def test_samm(batch_size, spatial_epochs, temporal_epochs, train_id, dB,
spatial_size, flag, tensorboard):
############## Path Preparation ######################
root_db_path = "/media/viprlab/01D31FFEF66D5170/"
workplace = root_db_path + dB + "/"
inputDir = root_db_path + dB + "/" + dB + "/"
######################################################
classes = 5
if dB == 'CASME2_TIM':
table = loading_casme_table(workplace + 'CASME2-ObjectiveClasses.xlsx')
listOfIgnoredSamples, IgnoredSamples_index = ignore_casme_samples(
inputDir)
############## Variables ###################
r = w = spatial_size
subjects = 2
n_exp = 5
# VidPerSubject = get_subfolders_num(inputDir, IgnoredSamples_index)
listOfIgnoredSamples = []
VidPerSubject = [2, 1]
timesteps_TIM = 10
data_dim = r * w
pad_sequence = 10
channel = 3
############################################
os.remove(workplace + "Classification/CASME2_TIM_label.txt")
elif dB == 'CASME2_Optical':
table = loading_casme_table(workplace + 'CASME2-ObjectiveClasses.xlsx')
listOfIgnoredSamples, IgnoredSamples_index = ignore_casme_samples(
inputDir)
############## Variables ###################
r = w = spatial_size
subjects = 26
n_exp = 5
VidPerSubject = get_subfolders_num(inputDir, IgnoredSamples_index)
timesteps_TIM = 9
data_dim = r * w
pad_sequence = 9
channel = 3
############################################
# os.remove(workplace + "Classification/CASME2_TIM_label.txt")
elif dB == 'SAMM_TIM10':
table, table_objective = loading_samm_table(root_db_path, dB)
listOfIgnoredSamples = []
IgnoredSamples_index = np.empty([0])
################# Variables #############################
r = w = spatial_size
subjects = 29
n_exp = 8
VidPerSubject = get_subfolders_num(inputDir, IgnoredSamples_index)
timesteps_TIM = 10
data_dim = r * w
pad_sequence = 10
channel = 3
classes = 8
#########################################################
elif dB == 'SAMM_CASME_Optical':
# total amount of videos 253
table, table_objective = loading_samm_table(root_db_path, dB)
table = table_objective
table2 = loading_casme_objective_table(root_db_path, dB)
# merge samm and casme tables
table = np.concatenate((table, table2), axis=1)
# print(table.shape)
# listOfIgnoredSamples, IgnoredSamples_index, sub_items = ignore_casme_samples(inputDir)
listOfIgnoredSamples = []
IgnoredSamples_index = np.empty([0])
sub_items = np.empty([0])
list_samples = filter_objective_samples(table)
r = w = spatial_size
subjects = 47 # some subjects were removed because of objective classes and ignore samples: 47
n_exp = 5
# TODO:
# 1) Further decrease the video amount, the one with objective classes >= 6
# list samples: samples with wanted objective class
VidPerSubject, list_samples = get_subfolders_num_crossdb(
inputDir, IgnoredSamples_index, sub_items, table, list_samples)
# print(VidPerSubject)
# print(len(VidPerSubject))
# print(sum(VidPerSubject))
timesteps_TIM = 9
data_dim = r * w
channel = 3
classes = 5
if os.path.isfile(workplace +
"Classification/SAMM_CASME_Optical_label.txt"):
os.remove(workplace +
"Classification/SAMM_CASME_Optical_label.txt")
##################### Variables ######################
######################################################
############## Flags ####################
tensorboard_flag = tensorboard
resizedFlag = 1
train_spatial_flag = 0
train_temporal_flag = 0
svm_flag = 0
finetuning_flag = 0
cam_visualizer_flag = 0
channel_flag = 0
if flag == 'st':
train_spatial_flag = 1
train_temporal_flag = 1
finetuning_flag = 1
elif flag == 's':
train_spatial_flag = 1
finetuning_flag = 1
elif flag == 't':
train_temporal_flag = 1
elif flag == 'nofine':
svm_flag = 1
elif flag == 'scratch':
train_spatial_flag = 1
train_temporal_flag = 1
elif flag == 'st4':
train_spatial_flag = 1
train_temporal_flag = 1
channel_flag = 1
elif flag == 'st7':
train_spatial_flag = 1
train_temporal_flag = 1
channel_flag = 2
#########################################
############ Reading Images and Labels ################
SubperdB = Read_Input_Images_SAMM_CASME(inputDir, list_samples,
listOfIgnoredSamples, dB,
resizedFlag, table, workplace,
spatial_size, channel)
print("Loaded Images into the tray...")
labelperSub = label_matching(workplace, dB, subjects, VidPerSubject)
print("Loaded Labels into the tray...")
if channel_flag == 1:
SubperdB_strain = Read_Input_Images_SAMM_CASME(
inputDir, list_samples, listOfIgnoredSamples, 'SAMM_CASME_Strain',
resizedFlag, table, workplace, spatial_size, 1)
elif channel_flag == 2:
SubperdB_strain = Read_Input_Images(inputDir, listOfIgnoredSamples,
'CASME2_Strain_TIM10', resizedFlag,
table, workplace, spatial_size, 1)
SubperdB_gray = Read_Input_Images(inputDir, listOfIgnoredSamples,
'CASME2_TIM', resizedFlag, table,
workplace, spatial_size, 3)
#######################################################
########### Model Configurations #######################
sgd = optimizers.SGD(lr=0.0001, decay=1e-7, momentum=0.9, nesterov=True)
adam = optimizers.Adam(lr=0.00001, decay=0.000001)
adam2 = optimizers.Adam(lr=0.00075, decay=0.0001)
# Different Conditions for Temporal Learning ONLY
if train_spatial_flag == 0 and train_temporal_flag == 1 and dB != 'CASME2_Optical':
data_dim = spatial_size * spatial_size
elif train_spatial_flag == 0 and train_temporal_flag == 1 and dB == 'CASME2_Optical':
data_dim = spatial_size * spatial_size * 3
else:
data_dim = 4096
########################################################
########### Training Process ############
# total confusion matrix to be used in the computation of f1 score
tot_mat = np.zeros((n_exp, n_exp))
# model checkpoint
spatial_weights_name = 'vgg_spatial_' + str(train_id) + '_casme2_'
temporal_weights_name = 'temporal_ID_' + str(train_id) + '_casme2_'
history = LossHistory()
stopping = EarlyStopping(monitor='loss',
min_delta=0,
mode='min',
patience=5)
# model checkpoint
if os.path.isdir('/media/viprlab/01D31FFEF66D5170/Weights/' +
str(train_id)) == False:
os.mkdir('/media/viprlab/01D31FFEF66D5170/Weights/' + str(train_id))
for sub in range(subjects):
# sub = sub + 25
# if sub > subjects:
# break
############### Reinitialization & weights reset of models ########################
spatial_weights_name = '/media/viprlab/01D31FFEF66D5170/Weights/' + str(
train_id) + '/vgg_spatial_' + str(train_id) + '_' + str(
dB) + '_' + str(sub) + '.h5'
spatial_weights_name_strain = '/media/viprlab/01D31FFEF66D5170/Weights/' + str(
train_id) + '/vgg_spatial_strain_' + str(train_id) + '_' + str(
dB) + '_' + str(sub) + '.h5'
temporal_weights_name = '/media/viprlab/01D31FFEF66D5170/Weights/' + str(
train_id) + '/temporal_ID_' + str(train_id) + '_' + str(
dB) + '_' + str(sub) + '.h5'
ae_weights_name = '/media/viprlab/01D31FFEF66D5170/Weights/' + str(
train_id) + '/autoencoder_' + str(train_id) + '_' + str(
dB) + '_' + str(sub) + '.h5'
ae_weights_name_strain = '/media/viprlab/01D31FFEF66D5170/Weights/' + str(
train_id) + '/autoencoder_strain_' + str(train_id) + '_' + str(
dB) + '_' + str(sub) + '.h5'
temporal_model = temporal_module(data_dim=data_dim,
timesteps_TIM=timesteps_TIM,
weights_path=temporal_weights_name)
temporal_model.compile(loss='categorical_crossentropy',
optimizer=adam,
metrics=[metrics.categorical_accuracy])
if channel_flag == 1 or channel_flag == 2:
vgg_model = VGG_16_4_channels(spatial_size=spatial_size,
weights_path=spatial_weights_name)
vgg_model.compile(loss='categorical_crossentropy',
optimizer=adam,
metrics=[metrics.categorical_accuracy])
else:
vgg_model = VGG_16(spatial_size=spatial_size,
weights_path='VGG_Face_Deep_16.h5')
vgg_model.compile(loss='categorical_crossentropy',
optimizer=adam,
metrics=[metrics.categorical_accuracy])
svm_classifier = SVC(kernel='linear', C=1)
####################################################################################
Train_X, Train_Y, Test_X, Test_Y, Test_Y_gt = data_loader_with_LOSO(
sub, SubperdB, labelperSub, subjects)
# Rearrange Training labels into a vector of images, breaking sequence
Train_X_spatial = Train_X.reshape(Train_X.shape[0] * timesteps_TIM, r,
w, channel)
Test_X_spatial = Test_X.reshape(Test_X.shape[0] * timesteps_TIM, r, w,
channel)
# Special Loading for 4-Channel
if channel_flag == 1:
Train_X_Strain, _, Test_X_Strain, _, _ = data_loader_with_LOSO(
sub, SubperdB_strain, labelperSub, subjects)
Train_X_Strain = Train_X_Strain.reshape(
Train_X_Strain.shape[0] * timesteps_TIM, r, w, 1)
Test_X_Strain = Test_X_Strain.reshape(
Test_X.shape[0] * timesteps_TIM, r, w, 1)
# Concatenate Train X & Train_X_Strain
Train_X_spatial = np.concatenate((Train_X_spatial, Train_X_Strain),
axis=3)
Test_X_spatial = np.concatenate((Test_X_spatial, Test_X_Strain),
axis=3)
total_channel = 4
elif channel_flag == 2:
Train_X_Strain, _, Test_X_Strain, _, _ = data_loader_with_LOSO(
sub, SubperdB_strain, labelperSub, subjects, classes)
Train_X_gray, _, Test_X_gray, _, _ = data_loader_with_LOSO(
sub, SubperdB_gray, labelperSub, subjects)
Train_X_Strain = Train_X_Strain.reshape(
Train_X_Strain.shape[0] * timesteps_TIM, r, w, 1)
Test_X_Strain = Test_X_Strain.reshape(
Test_X_Strain.shape[0] * timesteps_TIM, r, w, 1)
Train_X_gray = Train_X_gray.reshape(
Train_X_gray.shape[0] * timesteps_TIM, r, w, 3)
Test_X_gray = Test_X_gray.reshape(
Test_X_gray.shape[0] * timesteps_TIM, r, w, 3)
# Concatenate Train_X_Strain & Train_X & Train_X_gray
Train_X_spatial = np.concatenate(
(Train_X_spatial, Train_X_Strain, Train_X_gray), axis=3)
Test_X_spatial = np.concatenate(
(Test_X_spatial, Test_X_Strain, Test_X_gray), axis=3)
total_channel = 7
if channel == 1:
# Duplicate channel of input image
Train_X_spatial = duplicate_channel(Train_X_spatial)
Test_X_spatial = duplicate_channel(Test_X_spatial)
# Extend Y labels 10 fold, so that all images have labels
Train_Y_spatial = np.repeat(Train_Y, timesteps_TIM, axis=0)
Test_Y_spatial = np.repeat(Test_Y, timesteps_TIM, axis=0)
print("Train_X_shape: " + str(np.shape(Train_X_spatial)))
print("Train_Y_shape: " + str(np.shape(Train_Y_spatial)))
print("Test_X_shape: " + str(np.shape(Test_X_spatial)))
print("Test_Y_shape: " + str(np.shape(Test_Y_spatial)))
# print(Train_X_spatial)
##################### Training & Testing #########################
X = Train_X_spatial.reshape(Train_X_spatial.shape[0], total_channel, r,
w)
y = Train_Y_spatial.reshape(Train_Y_spatial.shape[0], classes)
normalized_X = X.astype('float32') / 255.
test_X = Test_X_spatial.reshape(Test_X_spatial.shape[0], total_channel,
r, w)
test_y = Test_Y_spatial.reshape(Test_Y_spatial.shape[0], classes)
normalized_test_X = test_X.astype('float32') / 255.
print(X.shape)
###### conv weights must be freezed for transfer learning ######
if finetuning_flag == 1:
for layer in vgg_model.layers[:33]:
layer.trainable = False
for layer in vgg_model_cam.layers[:31]:
layer.trainable = False
if train_spatial_flag == 1 and train_temporal_flag == 1:
# record f1 and loss
file_loss = open(
workplace + 'Classification/' + 'Result/' + dB + '/loss_' +
str(train_id) + '.txt', 'a')
file_loss.write(str(history.losses) + "\n")
file_loss.close()
file_loss = open(
workplace + 'Classification/' + 'Result/' + dB + '/accuracy_' +
str(train_id) + '.txt', 'a')
file_loss.write(str(history.accuracy) + "\n")
file_loss.close()
model = Model(inputs=vgg_model.input,
outputs=vgg_model.layers[35].output)
plot_model(model,
to_file="spatial_module_FULL_TRAINING.png",
show_shapes=True)
# Testing
output = model.predict(test_X, batch_size=batch_size)
features = output.reshape(Test_X.shape[0], timesteps_TIM,
output.shape[1])
predict = temporal_model.predict_classes(features,
batch_size=batch_size)
##############################################################
#################### Confusion Matrix Construction #############
print(predict)
print(Test_Y_gt)
ct = confusion_matrix(Test_Y_gt, predict)
# check the order of the CT
order = np.unique(np.concatenate((predict, Test_Y_gt)))
# create an array to hold the CT for each CV
mat = np.zeros((n_exp, n_exp))
# put the order accordingly, in order to form the overall ConfusionMat
for m in range(len(order)):
for n in range(len(order)):
mat[int(order[m]), int(order[n])] = ct[m, n]
tot_mat = mat + tot_mat
################################################################
#################### cumulative f1 plotting ######################
microAcc = np.trace(tot_mat) / np.sum(tot_mat)
[f1, precision, recall] = fpr(tot_mat, n_exp)
file = open(
workplace + 'Classification/' + 'Result/' + dB + '/f1_' +
str(train_id) + '.txt', 'a')
file.write(str(f1) + "\n")
file.close()
##################################################################
################# write each CT of each CV into .txt file #####################
record_scores(workplace, dB, ct, sub, order, tot_mat, n_exp, subjects)
###############################################################################
image_label_mapping = np.empty([0])
Train_X, Train_Y, Test_X, Test_Y, Test_Y_gt = data_loader_with_LOSO(
sub, SubperdB, labelperSub, subjects)
# Rearrange Training labels into a vector of images, breaking sequence
Train_X_spatial = Train_X.reshape(Train_X.shape[0] * 10, r, w, 1)
Test_X_spatial = Test_X.reshape(Test_X.shape[0] * 10, r, w, 1)
# Extend Y labels 10 fold, so that all images have labels
Train_Y_spatial = np.repeat(Train_Y, 10, axis=0)
Test_Y_spatial = np.repeat(Test_Y, 10, axis=0)
# Duplicate channel of input image
Train_X_spatial = duplicate_channel(Train_X_spatial)
Test_X_spatial = duplicate_channel(Test_X_spatial)
# temp = Test_X_spatial[0]
# temp = cv2.ims(temp)
# cv2.imwrite("concat_image.png", temp)
# print(temp.shape)
##################### VGG FACE 16 #########################
X = Train_X_spatial.reshape(Train_X_spatial.shape[0], 3, r, w)
y = Train_Y_spatial.reshape(Train_Y_spatial.shape[0], 5)
test_X = Test_X_spatial.reshape(Test_X_spatial.shape[0], 3, r, w)
# test_y = Test_Y_spatial.reshape(Test_Y_spatial.shape[0], 5)
test_y = np.repeat(Test_Y_gt, 10, axis=0)
def train_samm_cross(batch_size, spatial_epochs, temporal_epochs, train_id, dB, spatial_size, flag, tensorboard):
############## Path Preparation ######################
root_db_path = "/media/ice/OS/Datasets/"
workplace = root_db_path + dB + "/"
inputDir = root_db_path + dB + "/" + dB + "/"
######################################################
classes = 5
if dB == 'CASME2_TIM':
table = loading_casme_table(workplace + 'CASME2-ObjectiveClasses.xlsx')
listOfIgnoredSamples, IgnoredSamples_index = ignore_casme_samples(inputDir)
############## Variables ###################
r = w = spatial_size
subjects=2
n_exp = 5
# VidPerSubject = get_subfolders_num(inputDir, IgnoredSamples_index)
listOfIgnoredSamples = []
VidPerSubject = [2,1]
timesteps_TIM = 10
data_dim = r * w
pad_sequence = 10
channel = 3
############################################
os.remove(workplace + "Classification/CASME2_TIM_label.txt")
elif dB == 'CASME2_Optical':
table = loading_casme_table(workplace + 'CASME2-ObjectiveClasses.xlsx')
listOfIgnoredSamples, IgnoredSamples_index = ignore_casme_samples(inputDir)
############## Variables ###################
r = w = spatial_size
subjects=26
n_exp = 5
VidPerSubject = get_subfolders_num(inputDir, IgnoredSamples_index)
timesteps_TIM = 9
data_dim = r * w
pad_sequence = 9
channel = 3
############################################
# os.remove(workplace + "Classification/CASME2_TIM_label.txt")
elif dB == 'SAMM_TIM10':
table, table_objective = loading_samm_table(root_db_path, dB)
listOfIgnoredSamples = []
IgnoredSamples_index = np.empty([0])
################# Variables #############################
r = w = spatial_size
subjects = 29
n_exp = 8
VidPerSubject = get_subfolders_num(inputDir, IgnoredSamples_index)
timesteps_TIM = 10
data_dim = r * w
pad_sequence = 10
channel = 3
classes = 8
#########################################################
elif dB == 'SAMM_CASME_Optical':
# total amount of videos 253
# table, table_objective = loading_samm_table(root_db_path, dB)
# table = table_objective
table = loading_casme_objective_table(root_db_path, dB)
# merge samm and casme tables
# table = np.concatenate((table, table2), axis=1)
# print(table.shape)
# listOfIgnoredSamples, IgnoredSamples_index, sub_items = ignore_casme_samples(inputDir)
listOfIgnoredSamples = []
IgnoredSamples_index = np.empty([0])
sub_items = np.empty([0])
list_samples = filter_objective_samples(table)
r = w = spatial_size
subjects = 26 # some subjects were removed because of objective classes and ignore samples: 47
n_exp = 5
# TODO:
# 1) Further decrease the video amount, the one with objective classes >= 6
# list samples: samples with wanted objective class
VidPerSubject, list_samples = get_subfolders_num_crossdb(inputDir, IgnoredSamples_index, sub_items, table, list_samples)
# print(VidPerSubject)
# print(len(VidPerSubject))
# print(sum(VidPerSubject))
timesteps_TIM = 9
data_dim = r * w
channel = 3
classes = 5
if os.path.isfile(workplace + "Classification/SAMM_CASME_Optical_label.txt"):
os.remove(workplace + "Classification/SAMM_CASME_Optical_label.txt")
##################### Variables ######################
######################################################
############## Flags ####################
tensorboard_flag = tensorboard
resizedFlag = 1
train_spatial_flag = 0
train_temporal_flag = 0
svm_flag = 0
finetuning_flag = 0
cam_visualizer_flag = 0
channel_flag = 0
if flag == 'st':
train_spatial_flag = 1
train_temporal_flag = 1
finetuning_flag = 1
elif flag == 's':
train_spatial_flag = 1
finetuning_flag = 1
elif flag == 't':
train_temporal_flag = 1
elif flag == 'nofine':
svm_flag = 1
elif flag == 'scratch':
train_spatial_flag = 1
train_temporal_flag = 1
elif flag == 'st4':
train_spatial_flag = 1
train_temporal_flag = 1
channel_flag = 1
elif flag == 'st7':
train_spatial_flag = 1
train_temporal_flag = 1
channel_flag = 2
#########################################
############ Reading Images and Labels ################
SubperdB = Read_Input_Images_SAMM_CASME(inputDir, list_samples, listOfIgnoredSamples, dB, resizedFlag, table, workplace, spatial_size, channel)
print("Loaded Images into the tray...")
labelperSub = label_matching(workplace, dB, subjects, VidPerSubject)
print("Loaded Labels into the tray...")
if channel_flag == 1:
SubperdB_strain = Read_Input_Images(inputDir, listOfIgnoredSamples, 'CASME2_Strain_TIM10', resizedFlag, table, workplace, spatial_size, 1)
elif channel_flag == 2:
SubperdB_strain = Read_Input_Images(inputDir, listOfIgnoredSamples, 'CASME2_Strain_TIM10', resizedFlag, table, workplace, spatial_size, 1)
SubperdB_gray = Read_Input_Images(inputDir, listOfIgnoredSamples, 'CASME2_TIM', resizedFlag, table, workplace, spatial_size, 3)
#######################################################
########### Model Configurations #######################
sgd = optimizers.SGD(lr=0.0001, decay=1e-7, momentum=0.9, nesterov=True)
adam = optimizers.Adam(lr=0.00001, decay=0.000001)
adam2 = optimizers.Adam(lr= 0.00075, decay= 0.0001)
# Different Conditions for Temporal Learning ONLY
if train_spatial_flag == 0 and train_temporal_flag == 1 and dB != 'CASME2_Optical':
data_dim = spatial_size * spatial_size
elif train_spatial_flag == 0 and train_temporal_flag == 1 and dB == 'CASME2_Optical':
data_dim = spatial_size * spatial_size * 3
else:
data_dim = 4096
########################################################
########### Training Process ############
# total confusion matrix to be used in the computation of f1 score
tot_mat = np.zeros((n_exp,n_exp))
# model checkpoint
spatial_weights_name = 'vgg_spatial_'+ str(train_id) + '_casme2_'
temporal_weights_name = 'temporal_ID_' + str(train_id) + '_casme2_'
history = LossHistory()
stopping = EarlyStopping(monitor='loss', min_delta = 0, mode = 'min')
############### Reinitialization & weights reset of models ########################
vgg_model_cam = VGG_16(spatial_size=spatial_size, classes=classes, weights_path='VGG_Face_Deep_16.h5')
temporal_model = temporal_module(data_dim=data_dim, classes=classes, timesteps_TIM=timesteps_TIM)
temporal_model.compile(loss='categorical_crossentropy', optimizer=adam, metrics=[metrics.categorical_accuracy])
conv_ae = convolutional_autoencoder(spatial_size = spatial_size, classes = classes)
conv_ae.compile(loss='binary_crossentropy', optimizer=adam)
if channel_flag == 1 or channel_flag == 2:
vgg_model = VGG_16_4_channels(classes=classes, spatial_size = spatial_size)
vgg_model.compile(loss='categorical_crossentropy', optimizer=adam, metrics=[metrics.categorical_accuracy])
else:
vgg_model = VGG_16(spatial_size = spatial_size, classes=classes, weights_path='VGG_Face_Deep_16.h5')
vgg_model.compile(loss='categorical_crossentropy', optimizer=adam, metrics=[metrics.categorical_accuracy])
svm_classifier = SVC(kernel='linear', C=1)
####################################################################################
############ for tensorboard ###############
if tensorboard_flag == 1:
cat_path = tensorboard_path + str(sub) + "/"
os.mkdir(cat_path)
tbCallBack = keras.callbacks.TensorBoard(log_dir=cat_path, write_graph=True)
cat_path2 = tensorboard_path + str(sub) + "spat/"
os.mkdir(cat_path2)
tbCallBack2 = keras.callbacks.TensorBoard(log_dir=cat_path2, write_graph=True)
#############################################
image_label_mapping = np.empty([0])
Train_X, Train_Y= standard_data_loader(SubperdB, labelperSub, subjects, classes)
# Rearrange Training labels into a vector of images, breaking sequence
Train_X_spatial = Train_X.reshape(Train_X.shape[0]*timesteps_TIM, r, w, channel)
# Test_X_spatial = Test_X.reshape(Test_X.shape[0]* timesteps_TIM, r, w, channel)
# Special Loading for 4-Channel
if channel_flag == 1:
Train_X_Strain, _, Test_X_Strain, _, _ = data_loader_with_LOSO(sub, SubperdB_strain, labelperSub, subjects, classes)
Train_X_Strain = Train_X_Strain.reshape(Train_X_Strain.shape[0]*timesteps_TIM, r, w, 1)
Test_X_Strain = Test_X_Strain.reshape(Test_X.shape[0]*timesteps_TIM, r, w, 1)
# Concatenate Train X & Train_X_Strain
Train_X_spatial = np.concatenate((Train_X_spatial, Train_X_Strain), axis=3)
Test_X_spatial = np.concatenate((Test_X_spatial, Test_X_Strain), axis=3)
channel = 4
elif channel_flag == 2:
Train_X_Strain, _, Test_X_Strain, _, _ = data_loader_with_LOSO(sub, SubperdB_strain, labelperSub, subjects, classes)
Train_X_gray, _, Test_X_gray, _, _ = data_loader_with_LOSO(sub, SubperdB_gray, labelperSub, subjects)
Train_X_Strain = Train_X_Strain.reshape(Train_X_Strain.shape[0]*timesteps_TIM, r, w, 1)
Test_X_Strain = Test_X_Strain.reshape(Test_X_Strain.shape[0]*timesteps_TIM, r, w, 1)
Train_X_gray = Train_X_gray.reshape(Train_X_gray.shape[0]*timesteps_TIM, r, w, 3)
Test_X_gray = Test_X_gray.reshape(Test_X_gray.shape[0]*timesteps_TIM, r, w, 3)
# Concatenate Train_X_Strain & Train_X & Train_X_gray
Train_X_spatial = np.concatenate((Train_X_spatial, Train_X_Strain, Train_X_gray), axis=3)
Test_X_spatial = np.concatenate((Test_X_spatial, Test_X_Strain, Test_X_gray), axis=3)
channel = 7
if channel == 1:
# Duplicate channel of input image
Train_X_spatial = duplicate_channel(Train_X_spatial)
# Test_X_spatial = duplicate_channel(Test_X_spatial)
# Extend Y labels 10 fold, so that all images have labels
Train_Y_spatial = np.repeat(Train_Y, timesteps_TIM, axis=0)
# Test_Y_spatial = np.repeat(Test_Y, timesteps_TIM, axis=0)
# print ("Train_X_shape: " + str(np.shape(Train_X_spatial)))
# print ("Train_Y_shape: " + str(np.shape(Train_Y_spatial)))
# print ("Test_X_shape: " + str(np.shape(Test_X_spatial)))
# print ("Test_Y_shape: " + str(np.shape(Test_Y_spatial)))
# print(Train_X_spatial)
##################### Training & Testing #########################
X = Train_X_spatial.reshape(Train_X_spatial.shape[0], channel, r, w)
y = Train_Y_spatial.reshape(Train_Y_spatial.shape[0], classes)
normalized_X = X.astype('float32') / 255.
# test_X = Test_X_spatial.reshape(Test_X_spatial.shape[0], channel, r, w)
# test_y = Test_Y_spatial.reshape(Test_Y_spatial.shape[0], classes)
# normalized_test_X = test_X.astype('float32') / 255.
print(X.shape)
###### conv weights must be freezed for transfer learning ######
if finetuning_flag == 1:
for layer in vgg_model.layers[:33]:
layer.trainable = False
for layer in vgg_model_cam.layers[:31]:
layer.trainable = False
if train_spatial_flag == 1 and train_temporal_flag == 1:
# Autoencoder features
# conv_ae.fit(normalized_X, normalized_X, batch_size=batch_size, epochs=spatial_epochs, shuffle=True)
# Spatial Training
if tensorboard_flag == 1:
vgg_model.fit(X, y, batch_size=batch_size, epochs=spatial_epochs, shuffle=True, callbacks=[tbCallBack2])
else:
vgg_model.fit(X, y, batch_size=batch_size, epochs=spatial_epochs, shuffle=True, callbacks=[history, stopping])
# record f1 and loss
file_loss = open(workplace+'Classification/'+ 'Result/'+dB+'/loss_' + str(train_id) + '.txt', 'a')
file_loss.write(str(history.losses) + "\n")
file_loss.close()
file_loss = open(workplace+'Classification/'+ 'Result/'+dB+'/accuracy_' + str(train_id) + '.txt', 'a')
file_loss.write(str(history.accuracy) + "\n")
file_loss.close()
vgg_model.save_weights(spatial_weights_name + 'HDE'+ ".h5")
model = Model(inputs=vgg_model.input, outputs=vgg_model.layers[35].output)
plot_model(model, to_file="spatial_module_FULL_TRAINING.png", show_shapes=True)
model_ae = Model(inputs=conv_ae.input, outputs=conv_ae.output)
plot_model(model_ae, to_file='autoencoders.png', show_shapes=True)
# Autoencoding
output_ae = model_ae.predict(normalized_X, batch_size = batch_size)
for i in range(batch_size):
visual_ae = output_ae[i].reshape(224,224,channel)
# de-normalize
visual_ae = ( ( visual_ae - min(visual_ae) ) / ( max(visual_ae) - min(visual_ae) ) ) * 255
fname = '{prefix}_{index}_{hash}.{format}'.format(prefix='AE_output', index=str(sub),
hash=np.random.randint(1e7), format='png')
cv2.imwrite(workplace+'Classification/Result/ae_train/'+fname, visual_ae)
output_ae = model.predict(output_ae, batch_size = batch_size)
# Spatial Encoding
output = model.predict(X, batch_size = batch_size)
# features = output.reshape(int(Train_X.shape[0]), timesteps_TIM, output.shape[1])
# merging autoencoded features and spatial features
output = np.concatenate((output, output_ae), axis=1)
# print(output.shape)
features = output.reshape(int(Train_X.shape[0]), timesteps_TIM, output.shape[1])
# Temporal Training
if tensorboard_flag == 1:
temporal_model.fit(features, Train_Y, batch_size=batch_size, epochs=temporal_epochs, callbacks=[tbCallBack])
else:
temporal_model.fit(features, Train_Y, batch_size=batch_size, epochs=temporal_epochs)
temporal_model.save_weights(temporal_weights_name + 'HDE' + ".h5")
# # Testing
# output = model.predict(test_X, batch_size = batch_size)
# output_ae = model_ae.predict(normalized_test_X, batch_size = batch_size)
# for i in range(batch_size):
# visual_ae = output_ae[i].reshape(224,224,channel)
# # de-normalize
# visual_ae = ( ( visual_ae - min(visual_ae) ) / ( max(visual_ae) - min(visual_ae) ) ) * 255
# fname = '{prefix}_{index}_{hash}.{format}'.format(prefix='AE_output', index=str(sub),
# hash=np.random.randint(1e7), format='png')
# cv2.imwrite(workplace+'Classification/Result/ae_train/'+fname, visual_ae)
# output_ae = model.predict(output_ae, batch_size = batch_size)
# output = np.concatenate((output, output_ae), axis=1)
# features = output.reshape(Test_X.shape[0], timesteps_TIM, output.shape[1])
# predict = temporal_model.predict_classes(features, batch_size=batch_size)
# ##############################################################
# #################### Confusion Matrix Construction #############
# print (predict)
# print (Test_Y_gt)
# ct = confusion_matrix(Test_Y_gt,predict)
# # check the order of the CT
# order = np.unique(np.concatenate((predict,Test_Y_gt)))
# # create an array to hold the CT for each CV
# mat = np.zeros((n_exp,n_exp))
# # put the order accordingly, in order to form the overall ConfusionMat
# for m in range(len(order)):
# for n in range(len(order)):
# mat[int(order[m]),int(order[n])]=ct[m,n]
# tot_mat = mat + tot_mat
# ################################################################
# #################### cumulative f1 plotting ######################
# microAcc = np.trace(tot_mat) / np.sum(tot_mat)
# [f1,precision,recall] = fpr(tot_mat,n_exp)
# file = open(workplace+'Classification/'+ 'Result/'+dB+'/f1_' + str(train_id) + '.txt', 'a')
# file.write(str(f1) + "\n")
# file.close()
##################################################################
################# write each CT of each CV into .txt file #####################
# record_scores(workplace, dB, ct, sub, order, tot_mat, n_exp, subjects)
###############################################################################
def train_cae_lstm(batch_size, spatial_epochs, temporal_epochs, train_id, dB,
spatial_size, flag, tensorboard):
############## Path Preparation ######################
root_db_path = "/media/ice/OS/Datasets/"
workplace = root_db_path + dB + "/"
inputDir = root_db_path + dB + "/" + dB + "/"
######################################################
r, w, subjects, samples, n_exp, VidPerSubject, timesteps_TIM, timesteps_TIM, data_dim, channel, table, listOfIgnoredSamples = load_db(
root_db_path, dB, spatial_size)
# print(VidPerSubject)
############## Flags ####################
tensorboard_flag = tensorboard
resizedFlag = 1
train_spatial_flag = 0
train_temporal_flag = 0
svm_flag = 0
finetuning_flag = 0
cam_visualizer_flag = 0
channel_flag = 0
if flag == 'st':
train_spatial_flag = 1
train_temporal_flag = 1
finetuning_flag = 1
elif flag == 's':
train_spatial_flag = 1
finetuning_flag = 1
elif flag == 't':
train_temporal_flag = 1
elif flag == 'nofine':
svm_flag = 1
elif flag == 'scratch':
train_spatial_flag = 1
train_temporal_flag = 1
elif flag == 'st4':
train_spatial_flag = 1
train_temporal_flag = 1
channel_flag = 1
elif flag == 'st7':
train_spatial_flag = 1
train_temporal_flag = 1
channel_flag = 2
#########################################
############ Reading Images and Labels ################
SubperdB = Read_Input_Images(inputDir, listOfIgnoredSamples, dB,
resizedFlag, table, workplace, spatial_size,
channel)
print("Loaded Images into the tray...")
labelperSub = label_matching(workplace, dB, subjects, VidPerSubject)
print("Loaded Labels into the tray...")
if channel_flag == 1:
SubperdB_strain = Read_Input_Images(inputDir, listOfIgnoredSamples,
'CASME2_Strain_TIM10', resizedFlag,
table, workplace, spatial_size, 1)
elif channel_flag == 2:
SubperdB_strain = Read_Input_Images(inputDir, listOfIgnoredSamples,
'CASME2_Strain_TIM10', resizedFlag,
table, workplace, spatial_size, 1)
SubperdB_gray = Read_Input_Images(inputDir, listOfIgnoredSamples,
'CASME2_TIM', resizedFlag, table,
workplace, spatial_size, 3)
#######################################################
########### Model Configurations #######################
sgd = optimizers.SGD(lr=0.0001, decay=1e-7, momentum=0.9, nesterov=True)
adam = optimizers.Adam(lr=0.00001, decay=0.000001)
# Different Conditions for Temporal Learning ONLY
if train_spatial_flag == 0 and train_temporal_flag == 1 and dB != 'CASME2_Optical':
data_dim = spatial_size * spatial_size
elif train_spatial_flag == 0 and train_temporal_flag == 1 and dB == 'CASME2_Optical':
data_dim = spatial_size * spatial_size * 3
else:
data_dim = 4096
########################################################
########### Training Process ############
# Todo:
# 1) LOSO (done)
# 2) call model (done)
# 3) saving model architecture
# 4) Saving Checkpoint (done)
# 5) make prediction (done)
if tensorboard_flag == 1:
tensorboard_path = "/home/ice/Documents/Micro-Expression/tensorboard/"
# total confusion matrix to be used in the computation of f1 score
tot_mat = np.zeros((n_exp, n_exp))
# model checkpoint
spatial_weights_name = 'vgg_spatial_' + str(train_id) + '_' + str(dB) + '_'
temporal_weights_name = 'temporal_ID_' + str(train_id) + '_' + str(
dB) + '_'
ae_weights_name = 'autoencoder_' + str(train_id) + '_' + str(dB) + '_'
history = LossHistory()
stopping = EarlyStopping(monitor='loss', min_delta=0, mode='min')
for sub in range(subjects):
############### Reinitialization & weights reset of models ########################
vgg_model_cam = VGG_16(spatial_size=spatial_size,
classes=classes,
weights_path='VGG_Face_Deep_16.h5')
temporal_model = temporal_module(data_dim=data_dim,
classes=classes,
timesteps_TIM=timesteps_TIM)
temporal_model.compile(loss='categorical_crossentropy',
optimizer=adam,
metrics=[metrics.categorical_accuracy])
conv_ae = convolutional_autoencoder(spatial_size=spatial_size,
classes=classes)
conv_ae.compile(loss='binary_crossentropy', optimizer=adam)
if channel_flag == 1 or channel_flag == 2:
vgg_model = VGG_16_4_channels(classes=classes,
spatial_size=spatial_size)
vgg_model.compile(loss='categorical_crossentropy',
optimizer=adam,
metrics=[metrics.categorical_accuracy])
else:
vgg_model = VGG_16(spatial_size=spatial_size,
classes=classes,
weights_path='VGG_Face_Deep_16.h5')
vgg_model.compile(loss='categorical_crossentropy',
optimizer=adam,
metrics=[metrics.categorical_accuracy])
svm_classifier = SVC(kernel='linear', C=1)
####################################################################################
############ for tensorboard ###############
if tensorboard_flag == 1:
cat_path = tensorboard_path + str(sub) + "/"
os.mkdir(cat_path)
tbCallBack = keras.callbacks.TensorBoard(log_dir=cat_path,
write_graph=True)
cat_path2 = tensorboard_path + str(sub) + "spat/"
os.mkdir(cat_path2)
tbCallBack2 = keras.callbacks.TensorBoard(log_dir=cat_path2,
write_graph=True)
#############################################
image_label_mapping = np.empty([0])
Train_X, Train_Y, Test_X, Test_Y, Test_Y_gt = data_loader_with_LOSO(
sub, SubperdB, labelperSub, subjects, classes)
# Rearrange Training labels into a vector of images, breaking sequence
Train_X_spatial = Train_X.reshape(Train_X.shape[0] * timesteps_TIM, r,
w, channel)
Test_X_spatial = Test_X.reshape(Test_X.shape[0] * timesteps_TIM, r, w,
channel)
# Special Loading for 4-Channel
if channel_flag == 1:
Train_X_Strain, _, Test_X_Strain, _, _ = data_loader_with_LOSO(
sub, SubperdB_strain, labelperSub, subjects, classes)
Train_X_Strain = Train_X_Strain.reshape(
Train_X_Strain.shape[0] * timesteps_TIM, r, w, 1)
Test_X_Strain = Test_X_Strain.reshape(
Test_X.shape[0] * timesteps_TIM, r, w, 1)
# Concatenate Train X & Train_X_Strain
Train_X_spatial = np.concatenate((Train_X_spatial, Train_X_Strain),
axis=3)
Test_X_spatial = np.concatenate((Test_X_spatial, Test_X_Strain),
axis=3)
channel = 4
elif channel_flag == 2:
Train_X_Strain, _, Test_X_Strain, _, _ = data_loader_with_LOSO(
sub, SubperdB_strain, labelperSub, subjects, classes)
Train_X_gray, _, Test_X_gray, _, _ = data_loader_with_LOSO(
sub, SubperdB_gray, labelperSub, subjects)
Train_X_Strain = Train_X_Strain.reshape(
Train_X_Strain.shape[0] * timesteps_TIM, r, w, 1)
Test_X_Strain = Test_X_Strain.reshape(
Test_X_Strain.shape[0] * timesteps_TIM, r, w, 1)
Train_X_gray = Train_X_gray.reshape(
Train_X_gray.shape[0] * timesteps_TIM, r, w, 3)
Test_X_gray = Test_X_gray.reshape(
Test_X_gray.shape[0] * timesteps_TIM, r, w, 3)
# Concatenate Train_X_Strain & Train_X & Train_X_gray
Train_X_spatial = np.concatenate(
(Train_X_spatial, Train_X_Strain, Train_X_gray), axis=3)
Test_X_spatial = np.concatenate(
(Test_X_spatial, Test_X_Strain, Test_X_gray), axis=3)
channel = 7
if channel == 1:
# Duplicate channel of input image
Train_X_spatial = duplicate_channel(Train_X_spatial)
Test_X_spatial = duplicate_channel(Test_X_spatial)
# Extend Y labels 10 fold, so that all images have labels
Train_Y_spatial = np.repeat(Train_Y, timesteps_TIM, axis=0)
Test_Y_spatial = np.repeat(Test_Y, timesteps_TIM, axis=0)
# print ("Train_X_shape: " + str(np.shape(Train_X_spatial)))
# print ("Train_Y_shape: " + str(np.shape(Train_Y_spatial)))
# print ("Test_X_shape: " + str(np.shape(Test_X_spatial)))
# print ("Test_Y_shape: " + str(np.shape(Test_Y_spatial)))
# print(Train_X_spatial)
##################### Training & Testing #########################
# print(Train_X_spatial.shape)
X = Train_X_spatial.reshape(Train_X_spatial.shape[0], channel, r, w)
y = Train_Y_spatial.reshape(Train_Y_spatial.shape[0], classes)
normalized_X = X.astype('float32') / 255.
test_X = Test_X_spatial.reshape(Test_X_spatial.shape[0], channel, r, w)
test_y = Test_Y_spatial.reshape(Test_Y_spatial.shape[0], classes)
normalized_test_X = test_X.astype('float32') / 255.
print(X.shape)
###### conv weights must be freezed for transfer learning ######
if finetuning_flag == 1:
for layer in vgg_model.layers[:33]:
layer.trainable = False
for layer in vgg_model_cam.layers[:31]:
layer.trainable = False
if train_spatial_flag == 1 and train_temporal_flag == 1:
# Autoencoder first training
conv_ae.fit(normalized_X,
normalized_X,
batch_size=batch_size,
epochs=spatial_epochs,
shuffle=True)
# remove decoder
conv_ae.pop()
conv_ae.pop()
conv_ae.pop()
conv_ae.pop()
conv_ae.pop()
conv_ae.pop()
conv_ae.pop()
# append dense layers
conv_ae.add(Flatten())
conv_ae.add(Dense(4096, activation='relu'))
conv_ae.add(Dense(4096, activation='relu'))
conv_ae.add(Dense(n_exp, activation='sigmoid'))
model_ae = Model(inputs=conv_ae.input,
outputs=conv_ae.layers[9].output)
plot_model(model_ae, to_file='autoencoders.png', show_shapes=True)
# freeze encoder
for layer in conv_ae.layers[:6]:
layer.trainable = False
# finetune dense layers
conv_ae.compile(loss='categorical_crossentropy', optimizer=adam)
conv_ae.fit(normalized_X,
y,
batch_size=batch_size,
epochs=spatial_epochs,
shuffle=True)
model_ae = Model(inputs=conv_ae.input,
outputs=conv_ae.layers[8].output)
plot_model(model_ae, to_file='autoencoders.png', show_shapes=True)
# Autoencoding
output = model_ae.predict(normalized_X, batch_size=batch_size)
# print(output.shape)
features = output.reshape(int(Train_X.shape[0]), timesteps_TIM,
output.shape[1])
temporal_model.fit(features,
Train_Y,
batch_size=batch_size,
epochs=temporal_epochs)
temporal_model.save_weights(temporal_weights_name + str(sub) +
".h5")
# Testing
output = model_ae.predict(test_X, batch_size=batch_size)
features = output.reshape(Test_X.shape[0], timesteps_TIM,
output.shape[1])
predict = temporal_model.predict_classes(features,
batch_size=batch_size)
#################### Confusion Matrix Construction #############
print(predict)
print(Test_Y_gt)
ct = confusion_matrix(Test_Y_gt, predict)
# check the order of the CT
order = np.unique(np.concatenate((predict, Test_Y_gt)))
# create an array to hold the CT for each CV
mat = np.zeros((n_exp, n_exp))
# put the order accordingly, in order to form the overall ConfusionMat
for m in range(len(order)):
for n in range(len(order)):
mat[int(order[m]), int(order[n])] = ct[m, n]
tot_mat = mat + tot_mat
################################################################
#################### cumulative f1 plotting ######################
microAcc = np.trace(tot_mat) / np.sum(tot_mat)
[f1, precision, recall] = fpr(tot_mat, n_exp)
file = open(
workplace + 'Classification/' + 'Result/' + dB + '/f1_' +
str(train_id) + '.txt', 'a')
file.write(str(f1) + "\n")
file.close()
##################################################################
################# write each CT of each CV into .txt file #####################
record_scores(workplace, dB, ct, sub, order, tot_mat, n_exp, subjects)
###############################################################################
def train_samm(batch_size, spatial_epochs, temporal_epochs, train_id, dB,
spatial_size, flag, tensorboard):
############## Path Preparation ######################
root_db_path = "/media/ice/OS/Datasets/"
workplace = root_db_path + dB + "/"
inputDir = root_db_path + dB + "/" + dB + "/"
######################################################
classes = 5
if dB == 'CASME2_TIM':
table = loading_casme_table(workplace + 'CASME2-ObjectiveClasses.xlsx')
listOfIgnoredSamples, IgnoredSamples_index = ignore_casme_samples(
inputDir)
############## Variables ###################
r = w = spatial_size
subjects = 2
n_exp = 5
# VidPerSubject = get_subfolders_num(inputDir, IgnoredSamples_index)
listOfIgnoredSamples = []
VidPerSubject = [2, 1]
timesteps_TIM = 10
data_dim = r * w
pad_sequence = 10
channel = 3
############################################
os.remove(workplace + "Classification/CASME2_TIM_label.txt")
elif dB == 'CASME2_Optical':
table = loading_casme_table(workplace + 'CASME2-ObjectiveClasses.xlsx')
listOfIgnoredSamples, IgnoredSamples_index = ignore_casme_samples(
inputDir)
############## Variables ###################
r = w = spatial_size
subjects = 26
n_exp = 5
VidPerSubject = get_subfolders_num(inputDir, IgnoredSamples_index)
timesteps_TIM = 9
data_dim = r * w
pad_sequence = 9
channel = 3
############################################
# os.remove(workplace + "Classification/CASME2_TIM_label.txt")
elif dB == 'SAMM_TIM10':
table, table_objective = loading_samm_table(root_db_path, dB)
listOfIgnoredSamples = []
IgnoredSamples_index = np.empty([0])
################# Variables #############################
r = w = spatial_size
subjects = 29
n_exp = 8
VidPerSubject = get_subfolders_num(inputDir, IgnoredSamples_index)
timesteps_TIM = 10
data_dim = r * w
pad_sequence = 10
channel = 3
classes = 8
#########################################################
elif dB == 'SAMM_CASME_Strain':
# total amount of videos 253
table, table_objective = loading_samm_table(root_db_path, dB)
table = table_objective
table2 = loading_casme_objective_table(root_db_path, dB)
# merge samm and casme tables
table = np.concatenate((table, table2), axis=1)
# print(table.shape)
# listOfIgnoredSamples, IgnoredSamples_index, sub_items = ignore_casme_samples(inputDir)
listOfIgnoredSamples = []
IgnoredSamples_index = np.empty([0])
sub_items = np.empty([0])
list_samples = filter_objective_samples(table)
r = w = spatial_size
subjects = 47 # some subjects were removed because of objective classes and ignore samples: 47
n_exp = 5
# TODO:
# 1) Further decrease the video amount, the one with objective classes >= 6
# list samples: samples with wanted objective class
VidPerSubject, list_samples = get_subfolders_num_crossdb(
inputDir, IgnoredSamples_index, sub_items, table, list_samples)
# print(VidPerSubject)
# print(len(VidPerSubject))
# print(sum(VidPerSubject))
timesteps_TIM = 9
data_dim = r * w
channel = 3
classes = 5
if os.path.isfile(workplace +
"Classification/SAMM_CASME_Optical_label.txt"):
os.remove(workplace +
"Classification/SAMM_CASME_Optical_label.txt")
##################### Variables ######################
######################################################
############## Flags ####################
tensorboard_flag = tensorboard
resizedFlag = 1
train_spatial_flag = 0
train_temporal_flag = 0
svm_flag = 0
finetuning_flag = 0
cam_visualizer_flag = 0
channel_flag = 0
if flag == 'st':
train_spatial_flag = 1
train_temporal_flag = 1
finetuning_flag = 1
elif flag == 's':
train_spatial_flag = 1
finetuning_flag = 1
elif flag == 't':
train_temporal_flag = 1
elif flag == 'nofine':
svm_flag = 1
elif flag == 'scratch':
train_spatial_flag = 1
train_temporal_flag = 1
elif flag == 'st4':
train_spatial_flag = 1
train_temporal_flag = 1
channel_flag = 1
elif flag == 'st7':
train_spatial_flag = 1
train_temporal_flag = 1
channel_flag = 2
#########################################
############ Reading Images and Labels ################
SubperdB = Read_Input_Images_SAMM_CASME(inputDir, list_samples,
listOfIgnoredSamples, dB,
resizedFlag, table, workplace,
spatial_size, channel)
print("Loaded Images into the tray...")
labelperSub = label_matching(workplace, dB, subjects, VidPerSubject)
print("Loaded Labels into the tray...")
if channel_flag == 1:
SubperdB_strain = Read_Input_Images(inputDir, listOfIgnoredSamples,
'CASME2_Strain_TIM10', resizedFlag,
table, workplace, spatial_size, 1)
elif channel_flag == 2:
SubperdB_strain = Read_Input_Images(inputDir, listOfIgnoredSamples,
'CASME2_Strain_TIM10', resizedFlag,
table, workplace, spatial_size, 1)
SubperdB_gray = Read_Input_Images(inputDir, listOfIgnoredSamples,
'CASME2_TIM', resizedFlag, table,
workplace, spatial_size, 3)
#######################################################
########### Model Configurations #######################
sgd = optimizers.SGD(lr=0.0001, decay=1e-7, momentum=0.9, nesterov=True)
adam = optimizers.Adam(lr=0.00001, decay=0.000001)
adam2 = optimizers.Adam(lr=0.00075, decay=0.0001)
# Different Conditions for Temporal Learning ONLY
if train_spatial_flag == 0 and train_temporal_flag == 1 and dB != 'CASME2_Optical':
data_dim = spatial_size * spatial_size
elif train_spatial_flag == 0 and train_temporal_flag == 1 and dB == 'CASME2_Optical':
data_dim = spatial_size * spatial_size * 3
else:
data_dim = 4096
########################################################
########### Training Process ############
# total confusion matrix to be used in the computation of f1 score
tot_mat = np.zeros((n_exp, n_exp))
# model checkpoint
spatial_weights_name = 'vgg_spatial_' + str(train_id) + '_casme2_'
temporal_weights_name = 'temporal_ID_' + str(train_id) + '_casme2_'
history = LossHistory()
stopping = EarlyStopping(monitor='loss', min_delta=0, mode='min')
for sub in range(subjects):
############### Reinitialization & weights reset of models ########################
vgg_model_cam = VGG_16(spatial_size=spatial_size,
classes=classes,
weights_path='VGG_Face_Deep_16.h5')
temporal_model = temporal_module(data_dim=data_dim,
classes=classes,
timesteps_TIM=timesteps_TIM)
temporal_model.compile(loss='categorical_crossentropy',
optimizer=adam,
metrics=[metrics.categorical_accuracy])
conv_ae = convolutional_autoencoder(spatial_size=spatial_size,
classes=classes)
conv_ae.compile(loss='binary_crossentropy', optimizer=adam)
if channel_flag == 1 or channel_flag == 2:
vgg_model = VGG_16_4_channels(classes=classes,
spatial_size=spatial_size)
vgg_model.compile(loss='categorical_crossentropy',
optimizer=adam,
metrics=[metrics.categorical_accuracy])
else:
vgg_model = VGG_16(spatial_size=spatial_size,
classes=classes,
weights_path='VGG_Face_Deep_16.h5')
vgg_model.compile(loss='categorical_crossentropy',
optimizer=adam,
metrics=[metrics.categorical_accuracy])
svm_classifier = SVC(kernel='linear', C=1)
####################################################################################
############ for tensorboard ###############
if tensorboard_flag == 1:
cat_path = tensorboard_path + str(sub) + "/"
os.mkdir(cat_path)
tbCallBack = keras.callbacks.TensorBoard(log_dir=cat_path,
write_graph=True)
cat_path2 = tensorboard_path + str(sub) + "spat/"
os.mkdir(cat_path2)
tbCallBack2 = keras.callbacks.TensorBoard(log_dir=cat_path2,
write_graph=True)
#############################################
image_label_mapping = np.empty([0])
Train_X, Train_Y, Test_X, Test_Y, Test_Y_gt = data_loader_with_LOSO(
sub, SubperdB, labelperSub, subjects, classes)
# Rearrange Training labels into a vector of images, breaking sequence
Train_X_spatial = Train_X.reshape(Train_X.shape[0] * timesteps_TIM, r,
w, channel)
Test_X_spatial = Test_X.reshape(Test_X.shape[0] * timesteps_TIM, r, w,
channel)
# Special Loading for 4-Channel
if channel_flag == 1:
Train_X_Strain, _, Test_X_Strain, _, _ = data_loader_with_LOSO(
sub, SubperdB_strain, labelperSub, subjects, classes)
Train_X_Strain = Train_X_Strain.reshape(
Train_X_Strain.shape[0] * timesteps_TIM, r, w, 1)
Test_X_Strain = Test_X_Strain.reshape(
Test_X.shape[0] * timesteps_TIM, r, w, 1)
# Concatenate Train X & Train_X_Strain
Train_X_spatial = np.concatenate((Train_X_spatial, Train_X_Strain),
axis=3)
Test_X_spatial = np.concatenate((Test_X_spatial, Test_X_Strain),
axis=3)
channel = 4
elif channel_flag == 2:
Train_X_Strain, _, Test_X_Strain, _, _ = data_loader_with_LOSO(
sub, SubperdB_strain, labelperSub, subjects, classes)
Train_X_gray, _, Test_X_gray, _, _ = data_loader_with_LOSO(
sub, SubperdB_gray, labelperSub, subjects)
Train_X_Strain = Train_X_Strain.reshape(
Train_X_Strain.shape[0] * timesteps_TIM, r, w, 1)
Test_X_Strain = Test_X_Strain.reshape(
Test_X_Strain.shape[0] * timesteps_TIM, r, w, 1)
Train_X_gray = Train_X_gray.reshape(
Train_X_gray.shape[0] * timesteps_TIM, r, w, 3)
Test_X_gray = Test_X_gray.reshape(
Test_X_gray.shape[0] * timesteps_TIM, r, w, 3)
# Concatenate Train_X_Strain & Train_X & Train_X_gray
Train_X_spatial = np.concatenate(
(Train_X_spatial, Train_X_Strain, Train_X_gray), axis=3)
Test_X_spatial = np.concatenate(
(Test_X_spatial, Test_X_Strain, Test_X_gray), axis=3)
channel = 7
if channel == 1:
# Duplicate channel of input image
Train_X_spatial = duplicate_channel(Train_X_spatial)
Test_X_spatial = duplicate_channel(Test_X_spatial)
# Extend Y labels 10 fold, so that all images have labels
Train_Y_spatial = np.repeat(Train_Y, timesteps_TIM, axis=0)
Test_Y_spatial = np.repeat(Test_Y, timesteps_TIM, axis=0)
# print ("Train_X_shape: " + str(np.shape(Train_X_spatial)))
# print ("Train_Y_shape: " + str(np.shape(Train_Y_spatial)))
# print ("Test_X_shape: " + str(np.shape(Test_X_spatial)))
# print ("Test_Y_shape: " + str(np.shape(Test_Y_spatial)))
# print(Train_X_spatial)
##################### Training & Testing #########################
X = Train_X_spatial.reshape(Train_X_spatial.shape[0], channel, r, w)
y = Train_Y_spatial.reshape(Train_Y_spatial.shape[0], classes)
normalized_X = X.astype('float32') / 255.
test_X = Test_X_spatial.reshape(Test_X_spatial.shape[0], channel, r, w)
test_y = Test_Y_spatial.reshape(Test_Y_spatial.shape[0], classes)
normalized_test_X = test_X.astype('float32') / 255.
print(X.shape)
###### conv weights must be freezed for transfer learning ######
if finetuning_flag == 1:
for layer in vgg_model.layers[:33]:
layer.trainable = False
if train_spatial_flag == 1 and train_temporal_flag == 1:
# Autoencoder features
# conv_ae.fit(normalized_X, normalized_X, batch_size=batch_size, epochs=spatial_epochs, shuffle=True)
# Spatial Training
if tensorboard_flag == 1:
vgg_model.fit(X,
y,
batch_size=batch_size,
epochs=spatial_epochs,
shuffle=True,
callbacks=[tbCallBack2])
else:
vgg_model.fit(X,
y,
batch_size=batch_size,
epochs=spatial_epochs,
shuffle=True,
callbacks=[history, stopping])
# record f1 and loss
file_loss = open(
workplace + 'Classification/' + 'Result/' + dB + '/loss_' +
str(train_id) + '.txt', 'a')
file_loss.write(str(history.losses) + "\n")
file_loss.close()
file_loss = open(
workplace + 'Classification/' + 'Result/' + dB + '/accuracy_' +
str(train_id) + '.txt', 'a')
file_loss.write(str(history.accuracy) + "\n")
file_loss.close()
vgg_model.save_weights(spatial_weights_name + str(sub) + ".h5")
def train_smic(batch_size, spatial_epochs, temporal_epochs, train_id):
############################## Loading Labels & Images ##############################
# /media/ice/OS/Datasets/SMIC_TIM10/SMIC_TIM10
root_db_path = "/media/ice/OS/Datasets/"
dB = "SMIC_TIM10"
inputDir = root_db_path + dB + "/" + dB + "/"
workplace = root_db_path + dB + "/"
subject, filename, label, num_frames = loading_smic_labels(
root_db_path, dB)
filename = filename.as_matrix()
label = label.as_matrix()
table = np.transpose(np.array([filename, label]))
# os.remove(workplace + "Classification/SMIC_label.txt")
################# Variables #############################
spatial_size = 224
r = w = spatial_size
subjects = 16
samples = 164
n_exp = 3
IgnoredSamples_index = np.empty([0])
VidPerSubject = get_subfolders_num(inputDir, IgnoredSamples_index)
listOfIgnoredSamples = []
timesteps_TIM = 10
data_dim = r * w
pad_sequence = 10
#########################################################
############## Flags ####################
resizedFlag = 1
train_spatial_flag = 1
train_temporal_flag = 1
svm_flag = 0
finetuning_flag = 1
tensorboard_flag = 0
cam_visualizer_flag = 1
#########################################
############## Reading Images and Labels ################
# SubperdB = Read_SMIC_Images(inputDir, listOfIgnoredSamples, dB, resizedFlag, table, workplace, spatial_size)
SubperdB = Read_Input_Images(inputDir, listOfIgnoredSamples, dB,
resizedFlag, table, workplace, spatial_size)
labelperSub = label_matching(workplace, dB, subjects, VidPerSubject)
######################################################################################
########### Model #######################
sgd = optimizers.SGD(lr=0.0001, decay=1e-7, momentum=0.9, nesterov=True)
adam = optimizers.Adam(lr=0.00001)
if train_spatial_flag == 0 and train_temporal_flag == 1:
data_dim = spatial_size * spatial_size
else:
data_dim = 4096
temporal_model = temporal_module
#########################################
################# Pretrained Model ###################
vgg_model = VGG_16('VGG_Face_Deep_16.h5')
# keras_vgg = keras_vgg16(weights='imagenet')
# vgg_model = VGG_16('imagenet')
vgg_model.compile(loss='categorical_crossentropy',
optimizer=adam,
metrics=[metrics.sparse_categorical_accuracy])
plot_model(vgg_model, to_file='model.png', show_shapes=True)
svm_classifier = SVC(kernel='linear', C=1)
######################################################
# model checkpoint
spatial_weights_name = 'vgg_spatial_17a_smic_'
temporal_weights_name = 'temporal_ID_16_smic_'
# model checkpoint
root = "/home/viprlab/Documents/Micro-Expression/" + spatial_weights_name + "weights.{epoch:02d}-{val_loss:.2f}.hdf5"
root_temporal = "/home/viprlab/Documents/Micro-Expression/" + temporal_weights_name + "weights.{epoch:02d}-{val_loss:.2f}.hdf5"
model_checkpoint = keras.callbacks.ModelCheckpoint(root,
monitor='loss',
save_best_only=True,
save_weights_only=True)
model_checkpoint_temporal = keras.callbacks.ModelCheckpoint(
root_temporal,
monitor='loss',
save_best_only=True,
save_weights_only=True)
########### Training Process ############
# Todo:
# 1) LOSO (done)
# 2) call model (done)
# 3) saving model architecture
# 4) Saving Checkpoint
# 5) make prediction (done)
if tensorboard_flag == 1:
tensorboard_path = "/home/ice/Documents/Micro-Expression/tensorboard/"
tot_mat = np.zeros((n_exp, n_exp))
spatial_weights_name = 'vgg_spatial_ID_under_dev_smic.h5'
temporal_weights_name = 'temporal_ID_under_dev_smic.h5'
for sub in range(subjects):
vgg_model = VGG_16('VGG_Face_Deep_16.h5')
vgg_model.compile(loss='categorical_crossentropy',
optimizer=adam,
metrics=[metrics.sparse_categorical_accuracy])
############ for tensorboard ###############
if tensorboard_flag == 1:
cat_path = tensorboard_path + str(sub) + "/"
os.mkdir(cat_path)
tbCallBack = keras.callbacks.TensorBoard(log_dir=cat_path,
write_graph=True)
cat_path2 = tensorboard_path + str(sub) + "spat/"
os.mkdir(cat_path2)
tbCallBack2 = keras.callbacks.TensorBoard(log_dir=cat_path2,
write_graph=True)
#############################################
image_label_mapping = np.empty([0])
Train_X, Train_Y, Test_X, Test_Y, Test_Y_gt = data_loader_with_LOSO(
sub, SubperdB, labelperSub, subjects)
# Rearrange Training labels into a vector of images, breaking sequence
Train_X_spatial = Train_X.reshape(Train_X.shape[0] * 10, r, w, 1)
Test_X_spatial = Test_X.reshape(Test_X.shape[0] * 10, r, w, 1)
# Extend Y labels 10 fold, so that all images have labels
Train_Y_spatial = np.repeat(Train_Y, 10, axis=0)
Test_Y_spatial = np.repeat(Test_Y, 10, axis=0)
# Duplicate channel of input image
Train_X_spatial = duplicate_channel(Train_X_spatial)
Test_X_spatial = duplicate_channel(Test_X_spatial)
# print ("Train_X_shape: " + str(np.shape(Train_X_spatial)))
# print ("Train_Y_shape: " + str(np.shape(Train_Y_spatial)))
# print ("Test_X_shape: " + str(np.shape(Test_X_spatial)))
# print ("Test_Y_shape: " + str(np.shape(Test_Y_spatial)))
# print(Train_X_spatial)
##################### Training & Testing #########################
X = Train_X_spatial.reshape(Train_X_spatial.shape[0], 3, r, w)
y = Train_Y_spatial.reshape(Train_Y_spatial.shape[0], 5)
test_X = Test_X_spatial.reshape(Test_X_spatial.shape[0], 3, r, w)
test_y = Test_Y_spatial.reshape(Test_Y_spatial.shape[0], 5)
###### conv weights must be freezed for transfer learning ######
if finetuning_flag == 1:
for layer in vgg_model.layers[:33]:
layer.trainable = False
if train_spatial_flag == 1 and train_temporal_flag == 1:
# trains encoder until fc, train temporal
# Spatial Training
if tensorboard_flag == 1:
vgg_model.fit(X,
y,
batch_size=batch_size,
epochs=spatial_epochs,
shuffle=True,
callbacks=[tbCallBack2])
else:
vgg_model.fit(X,
y,
batch_size=batch_size,
epochs=spatial_epochs,
shuffle=True,
callbacks=[model_checkpoint])
# vgg_model.save_weights(spatial_weights_name)
model = Model(inputs=vgg_model.input,
outputs=vgg_model.layers[35].output)
plot_model(model,
to_file="spatial_module_FULL_TRAINING.png",
show_shapes=True)
# Spatial Encoding
output = model.predict(X, batch_size=batch_size)
features = output.reshape(int(output.shape[0] / 10), 10,
output.shape[1])
# Temporal Training
if tensorboard_flag == 1:
temporal_model.fit(features,
Train_Y,
batch_size=batch_size,
epochs=temporal_epochs,
callbacks=[tbCallBack])
else:
temporal_model.fit(features,
Train_Y,
batch_size=batch_size,
epochs=temporal_epochs,
callbacks=[model_checkpoint_temporal])
# temporal_model.save_weights(temporal_weights_name)
# Testing
output = model.predict(test_X, batch_size=batch_size)
features = output.reshape(int(output.shape[0] / 10), 10,
output.shape[1])
predict = temporal_model.predict_classes(features,
batch_size=batch_size)
elif train_spatial_flag == 1 and train_temporal_flag == 0 and cam_visualizer_flag == 0:
# trains spatial module ONLY, no escape
# Spatial Training
if tensorboard_flag == 1:
vgg_model.fit(X,
y,
batch_size=batch_size,
epochs=spatial_epochs,
shuffle=True,
callbacks=[tbCallBack2])
else:
vgg_model.fit(X,
y,
batch_size=batch_size,
epochs=spatial_epochs,
shuffle=True,
callbacks=[model_checkpoint])
# vgg_model.save_weights(spatial_weights_name)
plot_model(vgg_model,
to_file="spatial_module_ONLY.png",
show_shapes=True)
# Testing
predict = vgg_model.predict(test_X, batch_size=batch_size)
Test_Y_gt = np.repeat(Test_Y_gt, 10, axis=0)
elif train_spatial_flag == 0 and train_temporal_flag == 1:
# trains temporal module ONLY.
# Temporal Training
if tensorboard_flag == 1:
temporal_model.fit(Train_X,
Train_Y,
batch_size=batch_size,
epochs=spatial_epochs,
callbacks=[tbCallBack])
else:
temporal_model.fit(Train_X,
Train_Y,
batch_size=batch_size,
epochs=spatial_epochs,
callbacks=[model_checkpoint_temporal])
# temporal_model.save_weights(temporal_weights_name)
# Testing
predict = temporal_model.predict_classes(Test_X,
batch_size=batch_size)
elif svm_flag == 1 and finetuning_flag == 0:
# no finetuning
X = vgg_model.predict(X, batch_size=batch_size)
y_for_svm = np.argmax(y, axis=1)
svm_classifier.fit(X, y_for_svm)
test_X = vgg_model.predict(test_X, batch_size=batch_size)
predict = svm_classifier.predict(test_X)
Test_Y_gt = np.repeat(Test_Y_gt, 10, axis=0)
elif train_spatial_flag == 1 and train_temporal_flag == 0 and cam_visualizer_flag == 1:
# trains spatial module & CAM ONLY
# Spatial Training
if tensorboard_flag == 1:
vgg_model.fit(X,
y,
batch_size=batch_size,
epochs=spatial_epochs,
shuffle=True,
callbacks=[tbCallBack2])
else:
vgg_model.fit(X,
y,
batch_size=batch_size,
epochs=spatial_epochs,
shuffle=True,
callbacks=[model_checkpoint])
# vgg_model.save_weights(spatial_weights_name)
plot_model(vgg_model,
to_file="spatial_module_CAM_ONLY.png",
show_shapes=True)
# Testing
predict = vgg_model.predict(test_X, batch_size=batch_size)
Test_Y_gt = np.repeat(Test_Y_gt, 10, axis=0)
##############################################################
#################### Confusion Matrix Construction #############
print(predict)
print(Test_Y_gt)
ct = confusion_matrix(Test_Y_gt, predict)
# check the order of the CT
order = np.unique(np.concatenate((predict, Test_Y_gt)))
# create an array to hold the CT for each CV
mat = np.zeros((n_exp, n_exp))
# put the order accordingly, in order to form the overall ConfusionMat
for m in range(len(order)):
for n in range(len(order)):
mat[int(order[m]), int(order[n])] = ct[m, n]
tot_mat = mat + tot_mat
################################################################
#################### cumulative f1 plotting ######################
microAcc = np.trace(tot_mat) / np.sum(tot_mat)
[f1, precision, recall] = fpr(tot_mat, n_exp)
file = open(workplace + 'Classification/' + 'Result/' + '/f1.txt', 'a')
file.write(str(f1) + "\n")
file.close()
##################################################################
################# write each CT of each CV into .txt file #####################
record_scores(workplace, dB, ct, sub, order, tot_mat, n_exp, subjects)
###############################################################################