def train_face():
train_images = help_functions.load_all_images(
config.chokepoint_cropped_train, file_type='.pgm', preprocess=help_functions.prepare_face_random_resize)
# Hyper-parameters
people_count = 8
iterations = 25000
checkpoint = 20
save_checkpoint = 10000
backend.clear_session()
model = get_face_model((config.face_image_resize[1], config.face_image_resize[0], 1))
f = open(os.path.join('model_history', 'face_perf.txt'), 'a')
# print(model.summary())
for i in range(1, iterations+1):
inputs, targets = get_image_pairs(train_images, people_count)
(loss, acc) = model.train_on_batch(inputs, targets)
if i % checkpoint == 0:
logging.info('Iteration: {}'.format(i))
logging.info('Loss: {}'.format(loss))
logging.info('Accuracy: {}'.format(acc))
f.write(str(i) + ' ' + str(loss) + ' ' + str(acc) + '\n')
if i % save_checkpoint == 0:
model.save_weights(os.path.join('model_history', 'base_face_weights_it{}.h5'.format(i)))
f.flush()
model.save_weights(os.path.join('model_history', 'base_face_weights.h5'))
f.close()
def test_face_oneshot(model_file, iterations=10, versus=4):
test_images = help_functions.load_all_images(
config.chokepoint_cropped_test,
file_type='.pgm',
preprocess=help_functions.prepare_face)
model = get_face_model(
(config.face_image_resize[1], config.face_image_resize[0], 1))
model.load_weights(filepath=model_file)
matched = 0
for i in range(iterations):
inputs, targets = train_help_functions.get_oneshot_pair(
test_images, versus)
result = model.predict_on_batch(inputs)
matched += np.argmax(result) == np.argmax(targets)
print('Oneshot face:', float(matched) / float(iterations), 'vs', versus)
def improve_faces():
# same person in different folders might have different ID, causing false negatives if we connected them
train_images = []
# load images from each folder
for group_name in config.improve_camera_groups:
images = help_functions.load_all_images(
os.path.join(config.improve_folder, group_name, 'faces'),
file_type='.jpg',
preprocess=help_functions.prepare_face)
train_images.append(images)
# hyper-parameters
people_count = 8
iterations = 8000
checkpoint = 2
save_checkpoint = 5000
model = siamese_network.get_face_model(
(config.face_image_resize[1], config.face_image_resize[0], 1))
# are we improving base model of already improved model?
# load weight for model we are improving
if config.learning_start:
model.load_weights(filepath=config.base_face_model)
elif config.learning_improving:
model.load_weights(filepath=config.improved_face_model)
f = open(os.path.join('model_history', 'face_improve_perf.txt'), 'a')
logging.info('IMPROVING: Starting to improve model for faces')
for i in range(1, iterations + 1):
inputs, targets = get_image_pairs(
train_images[np.random.randint(0, len(train_images))],
people_count)
(loss, acc) = model.train_on_batch(inputs, targets)
if i % checkpoint == 0:
logging.info('Iteration: {}'.format(i))
logging.info('Loss: {}'.format(loss))
logging.info('Accuracy: {}'.format(acc))
f.write(str(i) + ' ' + str(loss) + ' ' + str(acc) + '\n')
if i % save_checkpoint == 0:
model.save_weights(os.path.join('model_history', str(i) + 'FI.h5'))
f.flush()
model.save_weights(config.improved_face_model)
f.close()
def test_face(model_file,
image_folder=config.chokepoint_cropped_test,
file_type='.pgm'):
test_images = help_functions.load_all_images(
image_folder,
file_type=file_type,
preprocess=help_functions.prepare_face)
model = get_face_model(
(config.face_image_resize[1], config.face_image_resize[0], 1))
model.load_weights(filepath=model_file)
print('face')
rates = np.array([0, 0, 0, 0])
for i in range(100):
inputs, targets = train_help_functions.get_image_pairs(test_images, 10)
if targets.shape[0] == 0:
continue
predicted = model.predict_on_batch(inputs)
rates += calc_rates(predicted, targets)
print_rates(rates)
import numpy as np
import logging
import cv2
import siamese_network
import config
body_model = siamese_network.get_body_model()
face_model = siamese_network.get_face_model()
if config.learning_start:
body_model.load_weights(filepath=config.base_body_model)
face_model.load_weights(filepath=config.base_face_model)
elif config.learning_improving or config.production:
body_model.load_weights(filepath=config.improved_body_model)
face_model.load_weights(filepath=config.improved_face_model)
def confirm_match(candidate_track, same_track):
while True:
face1 = candidate_track.get_face_images()
face2 = same_track.get_face_images()
body1 = candidate_track.get_body_images()
body2 = same_track.get_body_images()
showed = False
if body1.shape[0] > 0 and body2.shape[0] > 0:
body1 = body1[np.random.randint(0, body1.shape[0])]
body2 = body2[np.random.randint(0, body2.shape[0])]
cv2.imshow('candidate', body1.astype(np.uint8))
cv2.imshow('matched to', body2.astype(np.uint8))