def main(args):
# Ensure training, testing, and manip are not all turned off
assert (args.train or args.test or args.manip),\
'Cannot have train, test, and manip all set to 0, Nothing to do.'
# Load the training, validation, and testing data
try:
train_list, val_list, test_list = load_data(args.data_root_dir,
args.split_num)
except IndexError:
# Create the training and test splits if not found
split_data(args.data_root_dir, num_splits=4)
train_list, val_list, test_list = load_data(args.data_root_dir,
args.split_num)
# Get image properties from first image. Assume they are all the same.
img_shape = sitk.GetArrayFromImage(
sitk.ReadImage(join(args.data_root_dir, 'imgs',
train_list[0][0]))).shape
net_input_shape = (img_shape[0], img_shape[1], args.slices)
print(net_input_shape)
# Create the model for training/testing/manipulation
model_list = create_model(args=args, input_shape=net_input_shape)
print_summary(model=model_list[0], positions=[.38, .65, .75, 1.])
args.output_name = args.save_prefix +\
'split-' + str(args.split_num) + \
'-batch-' + str(args.batch_size) + \
'_shuff-' + str(args.shuffle_data) + \
'_aug-' + str(args.aug_data) + \
'_loss-' + str(args.loss) + \
'_strid-' + str(args.stride) + \
'_lr-' + str(args.initial_lr) + \
'_recon-' + str(args.recon_wei)
args.time = time
args.check_dir = join(args.data_root_dir, 'saved_models', args.net)
try:
makedirs(args.check_dir)
except FileExistsError:
pass
args.log_dir = join(args.data_root_dir, 'logs', args.net)
try:
makedirs(args.log_dir)
except FileExistsError:
pass
args.tf_log_dir = join(args.log_dir, 'tf_logs')
try:
makedirs(args.tf_log_dir)
except FileExistsError:
pass
args.output_dir = join(args.data_root_dir, 'plots', args.net)
try:
makedirs(args.output_dir)
except FileExistsError:
pass
if args.train:
from train import train
# Run training
train(args, train_list, val_list, model_list[0], net_input_shape)
if args.test:
from test import test
# Run testing
test(args, test_list, model_list, net_input_shape)
def main(args):
#tf.enable_eager_execution()
#sess = K.get_session()
#sess = tf_debug.LocalCLIDebugWrapperSession(sess)
#K.set_session(sess)
# Ensure training, testing, and manip are not all turned off
assert (args.train or args.test or args.manip), 'Cannot have train, test, and manip all set to 0, Nothing to do.'
# Load the training, validation, and testing data
try:
train_list, val_list, test_list = load_data(args.data_root_dir, args.split_num)
except:
# Create the training and test splits if not found
split_data(args.data_root_dir, num_splits=4)
train_list, val_list, test_list = load_data(args.data_root_dir, args.split_num)
# Get image properties from first image. Assume they are all the same.
img_shape = sitk.GetArrayFromImage(sitk.ReadImage(join(args.data_root_dir, 'imgs', train_list[0][0]))).shape
net_input_shape = (img_shape[1], img_shape[2], args.slices)
if args.pytorch:
from capsnet_pytorch import CapsNetBasic, CapsNetR3
model = CapsNetR3() #CapsNetBasic()
else:
# Create the model for training/testing/manipulation
model_list = create_model(args=args, input_shape=net_input_shape)
print_summary(model=model_list[0], positions=[.38, .65, .75, 1.])
args.output_name = 'split-' + str(args.split_num) + '_batch-' + str(args.batch_size) + \
'_shuff-' + str(args.shuffle_data) + '_aug-' + str(args.aug_data) + \
'_loss-' + str(args.loss) + '_slic-' + str(args.slices) + \
'_sub-' + str(args.subsamp) + '_strid-' + str(args.stride) + \
'_lr-' + str(args.initial_lr) + '_recon-' + str(args.recon_wei)
args.time = time
args.check_dir = join(args.data_root_dir,'saved_models', args.net)
try:
makedirs(args.check_dir)
except:
pass
args.log_dir = join(args.data_root_dir,'logs', args.net)
try:
makedirs(args.log_dir)
except:
pass
args.tf_log_dir = join(args.log_dir, 'tf_logs')
try:
makedirs(args.tf_log_dir)
except:
pass
args.output_dir = join(args.data_root_dir, 'plots', args.net)
try:
makedirs(args.output_dir)
except:
pass
if args.pytorch:
if args.train:
from train_pytorch import train
# Run training
train(args, model, train_list, net_input_shape)
#train(args, train_list, val_list, model_list[0], net_input_shape)
else:
if args.train:
from train import train
# Run training
train(args, train_list, val_list, model_list[0], net_input_shape)
if args.test:
from test import test
# Run testing
test(args, test_list, model_list, net_input_shape)
if args.manip:
from manip import manip
# Run manipulation of segcaps
manip(args, test_list, model_list, net_input_shape)
def main(args):
# Ensure training, testing, and manip are not all turned off
assert (args.train or args.test or args.manip), 'Cannot have train, test, and manip all set to 0, Nothing to do.'
# Load the training, validation, and testing data
try:
train_list, val_list, test_list = load_data(args.data_root_dir, args.split_num)
except:
# Create the training and test splits if not found
split_data(args.data_root_dir, num_splits=4)
train_list, val_list, test_list = load_data(args.data_root_dir, args.split_num)
# Get image properties from first image. Assume they are all the same.
img_shape = sitk.GetArrayFromImage(sitk.ReadImage(join(args.data_root_dir, 'imgs', train_list[0][0]))).shape
net_input_shape = (img_shape[1], img_shape[2], args.slices)
# Create the model for training/testing/manipulation
model_list = create_model(args=args, input_shape=net_input_shape)
print_summary(model=model_list[0], positions=[.38, .65, .75, 1.])
args.output_name = 'split-' + str(args.split_num) + '_batch-' + str(args.batch_size) + \
'_shuff-' + str(args.shuffle_data) + '_aug-' + str(args.aug_data) + \
'_loss-' + str(args.loss) + '_slic-' + str(args.slices) + \
'_sub-' + str(args.subsamp) + '_strid-' + str(args.stride) + \
'_lr-' + str(args.initial_lr) + '_recon-' + str(args.recon_wei)
args.time = time
args.check_dir = join(args.data_root_dir,'saved_models', args.net)
try:
makedirs(args.check_dir)
except:
pass
args.log_dir = join(args.data_root_dir,'logs', args.net)
try:
makedirs(args.log_dir)
except:
pass
args.tf_log_dir = join(args.log_dir, 'tf_logs')
try:
makedirs(args.tf_log_dir)
except:
pass
args.output_dir = join(args.data_root_dir, 'plots', args.net)
try:
makedirs(args.output_dir)
except:
pass
if args.train:
from train import train
# Run training
train(args, train_list, val_list, model_list[0], net_input_shape)
if args.test:
from test import test
# Run testing
test(args, test_list, model_list, net_input_shape)
if args.manip:
from manip import manip
# Run manipulation of segcaps
manip(args, test_list, model_list, net_input_shape)
def main(args):
image_shape = (128, 128)
# Ensure training, testing, and manip are not all turned off
assert (args.train or args.test or args.manip), 'Cannot have train, test, and manip all set to 0, Nothing to do.'
# Load the training, validation, and testing data
try:
train_list, val_list, test_list = load_data(args.data_root_dir, args.split_num)
except:
# Create the training and test splits if not found
split_data(args.data_root_dir, num_splits=4)
train_list, val_list, test_list = load_data(args.data_root_dir, args.split_num)
# Get image properties from first image. Assume they are all the same.
im = cv2.imread(join(args.data_root_dir, 'imgs', train_list[0][0]))
im = cv2.resize(im, image_shape)
gray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
gray = np.reshape(gray, (1, gray.shape[0], gray.shape[1]))
img_shape = gray.shape
net_input_shape = (img_shape[1], img_shape[2], args.slices)
# Create the model for training/testing/manipulation
model_list = create_model(args=args, input_shape=net_input_shape, class_num=6)
print_summary(model=model_list[0], positions=[.38, .65, .75, 1.])
args.output_name = 'split-' + str(args.split_num) + '_batch-' + str(args.batch_size) + \
'_shuff-' + str(args.shuffle_data) + '_aug-' + str(args.aug_data) + \
'_loss-' + str(args.loss) + '_slic-' + str(args.slices) + \
'_sub-' + str(args.subsamp) + '_strid-' + str(args.stride) + \
'_lr-' + str(args.initial_lr) + '_recon-' + str(args.recon_wei)
args.time = time
args.check_dir = join(args.data_root_dir, 'saved_models', args.net)
try:
makedirs(args.check_dir)
except:
pass
args.log_dir = join(args.data_root_dir, 'logs', args.net)
try:
makedirs(args.log_dir)
except:
pass
args.tf_log_dir = join(args.log_dir, 'tf_logs')
try:
makedirs(args.tf_log_dir)
except:
pass
args.output_dir = join(args.data_root_dir, 'plots', args.net)
try:
makedirs(args.output_dir)
except:
pass
if args.train:
print('training')
from train import train
# Run training
while ([] in train_list):
train_list.remove([])
CUDA_VISIBLE_DEVICES = 1
train(args, train_list, val_list, model_list[0], net_input_shape)
if args.test:
from test import test
# Run testing
while ([] in test_list):
test_list.remove([])
for i in range(39,40):
args.weights_path = f'saved_models/{args.net}/model' + str(i) + '.hdf5'
test(args, test_list, model_list, net_input_shape, i)
if args.manip:
from manip import manip
# Run manipulation of segcaps
manip(args, test_list, model_list, net_input_shape)
def main(args):
# Ensure training, testing, and manip are not all turned off
assert (args.train or args.test or args.manip), 'Cannot have train, test, and manip all set to 0, Nothing to do.'
# Load the training, validation, and testing data
try:
train_list, val_list, test_list = load_data(args.data_root_dir, args.split_num)
except:
# Create the training and test splits if not found
split_data(args.data_root_dir, num_splits=4)
train_list, val_list, test_list = load_data(args.data_root_dir, args.split_num)
# Get image properties from first image. Assume they are all the same.
#img_shape = sitk.GetArrayFromImage(sitk.ReadImage(join(args.data_root_dir, 'imgs', train_list[0][0]))).shape
im=cv2.imread(join(args.data_root_dir, 'imgs', train_list[0][0]))
gray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
#im = cv2.imread(join(img_path, img_name), -1)
#gray = im
gray=np.reshape(gray, (1,gray.shape[0],gray.shape[1]))
img_shape = gray.shape
net_input_shape = (512, 512, args.slices)
# Create the model for training/testing/manipulation
model_list = create_model(args=args, input_shape=net_input_shape)
print_summary(model=model_list[0], positions=[.38, .65, .75, 1.])
model_list[0].load_weights('liver_data3/saved_models_original/segcapsr3/model5.hdf5')
#print('model20')
#model_list[0].load_weights('C:/Users/212673708/Documents/TAU/semesterB/DeepLearningInMedicalImaging/modelLiver.hdf5')
args.output_name = 'split-' + str(args.split_num) + '_batch-' + str(args.batch_size) + \
'_shuff-' + str(args.shuffle_data) + '_aug-' + str(args.aug_data) + \
'_loss-' + str(args.loss) + '_slic-' + str(args.slices) + \
'_sub-' + str(args.subsamp) + '_strid-' + str(args.stride) + \
'_lr-' + str(args.initial_lr) + '_recon-' + str(args.recon_wei)
args.time = time
args.check_dir = join(args.data_root_dir,'saved_models', args.net)
try:
makedirs(args.check_dir)
except:
pass
args.log_dir = join(args.data_root_dir,'logs', args.net)
try:
makedirs(args.log_dir)
except:
pass
args.tf_log_dir = join(args.log_dir, 'tf_logs')
try:
makedirs(args.tf_log_dir)
except:
pass
args.output_dir = join(args.data_root_dir, 'plots', args.net)
try:
makedirs(args.output_dir)
except:
pass
if args.train:
print('training')
from train import train
# Run training
while ([] in train_list):
train_list.remove([])
CUDA_VISIBLE_DEVICES = 1
train(args, train_list, val_list, model_list[0], net_input_shape)
if args.test:
from test import test
# Run testing
while ([] in test_list):
test_list.remove([])
i=5
args.weights_path = 'saved_models_original/segcapsr3/model'+str(i)+'.hdf5'
test(args, test_list, model_list, net_input_shape,i)
if args.manip:
from manip import manip
# Run manipulation of segcaps
manip(args, test_list, model_list, net_input_shape)