla/doc/ScintillaDoc.html")
Regenerate("../src/SciIFaceTable.cpp", "//",
printIFaceTableCppFile([f, []]))
