def load_and_align_data(config, imgs):
print('Creating networks and loading parameters')
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(
per_process_gpu_memory_fraction=config.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options,
log_device_placement=False))
with sess.as_default():
detector = MTCNN(config, sess)
# print (config.compared_imgs)
nrof_samples = len(imgs)
img_list = [None] * nrof_samples
for i in xrange(nrof_samples):
img = misc.imread(os.path.expanduser(imgs[i]))
img_size = np.asarray(img.shape)[0:2]
bounding_boxes, _ = detector.detect_face(img)
det = np.squeeze(bounding_boxes[0, 0:4])
bb = np.zeros(4, dtype=np.int32)
bb[0] = np.maximum(det[0] - config.mtcnn.margin / 2, 0)
bb[1] = np.maximum(det[1] - config.mtcnn.margin / 2, 0)
bb[2] = np.minimum(det[2] + config.mtcnn.margin / 2, img_size[1])
bb[3] = np.minimum(det[3] + config.mtcnn.margin / 2, img_size[0])
cropped = img[bb[1]:bb[3], bb[0]:bb[2], :]
aligned = misc.imresize(
cropped, (config.mtcnn.image_size, config.mtcnn.image_size),
interp='bilinear')
prewhitened = prewhiten(aligned)
img_list[i] = prewhitened
images = np.stack(img_list)
return images
def main(config):
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(
per_process_gpu_memory_fraction=config.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options,
log_device_placement=False))
with sess.as_default():
detector = MTCNN(config, sess)
# Load the model
load_model(config.lfw.valid_model_path)
# Get input and output tensors
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")
# Run forward pass to calculate embeddings
with open(config.parse_path) as f:
names = f.readlines()
for name in names:
keyword, name, saved_dir = get_keyword(name, config.output_dir)
fanye_url = url_init_first + urllib.quote(keyword, safe='/')
feats = []
page = 0
while len(os.listdir(saved_dir)) < 20 and fanye_url != '':
onepage_urls, fanye_url = get_onepage_urls(fanye_url)
for index, url in enumerate(onepage_urls):
img_path = download(url,
page * len(onepage_urls) + index,
saved_dir)
try:
img = misc.imread(img_path)
nrof_faces, face = detect(img, detector, config)
face = np.expand_dims(face, 0)
if nrof_faces:
feed_dict = {
images_placeholder: face,
phase_train_placeholder: False
}
feats.append(
sess.run(embeddings, feed_dict=feed_dict))
if index != 0:
dist = np.sqrt(
np.sum(
np.square(
np.subtract(
feats[0], feats[-1]))))
print('the %d-th %s image dist: %f' %
(index, name, dist))
if dist > config.max_dist:
os.remove(img_path)
except Exception as e:
print(e)
if img_path:
os.remove(img_path)
continue
page += 1
def main(config):
print('Creating networks and loading parameters')
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(
per_process_gpu_memory_fraction=config.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options,
log_device_placement=False))
with sess.as_default():
detector = MTCNN(config, sess)
frame = cv2.imread(config.image)
# frame = cv2.resize(frame, (0,0), fx=0.5, fy=0.5) # If necessary
if frame.ndim == 2:
frame = to_rgb(frame)
frame = frame[:, :, 0:3]
bounding_boxes, _ = detector.detect_face(frame)
nrof_faces = bounding_boxes.shape[0]
print('Detected_FaceNum: %d' % nrof_faces)
if nrof_faces > 0:
det = bounding_boxes[:, 0:4]
bb = np.zeros((nrof_faces, 4), dtype=np.int32)
for i in range(nrof_faces):
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 inner of range!')
continue
cv2.rectangle(frame, (bb[i][0], bb[i][1]),
(bb[i][2], bb[i][3]), (0, 255, 0), 2)
else:
print('Unable to align')
cv2.imshow('Image', frame)
if cv2.waitKey(0):
cv2.destroyAllWindows()
def main(config):
print('Creating networks and loading parameters')
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(
per_process_gpu_memory_fraction=config.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options,
log_device_placement=False))
with sess.as_default():
detector = MTCNN(config, sess)
video_capture = cv2.VideoCapture(0)
prevTime = 0
c = 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() # calc fps
timeF = config.mtcnn.frame_interval
if (c % timeF == 0):
if frame.ndim == 2:
frame = to_rgb(frame)
frame = frame[:, :, 0:3]
bounding_boxes, _ = detector.detect_face(frame)
nrof_faces = bounding_boxes.shape[0]
print('Detected_FaceNum: %d' % nrof_faces)
if nrof_faces > 0:
det = bounding_boxes[:, 0:4]
bb = np.zeros((nrof_faces, 4), dtype=np.int32)
for i in range(nrof_faces):
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 inner of range!')
continue
cv2.rectangle(frame, (bb[i][0], bb[i][1]),
(bb[i][2], bb[i][3]), (0, 255, 0), 2)
else:
print('Unable to align')
sec = curTime - prevTime
prevTime = curTime
fps = 1 / (sec)
string = 'FPS: %2.3f' % fps
text_fps_x = len(frame[0]) - 150
text_fps_y = 20
cv2.putText(frame,
string, (text_fps_x, text_fps_y),
cv2.FONT_HERSHEY_COMPLEX_SMALL,
1, (0, 255, 0),
thickness=1,
lineType=2)
# c += 1
cv2.imshow('Video', frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
video_capture.release()
cv2.destroyAllWindows()
def main(config):
print('Creating networks and loading parameters')
Data = DataGenerator(config)
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=config.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False))
with sess.as_default():
detector = MTCNN(config,sess)
random_key = np.random.randint(0, high=99999)
bounding_boxes_filename = os.path.join(config.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
for cls in Data.dataset:
output_class_dir = os.path.join(config.output_dir, cls.name)
create_dirs([output_class_dir])
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)
img = cv2.resize(img, (0,0), fx=0.5, fy=0.5)
# print('read data dimension: ', img.ndim)
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 = to_rgb(img)
print('to_rgb data dimension: ', img.ndim)
img = img[:, :, 0:3]
# print('after data dimension: ', img.ndim)
bounding_boxes, _ = detector.detect_face(img)
nrof_faces = bounding_boxes.shape[0]
# print('detected_face: %d' % nrof_faces)
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_temp = np.zeros(4, dtype=np.int32)
bb_temp[0] = det[0]
bb_temp[1] = det[1]
bb_temp[2] = det[2]
bb_temp[3] = det[3]
cropped_temp = img[bb_temp[1]:bb_temp[3], bb_temp[0]:bb_temp[2], :]
try:
scaled_temp = misc.imresize(cropped_temp, (config.mtcnn.image_size, config.mtcnn.image_size), interp='bilinear')
except (IOError, ValueError, IndexError) as e:
continue
nrof_successfully_aligned += 1
misc.imsave(output_filename, scaled_temp)
text_file.write('%s %d %d %d %d\n' % (output_filename, bb_temp[0], bb_temp[1], bb_temp[2], bb_temp[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 main(config):
print('Creating networks and loading parameters')
Data = DataGenerator(config, False)
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(
per_process_gpu_memory_fraction=config.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options,
log_device_placement=False))
with sess.as_default():
detector = MTCNN(config, sess)
nrof_images_total = 0
nrof_successfully_aligned = 0
for cls in Data.dataset:
output_class_dir = os.path.join(config.output_dir, cls.name)
create_dirs([output_class_dir])
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)
# print('read data dimension: ', img.ndim)
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)
continue
if img.ndim == 2:
img = to_rgb(img)
print('to_rgb data dimension: ', img.ndim)
img = img[:, :, 0:3]
# print('after data dimension: ', img.ndim)
bounding_boxes, _ = detector.detect_face(img)
nrof_faces = bounding_boxes.shape[0]
# print('detected_face: %d' % nrof_faces)
if nrof_faces > 0:
det = bounding_boxes[:, 0:4]
bb_temp = np.zeros((nrof_faces, 4), dtype=np.int32)
for i in range(nrof_faces):
bb_temp[i][0] = det[i][0]
bb_temp[i][1] = det[i][1]
bb_temp[i][2] = det[i][2]
bb_temp[i][3] = det[i][3]
cropped_temp = img[bb_temp[i][1]:bb_temp[i][3],
bb_temp[i][0]:bb_temp[i][2], :]
try:
scaled_temp = misc.imresize(
cropped_temp, (config.mtcnn.image_size,
config.mtcnn.image_size),
interp='bilinear')
except (IOError, ValueError, IndexError) as e:
continue
nrof_successfully_aligned += 1
if nrof_faces == 1:
misc.imsave(output_filename, scaled_temp)
else:
output_bodyname = output_filename.split('.')[0]
output_indexname = '_%d' % i
misc.imsave(
output_bodyname + output_indexname +
'.png', scaled_temp)
else:
print('Unable to align "%s"' % image_path)
print('Total number of images: %d' % nrof_images_total)
print('Number of successfully aligned images: %d' %
nrof_successfully_aligned)
def main(config):
print('Creating networks and loading parameters')
graph_detect = tf.Graph()
with graph_detect.as_default():
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=config.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False))
with sess.as_default():
detector = MTCNN(config,sess)
load_model(config.lfw.valid_model_path)
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 = config.classifier_path
classifier_filename_exp = os.path.expanduser(classifier_filename)
print('load classifier file-> %s' % classifier_filename_exp)
with open(classifier_filename_exp, 'rb') as infile:
(model, class_names) = pickle.load(infile)
HumanNames = os.listdir(config.input_dir)
video_capture = cv2.VideoCapture(0)
prevTime = 0
c = 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() # calc fps
timeF = config.mtcnn.frame_interval
if (c % timeF == 0):
if frame.ndim == 2:
frame = to_rgb(frame)
frame = frame[:, :, 0:3]
bounding_boxes, _ = detector.detect_face(frame)
nrof_faces = bounding_boxes.shape[0]
print('Detected_FaceNum: %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 inner of range!')
continue
cropped.append(frame[bb[i][1]:bb[i][3], bb[i][0]:bb[i][2], :])
cropped[i] = flip(cropped[i], False)
scaled.append(misc.imresize(cropped[i], (182, 182), interp='bilinear'))
scaled[i] = cv2.resize(scaled[i], (160,160),interpolation=cv2.INTER_CUBIC)
scaled[i] = prewhiten(scaled[i])
scaled_reshape.append(scaled[i].reshape(-1,160,160,3))
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]
# print "best_class_probabilities:", best_class_probabilities
cv2.rectangle(frame, (bb[i][0], bb[i][1]), (bb[i][2], bb[i][3]), (0, 255, 0), 2)
text_x = bb[i][0]
text_y = bb[i][3] + 20
print('result: ', best_class_indices[0])
for H_i in HumanNames:
if HumanNames[best_class_indices[0]] == H_i:
result_names = HumanNames[best_class_indices[0]]
cv2.putText(frame, result_names, (text_x, text_y), cv2.FONT_HERSHEY_COMPLEX_SMALL,
1, (0, 0, 255), thickness=1, lineType=2)
else:
print('Unable to align')
sec = curTime - prevTime
prevTime = curTime
fps = 1 / (sec)
string = 'FPS: %2.3f' % fps
text_fps_x = len(frame[0]) - 150
text_fps_y = 20
cv2.putText(frame, string, (text_fps_x, text_fps_y),cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 255, 0), thickness=1, lineType=2)
c += 1
cv2.imshow('Video', frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
video_capture.release()
cv2.destroyAllWindows()