def main():
args = get_args()
input_path1 = args.input1
input_path2 = args.input2
db_name = args.db
batch_size = args.batch_size
nb_epochs = args.nb_epochs
netType = args.netType
logging.debug("Loading training data...")
image1, age1, image_size = load_data_npz(input_path1)
logging.debug("Loading testing data...")
image2, age2, image_size = load_data_npz(input_path2)
start_decay_epoch = [30, 60]
optMethod = Adam()
if netType == 1:
model_type = 'MobileNet'
alpha = 0.25
model = TYY_MobileNet_reg(image_size, alpha)()
save_name = 'mobilenet_reg_%s_%d' % (alpha, image_size)
model.compile(optimizer=optMethod,
loss=["mae"],
metrics={'pred_a': 'mae'})
elif netType == 2:
model_type = 'MobileNet'
alpha = 0.5
model = TYY_MobileNet_reg(image_size, alpha)()
save_name = 'mobilenet_reg_%s_%d' % (alpha, image_size)
model.compile(optimizer=optMethod,
loss=["mae"],
metrics={'pred_a': 'mae'})
elif netType == 3:
model_type = 'DenseNet'
N_densenet = 3
depth_densenet = 3 * N_densenet + 4
model = TYY_DenseNet_reg(image_size, depth_densenet)()
save_name = 'densenet_reg_%d_%d' % (depth_densenet, image_size)
model.compile(optimizer=optMethod,
loss=["mae"],
metrics={'pred_a': 'mae'})
elif netType == 4:
model_type = 'DenseNet'
N_densenet = 5
depth_densenet = 3 * N_densenet + 4
model = TYY_DenseNet_reg(image_size, depth_densenet)()
save_name = 'densenet_reg_%d_%d' % (depth_densenet, image_size)
model.compile(optimizer=optMethod,
loss=["mae"],
metrics={'pred_a': 'mae'})
if db_name == "meagaage":
weight_file = "../pre-trained/wiki/" + save_name + "/" + save_name + ".h5"
model.load_weights(weight_file)
logging.debug("Model summary...")
model.count_params()
model.summary()
logging.debug("Saving model...")
mk_dir(db_name + "_models")
mk_dir(db_name + "_models/" + model_type + "/")
mk_dir(db_name + "_models/" + model_type + "/batch_size_%d/" %
(batch_size))
mk_dir(db_name + "_models/" + model_type + "/batch_size_%d/" %
(batch_size) + save_name)
mk_dir(db_name + "_checkpoints")
mk_dir(db_name + "_checkpoints/" + model_type)
mk_dir(db_name + "_checkpoints/" + model_type + "/batch_size_%d/" %
(batch_size))
plot_model(model,
to_file=db_name + "_models/" + model_type + "/batch_size_%d/" %
(batch_size) + save_name + "/" + save_name + ".png")
with open(
os.path.join(
db_name + "_models/" + model_type + "/batch_size_%d/" %
(batch_size) + save_name, save_name + '.json'), "w") as f:
f.write(model.to_json())
decaylearningrate = TYY_callbacks.DecayLearningRate(start_decay_epoch)
callbacks = [
ModelCheckpoint(db_name + "_checkpoints/" + model_type +
"/batch_size_%d/" % (batch_size) +
"weights.{epoch:02d}-{val_loss:.2f}.hdf5",
monitor="val_loss",
verbose=1,
save_best_only=True,
mode="auto"), decaylearningrate
]
logging.debug("Running training...")
data_num = len(image1) + len(image2)
indexes1 = np.arange(len(image1))
indexes2 = np.arange(len(image2))
np.random.shuffle(indexes1)
np.random.shuffle(indexes2)
x_train = image1[indexes1]
x_test = image2[indexes2]
y_train_a = age1[indexes1]
y_test_a = age2[indexes2]
train_num = len(image1)
hist = model.fit_generator(generator=data_generator_reg(
X=x_train, Y=y_train_a, batch_size=batch_size),
steps_per_epoch=train_num // batch_size,
validation_data=(x_test, [y_test_a]),
epochs=nb_epochs,
verbose=1,
callbacks=callbacks)
logging.debug("Saving weights...")
model.save_weights(os.path.join(
db_name + "_models/" + model_type + "/batch_size_%d/" % (batch_size) +
save_name, save_name + '.h5'),
overwrite=True)
pd.DataFrame(hist.history).to_hdf(
os.path.join(
db_name + "_models/" + model_type + "/batch_size_%d/" %
(batch_size) + save_name, 'history_' + save_name + '.h5'),
"history")
def main():
args = get_args()
input_path = args.input
db_name = args.db
batch_size = args.batch_size
nb_epochs = args.nb_epochs
validation_split = args.validation_split
netType1 = args.netType1
netType2 = args.netType2
logging.debug("Loading data...")
image, gender, age, image_size = load_data_npz(input_path)
x_data = image
y_data_a = age
start_decay_epoch = [30,60]
optMethod = Adam()
stage_num = [3,3,3]
lambda_local = 0.25*(netType1%5)
lambda_d = 0.25*(netType2%5)
model = SSR_net(image_size,stage_num, lambda_local, lambda_d)()
save_name = 'ssrnet_%d_%d_%d_%d_%s_%s' % (stage_num[0],stage_num[1],stage_num[2], image_size, lambda_local, lambda_d)
model.compile(optimizer=optMethod, loss=["mae"], metrics={'pred_a':'mae'})
if db_name == "wiki":
weight_file = f'imdb_models/{save_name}/{save_name}.h5'
if os.path.isfile(weight_file): # error out if file not exist
print("previous weight loading...")
model.load_weights(weight_file)
elif db_name == "morph":
weight_file = f'wiki_models/{save_name}/{save_name}.h5'
if os.path.isfile(weight_file):
print("previous weight loading...")
model.load_weights(weight_file)
logging.debug("Model summary...")
model.count_params()
model.summary()
logging.debug("Saving model...")
mk_dir(db_name+"_models")
mk_dir(db_name+"_models/"+save_name)
mk_dir(db_name+"_checkpoints")
plot_model(model, to_file=db_name+"_age_models/"+save_name+"/"+save_name+".png")
with open(os.path.join(db_name+"_age_models/"+save_name, save_name+'.json'), "w") as f:
f.write(model.to_json())
decaylearningrate = TYY_callbacks.DecayLearningRate(start_decay_epoch)
callbacks = [ModelCheckpoint(db_name+"_checkpoints/weights.{epoch:02d}-{val_loss:.2f}.hdf5",
monitor="val_loss",
verbose=1,
save_best_only=True,
mode="auto"), decaylearningrate
]
logging.debug("Running training...")
data_num = len(x_data)
indexes = np.arange(data_num)
np.random.shuffle(indexes)
x_data = x_data[indexes]
y_data_a = y_data_a[indexes]
train_num = int(data_num * (1 - validation_split))
x_train = x_data[:train_num]
x_test = x_data[train_num:]
y_train_a = y_data_a[:train_num]
y_test_a = y_data_a[train_num:]
hist = model.fit_generator(generator=data_generator_reg(X=x_train, Y=y_train_a, batch_size=batch_size),
steps_per_epoch=train_num // batch_size,
validation_data=(x_test, [y_test_a]),
epochs=nb_epochs, verbose=1,
callbacks=callbacks)
logging.debug("Saving weights...")
model.save_weights(os.path.join(db_name+"_models/"+save_name, save_name+'.h5'), overwrite=True)
pd.DataFrame(hist.history).to_hdf(os.path.join(db_name+"_models/"+save_name, 'history_'+save_name+'.h5'), "history")
'''''' '''''' '''''' '''''' '''''' '''''' '''''' '''
file name
''' '''''' '''''' '''''' '''''' '''''' '''''' ''''''
test_file = sys.argv[1]
netType = int(sys.argv[2])
logging.debug("Loading testing data...")
image2, age2, image_size = load_data_npz(test_file)
if netType == 3:
N_densenet = 3
depth_densenet = 3 * N_densenet + 4
model_file = 'megaage_models/DenseNet/batch_size_50/densenet_reg_%d_64/densenet_reg_%d_64.h5' % (
depth_densenet, depth_densenet)
model = TYY_DenseNet_reg(image_size, depth_densenet)()
mk_dir('Results_csv')
save_name = 'Results_csv/densenet_reg_%d_%d.csv' % (depth_densenet,
image_size)
elif netType == 4:
N_densenet = 5
depth_densenet = 3 * N_densenet + 4
model_file = 'megaage_models/DenseNet/batch_size_50/densenet_reg_%d_64/densenet_reg_%d_64.h5' % (
depth_densenet, depth_densenet)
model = TYY_DenseNet_reg(image_size, depth_densenet)()
mk_dir('Results_csv')
save_name = 'Results_csv/densenet_reg_%d_%d.csv' % (depth_densenet,
image_size)
'''''' '''''' '''''' '''''' '''''' '''''' '''''' '''
load data
''' '''''' '''''' '''''' '''''' '''''' '''''' ''''''
def main():
args = get_args()
input_path = args.input
db_name = args.db
batch_size = args.batch_size
nb_epochs = args.nb_epochs
validation_split = args.validation_split
netType = args.netType
logging.debug("Loading data...")
image, gender, age, image_size = load_data_npz(input_path)
x_data = image
y_data_a = age
start_decay_epoch = [30,60]
optMethod = Adam()
if netType == 1:
alpha = 0.25
model = TYY_MobileNet_reg(image_size,alpha)()
save_name = 'mobilenet_reg_%s_%d' % (alpha, image_size)
model.compile(optimizer=optMethod, loss=["mae"], metrics={'pred_a':'mae'})
elif netType == 2:
alpha = 0.5
model = TYY_MobileNet_reg(image_size,alpha)()
save_name = 'mobilenet_reg_%s_%d' % (alpha, image_size)
model.compile(optimizer=optMethod, loss=["mae"], metrics={'pred_a':'mae'})
elif netType == 3:
N_densenet = 3
depth_densenet = 3*N_densenet+4
model = TYY_DenseNet_reg(image_size,depth_densenet)()
save_name = 'densenet_reg_%d_%d' % (depth_densenet, image_size)
model.compile(optimizer=optMethod, loss=["mae"], metrics={'pred_a':'mae'})
elif netType == 4:
N_densenet = 5
depth_densenet = 3*N_densenet+4
model = TYY_DenseNet_reg(image_size,depth_densenet)()
save_name = 'densenet_reg_%d_%d' % (depth_densenet, image_size)
model.compile(optimizer=optMethod, loss=["mae"], metrics={'pred_a':'mae'})
if db_name == "wiki":
weight_file = "imdb_models/"+save_name+"/"+save_name+".h5"
model.load_weights(weight_file)
#start_decay_epoch = range(0,nb_epochs,30)
elif db_name == "morph":
weight_file = "wiki_models/"+save_name+"/"+save_name+".h5"
model.load_weights(weight_file)
logging.debug("Model summary...")
model.count_params()
model.summary()
logging.debug("Saving model...")
mk_dir(db_name+"_models")
mk_dir(db_name+"_models/"+save_name)
mk_dir(db_name+"_checkpoints")
plot_model(model, to_file=db_name+"_models/"+save_name+"/"+save_name+".png")
with open(os.path.join(db_name+"_models/"+save_name, save_name+'.json'), "w") as f:
f.write(model.to_json())
decaylearningrate = TYY_callbacks.DecayLearningRate(start_decay_epoch)
callbacks = [ModelCheckpoint(db_name+"_checkpoints/weights.{epoch:02d}-{val_loss:.2f}.hdf5",
monitor="val_loss",
verbose=1,
save_best_only=True,
mode="auto"), decaylearningrate
]
logging.debug("Running training...")
data_num = len(x_data)
indexes = np.arange(data_num)
np.random.shuffle(indexes)
x_data = x_data[indexes]
y_data_a = y_data_a[indexes]
train_num = int(data_num * (1 - validation_split))
x_train = x_data[:train_num]
x_test = x_data[train_num:]
y_train_a = y_data_a[:train_num]
y_test_a = y_data_a[train_num:]
hist = model.fit_generator(generator=data_generator_reg(X=x_train, Y=y_train_a, batch_size=batch_size),
steps_per_epoch=train_num // batch_size,
validation_data=(x_test, [y_test_a]),
epochs=nb_epochs, verbose=1,
callbacks=callbacks)
logging.debug("Saving weights...")
model.save_weights(os.path.join(db_name+"_models/"+save_name, save_name+'.h5'), overwrite=True)
pd.DataFrame(hist.history).to_hdf(os.path.join(db_name+"_models/"+save_name, 'history_'+save_name+'.h5'), "history")
def main():
args = get_args()
input_path = args.input
batch_size = args.batch_size
nb_epochs = args.nb_epochs
validation_split = args.validation_split
logging.debug("Loading data...")
image, gender, age, image_size = load_MORPH_data_npz(input_path)
x_data = image
y_data_a = age
netType = 3
start_decay_epoch = [30, 60]
if netType == 1:
alpha = 1
model = TYY_MobileNet_reg(image_size, alpha)()
save_name = 'mobilenet_reg_%s_%d' % (alpha, image_size)
model.compile(optimizer=Adam(),
loss=["mae"],
metrics={'pred_a': 'mae'})
elif netType == 2:
N_densenet = 5
depth_densenet = 3 * N_densenet + 4
model = TYY_DenseNet_reg(image_size, depth_densenet)()
save_name = 'densenet_reg_%d_%d' % (depth_densenet, image_size)
model.compile(optimizer=Adam(),
loss=["mae"],
metrics={'pred_a': 'mae'})
elif netType == 3:
num_neu = 25
alpha = 0.25
model = TYY_MobileNet_dex(image_size, alpha, num_neu)()
save_name = 'mobilenet_dex_%s_%d_%d' % (alpha, image_size, num_neu)
model.compile(optimizer=Adam(),
loss=["categorical_crossentropy", "mae"],
loss_weights=[1, 0],
metrics={
'pred_a_softmax': 'accuracy',
'pred_a': 'mae'
})
elif netType == 4:
num_neu = 25
N_densenet = 3
depth_densenet = 3 * N_densenet + 4
model = TYY_DenseNet_dex(image_size, depth_densenet, num_neu)()
save_name = 'densenet_dex_%d_%d_%d' % (depth_densenet, image_size,
num_neu)
model.compile(optimizer=Adam(),
loss=["categorical_crossentropy", "mae"],
loss_weights=[1, 0],
metrics={
'pred_a_softmax': 'accuracy',
'pred_a': 'mae'
})
logging.debug("Model summary...")
model.count_params()
model.summary()
logging.debug("Saving model...")
mk_dir("models")
with open(os.path.join("models", save_name + '.json'), "w") as f:
f.write(model.to_json())
mk_dir("checkpoints")
decaylearningrate = TYY_callbacks.DecayLearningRate(start_decay_epoch)
callbacks = [
ModelCheckpoint("checkpoints/weights.{epoch:02d}-{val_loss:.2f}.hdf5",
monitor="val_loss",
verbose=1,
save_best_only=True,
mode="auto"), decaylearningrate
]
logging.debug("Running training...")
data_num = len(x_data)
indexes = np.arange(data_num)
np.random.shuffle(indexes)
x_data = x_data[indexes]
y_data_a = y_data_a[indexes]
train_num = int(data_num * (1 - validation_split))
x_train = x_data[:train_num]
x_test = x_data[train_num:]
y_train_a = y_data_a[:train_num]
y_test_a = y_data_a[train_num:]
if netType == 3 or netType == 4:
age_bins = np.linspace(
0, 100, num_neu + 1
) #(Important!!!) Remember to add 1 to turn bins number into index number
y_train_a_class = np.digitize(
y_train_a, age_bins
) - 1 #(Important!!!) Since np.digitize output start from 1, we want it start from zero, so we substract 1.
y_train_a_class = np_utils.to_categorical(y_train_a_class, num_neu)
y_test_a_class = np.digitize(
y_test_a, age_bins
) - 1 #(Important!!!) Since np.digitize output start from 1, we want it start from zero, so we substract 1.
y_test_a_class = np_utils.to_categorical(y_test_a_class, num_neu)
hist = model.fit(x_train, [y_train_a_class, y_train_a],
batch_size=batch_size,
epochs=nb_epochs,
callbacks=callbacks,
validation_data=(x_test, [y_test_a_class, y_test_a]))
else:
hist = model.fit(x_train, [y_train_a],
batch_size=batch_size,
epochs=nb_epochs,
callbacks=callbacks,
validation_data=(x_test, [y_test_a]))
logging.debug("Saving weights...")
model.save_weights(os.path.join("models", save_name + '.h5'),
overwrite=True)
pd.DataFrame(hist.history).to_hdf(
os.path.join("models", 'history_' + save_name + '.h5'), "history")
def main():
args = get_args()
input_path1 = args.input1
input_path2 = args.input2
db_name = args.db
batch_size = args.batch_size
nb_epochs = args.nb_epochs
netType1 = args.netType1
netType2 = args.netType2
logging.debug("Loading training data...")
image1, age1, image_size = load_data_npz(input_path1)
logging.debug("Loading testing data...")
image2, age2, image_size = load_data_npz(input_path2)
start_decay_epoch = [30, 60]
optMethod = Adam()
stage_num = [3, 3, 3]
lambda_local = 0.25 * (netType1 % 5)
lambda_d = 0.25 * (netType2 % 5)
model = SSR_net(image_size, stage_num, lambda_local, lambda_d)()
save_name = 'ssrnet_%d_%d_%d_%d_%s_%s' % (stage_num[0], stage_num[1],
stage_num[2], image_size,
lambda_local, lambda_d)
model.compile(optimizer=optMethod, loss=["mae"], metrics={'pred_a': 'mae'})
if db_name == "megaage":
weight_file = "./pre-trained/wiki/ssrnet_3_3_3_64_1.0_1.0/ssrnet_3_3_3_64_1.0_1.0.h5"
#weight_file = "./pre-trained/imdb/ssrnet_3_3_3_64_1.0_1.0/ssrnet_3_3_3_64_1.0_1.0.h5"
model.load_weights(weight_file)
logging.debug("Model summary...")
model.count_params()
model.summary()
logging.debug("Saving model...")
mk_dir(db_name + "_models")
mk_dir(db_name + "_models/batch_size_%d/" % (batch_size))
mk_dir(db_name + "_models/batch_size_%d/" % (batch_size) + save_name)
mk_dir(db_name + "_checkpoints")
mk_dir(db_name + "_checkpoints/batch_size_%d/" % (batch_size))
plot_model(model,
to_file=db_name + "_models/batch_size_%d/" % (batch_size) +
save_name + "/" + save_name + ".png")
with open(
os.path.join(
db_name + "_models/batch_size_%d/" % (batch_size) + save_name,
save_name + '.json'), "w") as f:
f.write(model.to_json())
decaylearningrate = TYY_callbacks.DecayLearningRate(start_decay_epoch)
callbacks = [
ModelCheckpoint(db_name + "_checkpoints/batch_size_%d/" %
(batch_size) +
"weights.{epoch:02d}-{val_loss:.2f}.hdf5",
monitor="val_loss",
verbose=1,
save_best_only=True,
mode="auto"), decaylearningrate
]
logging.debug("Running training...")
data_num = len(image1) + len(image2)
indexes1 = np.arange(len(image1))
indexes2 = np.arange(len(image2))
np.random.shuffle(indexes1)
np.random.shuffle(indexes2)
x_train = image1[indexes1]
x_test = image2[indexes2]
y_train_a = age1[indexes1]
y_test_a = age2[indexes2]
train_num = len(image1)
hist = model.fit_generator(generator=data_generator_reg(
X=x_train, Y=y_train_a, batch_size=batch_size),
steps_per_epoch=train_num // batch_size,
validation_data=(x_test, [y_test_a]),
epochs=nb_epochs,
verbose=1,
callbacks=callbacks)
logging.debug("Saving weights...")
model.save_weights(os.path.join(
db_name + "_models/batch_size_%d/" % (batch_size) + save_name,
save_name + '.h5'),
overwrite=True)
pd.DataFrame(hist.history).to_hdf(
os.path.join(
db_name + "_models/batch_size_%d/" % (batch_size) + save_name,
'history_' + save_name + '.h5'), "history")