def _create_generators(self):
tf_utils = TFRecordUtility()
if os.path.isfile('x_train_filenames.npy') and \
os.path.isfile('x_val_filenames.npy') and \
os.path.isfile('y_train_filenames.npy') and \
os.path.isfile('y_val_filenames.npy'):
x_train_filenames = load('x_train_filenames.npy')
x_val_filenames = load('x_val_filenames.npy')
y_train = load('y_train_filenames.npy')
y_val = load('y_val_filenames.npy')
else:
filenames, labels = tf_utils.create_image_and_labels_name()
filenames_shuffled, y_labels_shuffled = shuffle(filenames, labels)
x_train_filenames, x_val_filenames, y_train, y_val = train_test_split(
filenames_shuffled,
y_labels_shuffled,
test_size=0.1,
random_state=1)
save('x_train_filenames.npy', x_train_filenames)
save('x_val_filenames.npy', x_val_filenames)
save('y_train_filenames.npy', y_train)
save('y_val_filenames.npy', y_val)
return x_train_filenames, x_val_filenames, y_train, y_val
def _create_generators(self):
"""
check if we have the img & lbls name. and create in case we need it.
:return:
"""
fn_prefix = './file_names/' + self.dataset_name + '_'
x_trains_path = fn_prefix + 'x_train_fns.npy'
x_validations_path = fn_prefix + 'x_val_fns.npy'
y_trains_path = fn_prefix + 'y_train_fns.npy'
y_validations_path = fn_prefix + 'y_val_fns.npy'
tf_utils = TFRecordUtility(number_of_landmark=self.num_landmark)
if os.path.isfile(x_trains_path) and os.path.isfile(x_validations_path) \
and os.path.isfile(y_trains_path) and os.path.isfile(y_validations_path):
x_train_filenames = load(x_trains_path)
x_val_filenames = load(x_validations_path)
y_train = load(y_trains_path)
y_val = load(y_validations_path)
else:
filenames, labels = tf_utils.create_image_and_labels_name(
dataset_name=self.dataset_name)
filenames_shuffled, y_labels_shuffled = shuffle(filenames, labels)
x_train_filenames, x_val_filenames, y_train, y_val = train_test_split(
filenames_shuffled,
y_labels_shuffled,
test_size=0.05,
random_state=1)
save(x_trains_path, x_train_filenames)
save(x_validations_path, x_val_filenames)
save(y_trains_path, y_train)
save(y_validations_path, y_val)
return x_train_filenames, x_val_filenames, y_train, y_val
def create_pca(self, dataset_name, pca_postfix):
tf_record_util = TFRecordUtility()
lbl_arr = []
pose_arr = []
if dataset_name == DatasetName.ibug:
lbl_arr, img_arr, pose_arr = tf_record_util.retrieve_tf_record(
IbugConf.tf_train_path,
IbugConf.sum_of_train_samples,
only_label=True,
only_pose=True)
lbl_arr = np.array(lbl_arr)
print('PCA-retrieved')
'''need to be normalized based on the hyper face paper?'''
# reduced_lbl_arr, eigenvalues, eigenvectors = self.__svd_func(lbl_arr, pca_postfix)
reduced_lbl_arr, eigenvalues, eigenvectors = self.__func_PCA(
lbl_arr, pca_postfix)
mean_lbl_arr = np.mean(lbl_arr, axis=0)
eigenvectors = eigenvectors.T
self.__save_obj(
eigenvalues,
dataset_name + self.__eigenvalues_prefix + str(pca_postfix))
self.__save_obj(
eigenvectors,
dataset_name + self.__eigenvectors_prefix + str(pca_postfix))
self.__save_obj(
mean_lbl_arr,
dataset_name + self.__meanvector_prefix + str(pca_postfix))
'''calculate pose min max'''
p_1_arr = []
p_2_arr = []
p_3_arr = []
for p_item in pose_arr:
p_1_arr.append(p_item[0])
p_2_arr.append(p_item[1])
p_3_arr.append(p_item[2])
p_1_min = min(p_1_arr)
p_1_max = max(p_1_arr)
p_2_min = min(p_2_arr)
p_2_max = max(p_2_arr)
p_3_min = min(p_3_arr)
p_3_max = max(p_3_arr)
self.__save_obj(p_1_min, 'p_1_min')
self.__save_obj(p_1_max, 'p_1_max')
self.__save_obj(p_2_min, 'p_2_min')
self.__save_obj(p_2_max, 'p_2_max')
self.__save_obj(p_3_min, 'p_3_min')
self.__save_obj(p_3_max, 'p_3_max')
print('PCA-->done')
def _create_generators(self):
fn_prefix = './file_names/' + self.dataset_name + '_'
# x_trains_path = fn_prefix + 'x_train_fns.npy'
# x_validations_path = fn_prefix + 'x_val_fns.npy'
tf_utils = TFRecordUtility(number_of_landmark=self.num_landmark)
filenames, labels = tf_utils.create_image_and_labels_name(
img_path=self.img_path, annotation_path=self.annotation_path)
filenames_shuffled, y_labels_shuffled = shuffle(filenames, labels)
x_train_filenames, x_val_filenames, y_train, y_val = train_test_split(
filenames_shuffled,
y_labels_shuffled,
test_size=LearningConfig.batch_size,
random_state=1)
# save(x_trains_path, filenames_shuffled)
# save(x_validations_path, y_labels_shuffled)
# save(x_trains_path, x_train_filenames)
# save(x_validations_path, x_val_filenames)
# save(y_trains_path, y_train)
# save(y_validations_path, y_val)
# return filenames_shuffled, y_labels_shuffled
return x_train_filenames, x_val_filenames, y_train, y_val
def _eval_model(self, model, img_val_filenames, pn_val_filenames):
tf_util = TFRecordUtility(number_of_landmark=self.num_landmark)
nme_sum = 0
fail_counter_sum = 0
batch_size = 20 # LearningConfig.batch_size
step_per_epoch = int(len(img_val_filenames) // (batch_size))
for batch_index in tqdm(range(step_per_epoch)):
images, anno_gts = self._get_batch_sample(
batch_index=batch_index,
x_train_filenames=img_val_filenames,
y_train_filenames=pn_val_filenames,
is_eval=True,
batch_size=batch_size)
'''predict:'''
anno_Pres = model.predict_on_batch(
images) # hm_pr: 4, bs, 64, 64, 68
'''calculate NME for batch'''
bath_nme, bath_fr = tf_util.calc_NME_over_batch(
anno_GTs=anno_gts,
anno_Pres=anno_Pres,
ds_name=self.dataset_name)
nme_sum += bath_nme
fail_counter_sum += bath_fr
'''calculate total'''
fr = 100 * fail_counter_sum / len(img_val_filenames)
nme = 100 * nme_sum / len(img_val_filenames)
print('nme:' + str(nme))
print('fr:' + str(fr))
return nme, fr
def test_pca_validity(self, pca_postfix):
cnn_model = CNNModel()
pca_utility = PCAUtility()
tf_record_utility = TFRecordUtility()
image_utility = ImageUtility()
eigenvalues, eigenvectors, meanvector = pca_utility.load_pca_obj(
dataset_name=DatasetName.ibug, pca_postfix=pca_postfix)
lbl_arr, img_arr, pose_arr = tf_record_utility.retrieve_tf_record(
tfrecord_filename=IbugConf.tf_train_path,
number_of_records=30,
only_label=False)
for i in range(20):
b_vector_p = self.calculate_b_vector(lbl_arr[i], True, eigenvalues,
eigenvectors, meanvector)
lbl_new = meanvector + np.dot(eigenvectors, b_vector_p)
labels_true_transformed, landmark_arr_x_t, landmark_arr_y_t = image_utility. \
create_landmarks_from_normalized(lbl_arr[i], 224, 224, 112, 112)
labels_true_transformed_pca, landmark_arr_x_pca, landmark_arr_y_pca = image_utility. \
create_landmarks_from_normalized(lbl_new, 224, 224, 112, 112)
image_utility.print_image_arr(i, img_arr[i], landmark_arr_x_t,
landmark_arr_y_t)
image_utility.print_image_arr(i * 1000, img_arr[i],
landmark_arr_x_pca,
landmark_arr_y_pca)
def _create_generators(self):
tf_utils = TFRecordUtility()
if self.point_wise:
if True or os.path.isfile('npy/' +'x_train_filenames_pw.npy') and \
os.path.isfile('npy/' +'x_val_filenames_pw.npy') and \
os.path.isfile('npy/' +'y_train_filenames_pw.npy') and \
os.path.isfile('npy/' +'y_val_filenames_pw.npy'):
x_train_filenames = load('npy/x_train_filenames_pw.npy')
x_val_filenames = load('npy/x_val_filenames_pw.npy')
y_train = load('npy/y_train_filenames_pw.npy')
y_val = load('npy/y_val_filenames_pw.npy')
else:
for i in range(68):
filenames, labels = tf_utils.create_fused_images_and_labels_name(
)
filenames_shuffled, y_labels_shuffled = shuffle(
filenames, labels)
x_train_filenames, x_val_filenames, y_train, y_val = train_test_split(
filenames_shuffled,
y_labels_shuffled,
test_size=0.1,
random_state=1)
save('npy/' + 'x_train_filenames_pw_.npy',
x_train_filenames)
save('npy/' + 'x_val_filenames_pw_.npy', x_val_filenames)
save('npy/' + 'y_train_filenames_pw_.npy', y_train)
save('npy/' + 'y_val_filenames_pw_.npy', y_val)
else:
if os.path.isfile('x_train_filenames.npy') and \
os.path.isfile('x_val_filenames.npy') and \
os.path.isfile('y_train_filenames.npy') and \
os.path.isfile('y_val_filenames.npy'):
x_train_filenames = load('x_train_filenames.npy')
x_val_filenames = load('x_val_filenames.npy')
y_train = load('y_train_filenames.npy')
y_val = load('y_val_filenames.npy')
else:
filenames, labels = tf_utils.create_image_and_labels_name(
self.point_wise)
filenames_shuffled, y_labels_shuffled = shuffle(
filenames, labels)
x_train_filenames, x_val_filenames, y_train, y_val = train_test_split(
filenames_shuffled,
y_labels_shuffled,
test_size=0.1,
random_state=1)
save('x_train_filenames.npy', x_train_filenames)
save('x_val_filenames.npy', x_val_filenames)
save('y_train_filenames.npy', y_train)
save('y_val_filenames.npy', y_val)
return x_train_filenames, x_val_filenames, y_train, y_val
def _test_on_W300(self, model):
tf_record_utility = TFRecordUtility(self.num_landmark)
lbl_arr_challenging, img_arr_challenging = tf_record_utility.retrieve_tf_record_test_set(
tfrecord_filename=IbugConf.tf_test_path_challenging,
number_of_records=IbugConf.orig_number_of_test_challenging,
only_label=False)
nme_ch, fr_ch, auc_ch, mae_yaw_ch, mae_pitch_ch, mae_roll_ch = self._calculate_errors(model, W300Conf.number_of_all_sample_challenging,
img_arr_challenging, lbl_arr_challenging)
lbl_arr_challenging = np.array(lbl_arr_challenging)
img_arr_challenging = np.array(img_arr_challenging)
print('nme_ch: ', str(nme_ch), 'fr_ch: ', str(fr_ch), 'auc_ch: ', str(auc_ch))
print('mae_yaw: ', str(mae_yaw_ch), 'mae_pitch: ', str(mae_pitch_ch), 'mae_roll: ', str(mae_roll_ch))
lbl_arr_common, img_arr_common = tf_record_utility.retrieve_tf_record_test_set(
tfrecord_filename=IbugConf.tf_test_path_common,
number_of_records=IbugConf.orig_number_of_test_common,
only_label=False)
lbl_arr_full, img_arr_full = tf_record_utility.retrieve_tf_record_test_set(
tfrecord_filename=IbugConf.tf_test_path_full,
number_of_records=IbugConf.orig_number_of_test_full,
only_label=False)
lbl_arr_common = np.array(lbl_arr_common)
img_arr_common = np.array(img_arr_common)
lbl_arr_full = np.array(lbl_arr_full)
img_arr_full = np.array(img_arr_full)
nme_c, fr_c, auc_c, mae_yaw_c, mae_pitch_c, mae_roll_c = self._calculate_errors(model,
W300Conf.number_of_all_sample_common,
img_arr_common, lbl_arr_common)
print('nme_c: ', str(nme_c), 'fr_c: ', str(fr_c), 'auc_c: ', str(auc_c))
print('mae_yaw: ', str(mae_yaw_c), 'mae_pitch: ', str(mae_pitch_c), 'mae_roll: ', str(mae_roll_c))
nme_f, fr_f, auc_f, mae_yaw_f, mae_pitch_f, mae_roll_f = self._calculate_errors(model,
W300Conf.number_of_all_sample_full,
img_arr_full, lbl_arr_full)
print('nme_f: ', str(nme_f), 'fr_f: ', str(fr_f), 'auc_f: ', str(auc_f))
print('mae_yaw: ', str(mae_yaw_f), 'mae_pitch: ', str(mae_pitch_f), 'mae_roll: ', str(mae_roll_f))
result_str = "-------------------------_test_on_W300------------------------------------" + '\n\r' \
'nme_ch: ', str(nme_ch), 'fr_ch: ', str(fr_ch), 'auc_ch: ', str(auc_ch) + '\n\r' \
'mae_yaw: ', str(mae_yaw_ch), 'mae_pitch: ', str(mae_pitch_ch), 'mae_roll: ', str(mae_roll_ch) + '\n\r' \
'nme_c: ', str(nme_c), 'fr_c: ', str(fr_c), 'auc_c: ', str(auc_c) + '\n\r' \
'mae_yaw: ', str(mae_yaw_c), 'mae_pitch: ', str(mae_pitch_c), 'mae_roll: ', str(mae_roll_c) + '\n\r' \
'nme_f: ', str(nme_f), 'fr_f: ', str(fr_f), 'auc_f: ', str(auc_f) + '\n\r' \
'mae_yaw: ', str(mae_yaw_f), 'mae_pitch: ', str(mae_pitch_f), 'mae_roll: ', str(mae_roll_f)
return str(result_str)
def _test_on_COFW(self, model):
tf_record_utility = TFRecordUtility(self.output_len)
lbl_arr_total, img_arr_total = tf_record_utility.retrieve_tf_record_test_set(
tfrecord_filename=CofwConf.tf_test_path,
number_of_records=CofwConf.orig_number_of_test,
only_label=False)
lbl_arr_total = np.array(lbl_arr_total)
img_arr_total = np.array(img_arr_total)
nme, fr, auc, = self._calculate_errors(model,
CofwConf.orig_number_of_test,
img_arr_total, lbl_arr_total)
print('nme: ', str(nme), 'fr: ', str(fr), 'auc: ', str(auc))
print("-------------------------------------------------------------")
def _create_generators(self, img_path=None, annotation_path=None):
# x_trains_path = fn_prefix + 'x_train_fns.npy'
# x_validations_path = fn_prefix + 'x_val_fns.npy'
tf_utils = TFRecordUtility(number_of_landmark=self.num_landmark)
if img_path is None:
filenames, labels = tf_utils.create_image_and_labels_name(
img_path=self.img_path, annotation_path=self.annotation_path)
else:
filenames, labels = tf_utils.create_image_and_labels_name(
img_path=img_path, annotation_path=annotation_path)
filenames_shuffled, y_labels_shuffled = shuffle(filenames, labels)
# x_train_filenames, x_val_filenames, y_train, y_val = train_test_split(
# filenames_shuffled, y_labels_shuffled, test_size=LearningConfig.batch_size, random_state=1)
return filenames_shuffled, y_labels_shuffled
def _create_generators(self):
tf_utils = TFRecordUtility(self.output_len)
filenames, labels = tf_utils.create_image_and_labels_name()
filenames_shuffled, y_labels_shuffled = shuffle(filenames, labels)
x_train_filenames, x_val_filenames, y_train, y_val = train_test_split(
filenames_shuffled,
y_labels_shuffled,
test_size=0.05,
random_state=100,
shuffle=True)
save('x_train_filenames.npy', x_train_filenames)
save('x_val_filenames.npy', x_val_filenames)
save('y_train_filenames.npy', y_train)
save('y_val_filenames.npy', y_val)
return x_train_filenames, x_val_filenames, y_train, y_val
def convert_pts_to_hm(self, pts):
"""
we want to convert pts to hm{56 * 56 * self.num_landmark//2} and then calculate loss
:param pts: bs * self.num_landmark: pts are normal between -0.5, +0.5 --> need to upsample
:return:
"""
pts = pts.numpy()
# pts = tf.keras.backend.eval(pts)
hm_arr = []
tf_util = TFRecordUtility(self.num_landmark // 2)
for i in range(LearningConfig.batch_size):
hm_t = tf_util.generate_hm_Ten(height=InputDataSize.hm_size,
width=InputDataSize.hm_size,
landmarks=pts[i],
s=3.0,
upsample=True)
hm_arr.append(hm_t)
hm_pts = tf.convert_to_tensor(np.array(hm_arr))
return hm_pts
def train_fit(self):
tf_record_util = TFRecordUtility(self.output_len)
'''prepare callbacks'''
callbacks_list = self._prepare_callback()
''' define optimizers'''
optimizer = self._get_optimizer()
'''create train, validation, test data iterator'''
train_images, train_landmarks = tf_record_util.create_training_tensor_points(
tfrecord_filename=self.tf_train_path, batch_size=self.BATCH_SIZE)
validation_images, validation_landmarks = \
tf_record_util.create_training_tensor_points(tfrecord_filename=self.tf_eval_path,
batch_size=self.BATCH_SIZE)
'''creating model'''
cnn = CNNModel()
# model = tf.keras.models.load_model(self.weight)
model = cnn.get_model(train_images=train_images,
arch=self.arch,
num_output_layers=self.num_output_layers,
output_len=self.output_len,
input_tensor=train_images,
inp_shape=None)
if self.weight is not None:
model.load_weights(self.weight)
'''compiling model'''
model.compile(
loss=self._generate_loss(),
optimizer=optimizer,
metrics=['mse', 'mae'],
target_tensors=self._generate_target_tensors(train_landmarks),
loss_weights=self._generate_loss_weights())
'''train Model '''
print('< ========== Start Training ============= >')
history = model.fit(train_images,
train_landmarks,
epochs=self.EPOCHS,
steps_per_epoch=self.STEPS_PER_EPOCH,
validation_data=(validation_images,
validation_landmarks),
validation_steps=self.STEPS_PER_VALIDATION_EPOCH,
verbose=1,
callbacks=callbacks_list)
def _test_on_W300(self, model):
tf_record_utility = TFRecordUtility(self.output_len)
lbl_arr_challenging, img_arr_challenging = tf_record_utility.retrieve_tf_record_test_set(
tfrecord_filename=W300Conf.tf_challenging,
number_of_records=W300Conf.number_of_all_sample_challenging,
only_label=False)
lbl_arr_common, img_arr_common = tf_record_utility.retrieve_tf_record_test_set(
tfrecord_filename=W300Conf.tf_common,
number_of_records=W300Conf.number_of_all_sample_common,
only_label=False)
lbl_arr_full, img_arr_full = tf_record_utility.retrieve_tf_record_test_set(
tfrecord_filename=W300Conf.tf_full,
number_of_records=W300Conf.number_of_all_sample_full,
only_label=False)
lbl_arr_challenging = np.array(lbl_arr_challenging)
img_arr_challenging = np.array(img_arr_challenging)
lbl_arr_common = np.array(lbl_arr_common)
img_arr_common = np.array(img_arr_common)
lbl_arr_full = np.array(lbl_arr_full)
img_arr_full = np.array(img_arr_full)
nme_ch, fr_ch, auc_ch = self._calculate_errors(
model, W300Conf.number_of_all_sample_challenging,
img_arr_challenging, lbl_arr_challenging)
print('nme_ch: ', str(nme_ch), 'fr_ch: ', str(fr_ch), 'auc_ch: ',
str(auc_ch))
nme_c, fr_c, auc_c = self._calculate_errors(
model, W300Conf.number_of_all_sample_common, img_arr_common,
lbl_arr_common)
print('nme_c: ', str(nme_c), 'fr_c: ', str(fr_c), 'auc_c: ',
str(auc_c))
nme_f, fr_f, auc_f = self._calculate_errors(
model, W300Conf.number_of_all_sample_full, img_arr_full,
lbl_arr_full)
print('nme_f: ', str(nme_f), 'fr_f: ', str(fr_f), 'auc_f: ',
str(auc_f))
def _points_to_2d(self, _points):
"""
:param _points:
:return:
"""
tf_rec = TFRecordUtility(self.num_landmark)
image_utility = ImageUtility()
hm_arr = []
for i in range(LearningConfig.batch_size):
_x_y, _x, _y = image_utility.create_landmarks_from_normalized(
_points[i], InputDataSize.image_input_size,
InputDataSize.image_input_size, InputDataSize.img_center,
InputDataSize.img_center)
hm_multi_layer = tf_rec.generate_hm(InputDataSize.hm_size,
InputDataSize.hm_size,
np.array(_x_y),
self.hm_stride / 2, False)
hm = np.sum(hm_multi_layer, axis=2)
hm_arr.append(hm)
return np.array(hm_arr)
def convert_hm_to_pts(self, hm):
x_center = InputDataSize.image_input_size // 2
width = InputDataSize.image_input_size
hm_arr = []
tf_util = TFRecordUtility(self.num_landmark // 2)
for i in range(LearningConfig.batch_size):
hm_t = tf_util.from_heatmap_to_point_tensor(heatmaps=hm[i],
number_of_points=5)
hm_t = tf.reshape(tensor=hm_t, shape=self.num_landmark)
'''hm is in [0,224] --> should be in [-0.5,+0.5]'''
hm_t_norm = tf.math.scalar_mul(
scalar=1 / width,
x=tf.math.subtract(hm_t, np.repeat(x_center,
self.num_landmark)))
hm_arr.append(hm_t_norm)
'''reshape hm'''
hm_pts = tf.stack(
[hm_arr[i] for i in range(LearningConfig.batch_size)],
0) # bs * self.num_landmark
return hm_pts
def custom_loss_hm(self, ten_hm_t, ten_hm_p):
# print(ten_hm_t.get_shape()) # [None, 56, 56, 68]
# print(ten_hm_p.get_shape())
tf_utility = TFRecordUtility()
sqr = K.square(ten_hm_t - ten_hm_p) # [None, 56, 56, 68]
mean1 = K.mean(sqr, axis=1)
mean2 = K.mean(mean1, axis=1)
tensor_mean_square_error = K.mean(mean2, axis=1)
# print(tensor_mean_square_error.get_shape().as_list()) # [None, 68]
# vec_mse = K.eval(tensor_mean_square_error)
# print("mse.shape:")
# print(vec_mse.shape) # (50, 68)
# print(vec_mse)
# print("----------->>>")
'''calculate points from generated hm'''
p_points_batch = tf.stack([
tf_utility.from_heatmap_to_point_tensor(ten_hm_p[i], 5, 1)
for i in range(LearningConfig.batch_size)
])
t_points_batch = tf.stack([
tf_utility.from_heatmap_to_point_tensor(ten_hm_t[i], 5, 1)
for i in range(LearningConfig.batch_size)
])
'''p_points_batch is [batch, 2, 68]'''
sqr_2 = K.square(t_points_batch - p_points_batch) # [None, 2, 68]
mean_1 = K.mean(sqr_2, axis=1)
tensor_indices_mean_square_error = K.mean(mean_1, axis=1)
# tensor_total_loss = tf.reduce_mean([tensor_mean_square_error, tensor_indices_mean_square_error])
tensor_total_loss = tf.add(tensor_mean_square_error,
tensor_indices_mean_square_error)
return tensor_total_loss
def _test_on_COFW(self, model):
tf_record_utility = TFRecordUtility(self.output_len)
lbl_arr_total, img_arr_total = tf_record_utility.retrieve_tf_record_test_set(
tfrecord_filename=CofwConf.tf_test_path,
number_of_records=CofwConf.orig_number_of_test,
only_label=False)
lbl_arr_total = np.array(lbl_arr_total)
img_arr_total = np.array(img_arr_total)
nme, fr, auc, mae_yaw, mae_pitch, mae_roll = self._calculate_errors(model,
CofwConf.orig_number_of_test,
img_arr_total, lbl_arr_total)
result_str = "-------------------------_test_on_COFW------------------------------------" + '\n\r' \
+ 'nme: ', str(nme), 'fr: ', str(fr), 'auc: ', str(auc) + '\n\r' \
+ 'mae_yaw: ', str(mae_yaw), 'mae_pitch: ', str(mae_pitch), 'mae_roll: ', str(mae_roll)
print('nme: ', str(nme), 'fr: ', str(fr), 'auc: ', str(auc))
print('mae_yaw: ', str(mae_yaw), 'mae_pitch: ', str(mae_pitch), 'mae_roll: ', str(mae_roll))
print("-------------------------------------------------------------")
return result_str
def train_fit(self):
tf_record_util = TFRecordUtility()
'''prepare callbacks'''
callbacks_list = self._prepare_callback()
''' define optimizers'''
optimizer = self._get_optimizer()
'''create train, validation, test data iterator'''
train_images, _, _, _, _, _, _, train_heatmap, _ = \
tf_record_util.create_training_tensor(tfrecord_filename=IbugConf.tf_train_path_heatmap,
batch_size=self.BATCH_SIZE, reduced=True)
validation_images, _, _, _, _, _, _, validation_heatmap, _ = \
tf_record_util.create_training_tensor(tfrecord_filename=IbugConf.tf_evaluation_path_heatmap,
batch_size=self.BATCH_SIZE, reduced=True)
'''creating model'''
model = self._get_model(train_images)
if self.weight is not None:
model.load_weights(self.weight)
'''compiling model'''
model.compile(
loss=self._generate_loss(),
optimizer=optimizer,
metrics=['mse', 'mae'],
target_tensors=self._generate_target_tensors(train_heatmap),
loss_weights=self._generate_loss_weights())
'''train Model '''
print('< ========== Start Training ============= >')
history = model.fit(
train_images,
train_heatmap,
epochs=self.EPOCHS,
steps_per_epoch=self.STEPS_PER_EPOCH,
validation_data=(validation_images, validation_heatmap),
validation_steps=self.STEPS_PER_VALIDATION_EPOCH,
verbose=1,
callbacks=callbacks_list,
)
def calculate_adoptive_weight(self, epoch, batch_index, y_train_filenames):
tf_utils = TFRecordUtility(self.num_landmark)
batch_y = y_train_filenames[batch_index *
LearningConfig.batch_size:(batch_index +
1) *
LearningConfig.batch_size]
if 0 <= epoch <= 10:
asm_acc = 80
elif 10 < epoch <= 20:
asm_acc = 85
elif 20 < epoch <= 50:
asm_acc = 90
elif 50 < epoch <= 100:
asm_acc = 95
else:
asm_acc = 97
asm_acc = 97
'''for each point in training set, calc delta_i = ASM(gt_i)-pr_i: '''
if self.dataset_name == DatasetName.cofw: # this ds is not normalized
if self.arch == 'efNb0':
pn_batch = np.array([
self._load_and_normalize(self.annotation_path + file_name)
for file_name in batch_y
])
pn_batch_asm = np.array([
tf_utils.get_asm(
input=self._load_and_normalize(self.annotation_path +
file_name),
dataset_name=self.dataset_name,
accuracy=asm_acc) for file_name in batch_y
])
else:
pn_batch = np.array([
load(self.annotation_path + file_name)
for file_name in batch_y
])
pn_batch_asm = np.array([
tf_utils.get_asm(input=load(self.annotation_path +
file_name),
dataset_name=self.dataset_name,
accuracy=asm_acc) for file_name in batch_y
])
else:
pn_batch = np.array([
self._load_and_normalize(self.annotation_path + file_name)
for file_name in batch_y
])
pn_batch_asm = np.array([
tf_utils.get_asm(
input=self._load_and_normalize(self.annotation_path +
file_name),
dataset_name=self.dataset_name,
accuracy=asm_acc) for file_name in batch_y
])
'''phi = mean(delta_i s)'''
'''1d'''
delta = np.array([
abs(pn_batch[i] - pn_batch_asm[i]) for i in range(len(pn_batch))
]) # 1-d
'''2d'''
# pn_batch = np.reshape(pn_batch, [pn_batch.shape[0], pn_batch.shape[1] // 2, 2]) # bs, 68, 2
# pn_batch_asm = np.reshape(pn_batch_asm, [pn_batch_asm.shape[0], pn_batch_asm.shape[1] // 2, 2]) # bs, 68, 2
# delta = np.sqrt(np.sum(np.square(pn_batch - pn_batch_asm), axis=2))
omega = np.zeros_like(delta)
for i in range(len(delta)):
omega[i] = np.array([
1 / (0.2 + math.exp(-50 * delta[i][j]))
for j in range(len(delta[i]))
])
return omega
def _test_on_WFLW(self, model):
tf_record_utility = TFRecordUtility(self.num_landmark)
result_str = ''
# lbl_arr_total, img_arr_total = tf_record_utility.retrieve_tf_record_test_set(
# tfrecord_filename=WflwConf.tf_test_path,
# number_of_records=WflwConf.orig_number_of_test,
# only_label=False)
# nme, fr, auc, mae_yaw, mae_pitch, mae_roll = self._calculate_errors(detect, model, WflwConf.orig_number_of_test,
# img_arr_total, lbl_arr_total)
# result_str += "\n\r\n\r-------------------------_test_on_WFLW:total------------------------------------" + '\n\r' \
# + 'nme: ', str(nme), 'fr: ', str(fr), 'auc: ', str(auc) + '\n\r' \
# + 'mae_yaw: ', str(mae_yaw), 'mae_pitch: ', str(mae_pitch), 'mae_roll: ', str(mae_roll)
#
# print('nme: ', str(nme), 'fr: ', str(fr), 'auc: ', str(auc))
# print('mae_yaw: ', str(mae_yaw), 'mae_pitch: ', str(mae_pitch), 'mae_roll: ', str(mae_roll))
# print("-------------------------------------------------------------")
#
lbl_arr_largepose, img_arr_largepose = tf_record_utility.retrieve_tf_record_test_set(
tfrecord_filename=WflwConf.tf_test_path_largepose,
number_of_records=WflwConf.orig_of_all_test_largepose,
only_label=False)
nme, fr, auc, mae_yaw, mae_pitch, mae_roll = self._calculate_errors(model, WflwConf.orig_of_all_test_largepose,
img_arr_largepose, lbl_arr_largepose)
result_str += '\n\r\n\r-------------------------_test_on_WFLW: largepose------------------------------------nme: '\
+ str(nme)+'fr: ' + str(fr) + 'auc: '+ str(auc) + '\n\r' + 'mae_yaw: '+ str(mae_yaw)+ 'mae_pitch: '\
+ str(mae_pitch)+ 'mae_roll: '+ str(mae_roll)
print('nme: '+ str(nme)+ 'fr: ' + str(fr)+ 'auc: '+ str(auc))
print('mae_yaw: '+ str(mae_yaw)+ 'mae_pitch: '+ str(mae_pitch)+ 'mae_roll: '+ str(mae_roll))
print("-------------------------------------------------------------")
lbl_arr_occlusion, img_arr_occlusion = tf_record_utility.retrieve_tf_record_test_set(
tfrecord_filename=WflwConf.tf_test_path_occlusion,
number_of_records=WflwConf.orig_of_all_test_occlusion,
only_label=False)
nme, fr, auc, mae_yaw, mae_pitch, mae_roll = self._calculate_errors(model, WflwConf.orig_of_all_test_occlusion,
img_arr_occlusion, lbl_arr_occlusion)
result_str += '\n\r\n\r-------------------------_test_on_WFLW _occlusion------------------------------------'+ '\n\r' \
+ 'nme: '+ str(nme)+ 'fr: '+ str(fr)+ 'auc: '+ str(auc) + '\n\r' \
+ 'mae_yaw: '+ str(mae_yaw)+ 'mae_pitch: '+ str(mae_pitch)+ 'mae_roll: '+ str(mae_roll)
print('nme: '+ str(nme)+ 'fr: '+ str(fr)+ 'auc: '+ str(auc))
print('mae_yaw: '+ str(mae_yaw)+ 'mae_pitch: '+ str(mae_pitch)+ 'mae_roll: '+ str(mae_roll))
print("-------------------------------------------------------------")
lbl_arr_makeup, img_arr_makeup = tf_record_utility.retrieve_tf_record_test_set(
tfrecord_filename=WflwConf.tf_test_path_makeup,
number_of_records=WflwConf.orig_of_all_test_makeup,
only_label=False)
nme, fr, auc, mae_yaw, mae_pitch, mae_roll = self._calculate_errors(model, WflwConf.orig_of_all_test_makeup,
img_arr_makeup, lbl_arr_makeup)
result_str += '\n\r\n\r-------------------------_test_on_WFLW_makeup------------------------------------' + '\n\r' \
+ 'nme: '+ str(nme)+ 'fr: '+ str(fr)+ 'auc: '+ str(auc) + '\n\r' \
+ 'mae_yaw: '+ str(mae_yaw)+ 'mae_pitch: '+ str(mae_pitch)+ 'mae_roll: '+ str(mae_roll)
print('nme: '+ str(nme)+ 'fr: '+ str(fr)+ 'auc: '+ str(auc))
print('mae_yaw: '+ str(mae_yaw)+ 'mae_pitch: '+ str(mae_pitch)+ 'mae_roll: '+ str(mae_roll))
print("-------------------------------------------------------------")
lbl_arr_expression, img_arr_expression = tf_record_utility.retrieve_tf_record_test_set(
tfrecord_filename=WflwConf.tf_test_path_expression,
number_of_records=WflwConf.orig_of_all_test_expression,
only_label=False)
nme, fr, auc, mae_yaw, mae_pitch, mae_roll = self._calculate_errors(model, WflwConf.orig_of_all_test_expression,
img_arr_expression, lbl_arr_expression)
result_str += '\n\r\n\r-------------------------_test_on_WFLW_expression------------------------------------' + '\n\r' \
+ 'nme: '+ str(nme)+ 'fr: '+ str(fr)+ 'auc: '+ str(auc) + '\n\r' \
+ 'mae_yaw: '+ str(mae_yaw)+ 'mae_pitch: '+ str(mae_pitch)+ 'mae_roll: '+ str(mae_roll)
print('nme: '+ str(nme)+ 'fr: '+ str(fr)+ 'auc: '+ str(auc))
print('mae_yaw: '+ str(mae_yaw)+ 'mae_pitch: '+ str(mae_pitch)+ 'mae_roll: '+ str(mae_roll))
print("-------------------------------------------------------------")
lbl_arr_illumination, img_arr_illumination = tf_record_utility.retrieve_tf_record_test_set(
tfrecord_filename=WflwConf.tf_test_path_illumination,
number_of_records=WflwConf.orig_of_all_test_illumination,
only_label=False)
nme, fr, auc, mae_yaw, mae_pitch, mae_roll = self._calculate_errors(model, WflwConf.orig_of_all_test_illumination,
img_arr_illumination, lbl_arr_illumination)
result_str += '\n\r\n\r-------------------------_test_on_WFLW _illumination ------------------------------------' + '\n\r' \
+ 'nme: '+ str(nme)+ 'fr: '+ str(fr)+ 'auc: '+ str(auc) + '\n\r' \
+ 'mae_yaw: '+ str(mae_yaw)+ 'mae_pitch: '+ str(mae_pitch)+ 'mae_roll: '+ str(mae_roll)
print('nme: '+ str(nme)+ 'fr: '+ str(fr)+ 'auc: '+ str(auc))
print('mae_yaw: '+ str(mae_yaw)+ 'mae_pitch: '+ str(mae_pitch) + 'mae_roll: ' + str(mae_roll))
print("-------------------------------------------------------------")
lbl_arr_blur, img_arr_blur = tf_record_utility.retrieve_tf_record_test_set(
tfrecord_filename=WflwConf.tf_test_path_blur,
number_of_records=WflwConf.orig_of_all_test_blur,
only_label=False)
nme, fr, auc, mae_yaw, mae_pitch, mae_roll = self._calculate_errors(model, WflwConf.orig_of_all_test_blur,
img_arr_blur, lbl_arr_blur)
result_str += '\n\r\n\r-------------------------_test_on_WFLW_blur------------------------------------' + '\n\r' \
+ 'nme: '+ str(nme)+ 'fr: '+ str(fr)+ 'auc: '+ str(auc) + '\n\r' \
+ 'mae_yaw: '+ str(mae_yaw)+ 'mae_pitch: '+ str(mae_pitch)+ 'mae_roll: '+ str(mae_roll)
print('nme: '+ str(nme)+ 'fr: '+ str(fr)+ 'auc: '+ str(auc))
print('mae_yaw: '+ str(mae_yaw)+ 'mae_pitch: '+ str(mae_pitch)+ 'mae_roll: '+ str(mae_roll))
print("-------------------------------------------------------------")
return result_str
def custom_loss_hm(self, ten_hm_t, ten_hm_p):
# print(ten_hm_t.get_shape().as_list()) # [None, 56, 56, 68]
# print(ten_hm_p.get_shape())
tf_utility = TFRecordUtility()
sqr = K.square(ten_hm_t - ten_hm_p) # [None, 56, 56, 68]
mean1 = K.mean(sqr, axis=1)
mean2 = K.mean(mean1, axis=1)
tensor_mean_square_error = K.mean(mean2, axis=1)
# print(tensor_mean_square_error.get_shape().as_list()) # [None, 68]
# vec_mse = K.eval(tensor_mean_square_error)
# print("mse.shape:")
# print(vec_mse.shape) # (50, 68)
# print(vec_mse)
# print("----------->>>")
'''convert tensor to vector'''
vec_hm_p = K.eval(ten_hm_p)
vec_hm_t = K.eval(ten_hm_t)
loss_array = []
for i in range(LearningConfig.batch_size):
'''convert heatmap to points'''
x_h_p, y_h_p, xy_h_p = tf_utility.from_heatmap_to_point(vec_hm_p[i], 5, 1)
x_h_t, y_h_t, xy_h_t = tf_utility.from_heatmap_to_point(vec_hm_t[i], 5, 1)
'''normalise points to be in [0, 1]'''
x_h_p = x_h_p / 56
y_h_p = y_h_p / 56
xy_h_p = xy_h_p / 56
x_h_t = x_h_t / 56
y_h_t = y_h_t / 56
xy_h_t = xy_h_t / 56
'''test print images'''
# imgpr.print_image_arr(i + 1, np.zeros(shape=[56, 56]), x_h_t, y_h_t)
# imgpr.print_image_arr((i + 1)*1000, np.zeros(shape=[56, 56]), x_h_p, y_h_p)
# print('--xy_h_p:---')
# print(xy_h_p)
# print('--xy_h_t:---')
# print(xy_h_t)
face_p, mouth_p, nose_p, leye_p, reye_p = self._depart_facial_point(xy_h_p)
face_t, mouth_t, nose_t, leye_t, reye_t = self._depart_facial_point(xy_h_t)
'''generate facial distance matrix'''
face_p_mat, face_t_mat = self._generate_distance_matrix(face_p), self._generate_distance_matrix(face_t)
mouth_p_mat, mouth_t_mat = self._generate_distance_matrix(mouth_p), self._generate_distance_matrix(mouth_t)
nose_p_mat, nose_t_mat = self._generate_distance_matrix(nose_p), self._generate_distance_matrix(nose_t)
leye_p_mat, leye_t_mat = self._generate_distance_matrix(leye_p), self._generate_distance_matrix(leye_t)
reye_p_mat, reye_t_mat = self._generate_distance_matrix(reye_p), self._generate_distance_matrix(reye_t)
'''calculate loss from each pair matrices'''
face_loss = LearningConfig.reg_term_face * self._calculate_mse(face_p_mat, face_t_mat) / len(face_p)
mouth_loss = LearningConfig.reg_term_mouth * self._calculate_mse(mouth_p_mat, mouth_t_mat) / len(mouth_p)
nose_loss = LearningConfig.reg_term_nose * self._calculate_mse(nose_p_mat, nose_t_mat) / len(nose_p)
leye_loss = LearningConfig.reg_term_leye * self._calculate_mse(leye_p_mat, leye_t_mat) / len(leye_p)
reye_loss = LearningConfig.reg_term_reye * self._calculate_mse(reye_p_mat, reye_t_mat) / len(reye_p)
loss_array.append(face_loss + mouth_loss + nose_loss + leye_loss + reye_loss)
# print('mse[i]: ' + str(vec_mse[i]))
# print('face_loss[i]: ' + str(face_loss))
# print('mouth_loss[i]: ' + str(mouth_loss))
# print('nose_loss[i]: ' + str(nose_loss))
# print('leye_loss[i]: ' + str(leye_loss))
# print('reye_loss[i]: ' + str(reye_loss))
# print('============')
loss_array = np.array(loss_array)
tensor_distance_loss = K.variable(loss_array)
# tensor_total_loss = tf.reduce_mean([tensor_mean_square_error, loss_array])
tensor_total_loss = tf.add(tensor_mean_square_error, tensor_distance_loss)
return tensor_total_loss
def __customLoss_base(self, yTrue, yPred):
pca_utility = PCAUtility()
image_utility = ImageUtility()
tf_record_utility = TFRecordUtility()
eigenvalues, eigenvectors, meanvector = pca_utility.load_pca_obj(DatasetName.ibug)
# yTrue = tf.constant([[1.0, 2.0, 3.0], [5.0, 4.0, 7.0]])
# yPred = tf.constant([[9.0, 1.0, 2.0], [7.0, 3.0, 8.0]])
# session = K.get_session()
tensor_mean_square_error = K.mean(K.square(yPred - yTrue), axis=-1)
# tensor_mean_square_error = keras.losses.mean_squared_error(yPred, yTrue)
mse = K.eval(tensor_mean_square_error)
yPred_arr = K.eval(yPred)
yTrue_arr = K.eval(yTrue)
loss_array = []
for i in range(LearningConfig.batch_size):
asm_loss = 0
truth_vector = yTrue_arr[i]
predicted_vector = yPred_arr[i]
b_vector_p = self.calculate_b_vector(predicted_vector, True, eigenvalues, eigenvectors, meanvector)
y_pre_asm = meanvector + np.dot(eigenvectors, b_vector_p)
"""in order to test the results after PCA, you can use these lines of code"""
# landmark_arr_xy, landmark_arr_x, landmark_arr_y = image_utility.create_landmarks_from_normalized(truth_vector, 224, 224, 112, 112)
# image_utility.print_image_arr(i, np.ones([224, 224]), landmark_arr_x, landmark_arr_y)
#
# landmark_arr_xy_new, landmark_arr_x_new, landmark_arr_y_new= image_utility.create_landmarks_from_normalized(y_pre_asm, 224, 224, 112, 112)
# image_utility.print_image_arr(i*100, np.ones([224, 224]), landmark_arr_x_new, landmark_arr_y_new)
for j in range(len(y_pre_asm)):
asm_loss += (truth_vector[j] - y_pre_asm[j]) ** 2
asm_loss /= len(y_pre_asm)
# asm_loss *= mse[i]
# asm_loss *= LearningConfig.regularization_term
loss_array.append(asm_loss)
print('mse[i]' + str(mse[i]))
print('asm_loss[i]' + str(asm_loss))
print('============' )
loss_array = np.array(loss_array)
tensor_asm_loss = K.variable(loss_array)
# sum_loss_tensor = tf.math.add(tensor_mean_square_error, tensor_asm_loss)
tensor_total_loss = tf.reduce_mean([tensor_mean_square_error, tensor_asm_loss], axis=0)
# sum_loss = np.array(K.eval(tensor_asm_loss))
# print(mse)
# print(K.eval(tensor_mean_square_error))
# print(K.eval(tensor_asm_loss))
# print('asm_loss ' + str(loss_array[0]))
# print('mse_loss ' + str(mse[0]))
# print('sum_loss ' + str(sum_loss[0]))
# print('total_loss ' + str(total_loss[0]))
# print(' ')
return tensor_total_loss
def train(self, teachers_arch, teachers_weight_files, teachers_weight_loss,
teachers_tf_train_paths, student_weight_file):
"""
:param teachers_arch: an array containing architecture of teacher networks
:param teachers_weight_files: an array containing teachers h5 files
:param teachers_weight_loss: an array containing weight of teachers model in loss function
:param teachers_tf_train_paths: an array containing path of train tf records
:param student_weight_file : student h5 weight path
:return: null
"""
tf_record_util = TFRecordUtility(self.output_len)
c_loss = Custom_losses()
'''-------------------------------------'''
''' preparing student models '''
'''-------------------------------------'''
teacher_models = []
cnn = CNNModel()
for i in range(len(teachers_arch)):
student_train_images, student_train_landmarks = tf_record_util.create_training_tensor_points(
tfrecord_filename=teachers_tf_train_paths[i],
batch_size=self.BATCH_SIZE)
model = cnn.get_model(train_images=student_train_images,
arch=teachers_arch[i],
num_output_layers=1,
output_len=self.output_len,
input_tensor=None)
model.load_weights(teachers_weight_files[i])
teacher_models.append(model)
'''---------------------------------'''
''' creating student model '''
'''---------------------------------'''
'''retrieve tf data'''
train_images, train_landmarks = tf_record_util.create_training_tensor_points(
tfrecord_filename=self.tf_train_path, batch_size=self.BATCH_SIZE)
validation_images, validation_landmarks = tf_record_util.create_training_tensor_points(
tfrecord_filename=self.tf_eval_path, batch_size=self.BATCH_SIZE)
'''create model'''
student_model = cnn.get_model(train_images=train_images,
arch=self.arch,
num_output_layers=1,
output_len=self.output_len,
input_tensor=train_images,
inp_shape=None)
if student_weight_file is not None:
student_model.load_weights(student_weight_file)
'''prepare callbacks'''
callbacks_list = self._prepare_callback()
''' define optimizers'''
optimizer = Adam(lr=1e-3,
beta_1=0.9,
beta_2=0.999,
decay=1e-5,
amsgrad=False)
'''create loss'''
# file = open("map_aug" + self.dataset_name, 'rb')
file = open("map_orig" + self.dataset_name, 'rb')
landmark_img_map = pickle.load(file)
file.close()
# loss_func = c_loss.custom_teacher_student_loss_cos(img_path=self.img_path, lnd_img_map=landmark_img_map,
# teacher_models=teacher_models,
# teachers_weight_loss=teachers_weight_loss,
# bath_size=self.BATCH_SIZE,
# num_points=self.output_len, cos_weight=cos_weight)
loss_func = c_loss.custom_teacher_student_loss(
img_path=self.img_path,
lnd_img_map=landmark_img_map,
teacher_models=teacher_models,
teachers_weight_loss=teachers_weight_loss,
bath_size=self.BATCH_SIZE,
num_points=self.output_len,
ds_name=self.dataset_name,
loss_type=0)
'''compiling model'''
student_model.compile(loss=loss_func,
optimizer=optimizer,
metrics=['mse', 'mae'],
target_tensors=train_landmarks)
print('< ========== Start Training Student============= >')
history = student_model.fit(
train_images,
train_landmarks,
epochs=self.EPOCHS,
steps_per_epoch=self.STEPS_PER_EPOCH,
validation_data=(validation_images, validation_landmarks),
validation_steps=self.STEPS_PER_VALIDATION_EPOCH,
verbose=1,
callbacks=callbacks_list)
from tf_record_utility import TFRecordUtility
from configuration import DatasetName, DatasetType, AffectnetConf, IbugConf, W300Conf, InputDataSize
from cnn_model import CNNModel
from pca_utility import PCAUtility
from image_utility import ImageUtility
import numpy as np
from train import Train
from test import Test
if __name__ == '__main__':
tf_record_util = TFRecordUtility()
pca_utility = PCAUtility()
cnn_model = CNNModel()
image_utility = ImageUtility()
# trainer = Train(use_tf_record=False,
# dataset_name=DatasetName.ibug,
# custom_loss=False,
# arch='mn_main',
# inception_mode=True,
# num_output_layers=1,
# point_wise=True,
# weight=None
# )
# tester = Test()
# trainer = Train(use_tf_record=True,
# dataset_name=DatasetName.ibug,
# custom_loss=False,
# arch='mn_r',
