def main(args=None):
imed_utils.init_ivadomed()
parser = get_parser()
args = imed_utils.get_arguments(parser, args)
extract_mid_slice_and_convert_coordinates_to_heatmaps(path=args.path,
suffix=args.suffix,
aim=args.aim)
def main(args=None):
imed_utils.init_ivadomed()
parser = get_parser()
args = imed_utils.get_arguments(parser, args)
df = pd.read_csv(args.dataframe)
compute_statistics(df, int(args.n_iterations), bool(args.run_test),
args.out)
def main():
init_ivadomed()
parser = get_parser()
args = parser.parse_args()
# Run script
extract_small_dataset(args.input, args.output, int(args.number), args.contrasts.split(","),
bool(int(args.derivatives)), int(args.seed))
def main():
init_ivadomed()
parser = get_parser()
args = parser.parse_args()
# Run automate training
visualize_and_compare_models(args.ofolders, args.metric, args.metadata)
def main(args=None):
imed_utils.init_ivadomed()
parser = get_parser()
args = imed_utils.get_arguments(parser, args)
run_visualization(input=args.input,
config=args.config,
number=int(args.number),
output=args.output,
roi=args.roi)
def main():
init_ivadomed()
parser = get_parser()
args = parser.parse_args()
df = pd.read_csv(args.dataframe)
# Compute statistics
compute_statistics(df, int(args.n_iterations), bool(args.run_test),
args.out)
def main():
imed_utils.init_ivadomed()
parser = get_parser()
args = parser.parse_args()
bids_path = args.path
suffix = args.suffix
aim = args.aim
# Run Script
extract_mid_slice_and_convert_coordinates_to_heatmaps(bids_path, suffix, aim)
def main(args=None):
imed_utils.init_ivadomed()
parser = get_parser()
args = imed_utils.get_arguments(parser, args)
fname_model = args.model
dimension = int(args.dimension)
gpu_id = str(args.gpu_id)
n_channels = args.n_channels
convert_pytorch_to_onnx(fname_model, dimension, n_channels, gpu_id)
def main():
imed_utils.init_ivadomed()
parser = get_parser()
args = parser.parse_args()
fname_model = args.model
dimension = int(args.dimension)
gpu = str(args.gpu)
# Run Script
convert_pytorch_to_onnx(fname_model, dimension, gpu)
def main(args=None):
imed_utils.init_ivadomed()
parser = get_parser()
args = imed_utils.get_arguments(parser, args)
y_lim_loss = [int(y) for y in args.ylim_loss.split(',')
] if args.ylim_loss else None
run_plot_training_curves(input_folder=args.input,
output_folder=args.output,
multiple_training=args.multiple,
y_lim_loss=y_lim_loss)
def main(args=None):
imed_utils.init_ivadomed()
parser = get_parser()
args = imed_utils.get_arguments(parser, args)
if args.contrasts is not None:
contrast_list = args.contrasts.split(",")
else:
contrast_list = None
extract_small_dataset(args.input, args.output, int(args.number), contrast_list,
bool(int(args.derivatives)), int(args.seed))
def main():
imed_utils.init_ivadomed()
parser = get_parser()
args = parser.parse_args()
input = args.input
config = args.config
number = int(args.number)
output = args.output
roi = args.roi
# Run script
run_visualization(input, config, number, output, roi)
def main():
init_ivadomed()
parser = get_parser()
args = parser.parse_args()
# Get thr increment if available
thr_increment = args.thr_increment if args.thr_increment else None
# Run automate training
automate_training(args.config, args.params, bool(args.fixed_split), bool(args.all_combin), int(args.n_iterations),
bool(args.run_test), args.all_logs, thr_increment)
def main():
init_ivadomed()
parser = get_parser()
args = parser.parse_args()
input_folder = args.input
multiple = args.multiple
output_folder = args.output
y_lim_loss = [int(y) for y in args.ylim_loss.split(',')
] if args.ylim_loss else None
# Run script
run_plot_training_curves(input_folder, output_folder, multiple, y_lim_loss)
def run_main():
imed_utils.init_ivadomed()
parser = get_parser()
args = parser.parse_args()
# Get context from configuration file
path_config_file = args.config
context = imed_config_manager.ConfigurationManager(
path_config_file).get_config()
# Run command
run_command(
context=context,
n_gif=args.gif if args.gif is not None else 0,
thr_increment=args.thr_increment if args.thr_increment else None,
resume_training=bool(args.resume_training))
def main(args=None):
imed_utils.init_ivadomed()
parser = get_parser()
args = imed_utils.get_arguments(parser, args)
thr_increment = args.thr_increment if args.thr_increment else None
automate_training(
file_config=args.config,
file_config_hyper=args.config_hyper,
fixed_split=bool(args.fixed_split),
all_combin=bool(args.all_combin),
path_data=args.path_data if args.path_data is not None else None,
n_iterations=int(args.n_iterations),
run_test=bool(args.run_test),
all_logs=args.all_logs,
thr_increment=thr_increment,
multi_params=bool(args.multi_params),
output_dir=args.output_dir)
def main(args=None):
imed_utils.init_ivadomed()
# Dictionary containing list of URLs for data names.
# Mirror servers are listed in order of decreasing priority.
# If exists, favour release artifact straight from github
parser = get_parser()
arguments = imed_utils.get_arguments(parser, args)
data_name = arguments.d
if arguments.output is None:
dest_folder = os.path.join(os.path.abspath(os.curdir), data_name)
else:
dest_folder = arguments.output
url = DICT_URL[data_name]["url"]
install_data(url, dest_folder, keep=bool(arguments.keep))
return 0
def run_main():
imed_utils.init_ivadomed()
parser = get_parser()
args = parser.parse_args()
# Get context from configuration file
path_config_file = args.config
if not os.path.isfile(path_config_file) or not path_config_file.endswith(
'.json'):
print(
"\nERROR: The provided configuration file path (.json) is invalid: {}\n"
.format(path_config_file))
return
with open(path_config_file, "r") as fhandle:
context = json.load(fhandle)
# Run command
run_command(
context=context,
n_gif=args.gif if args.gif is not None else 0,
thr_increment=args.thr_increment if args.thr_increment else None,
resume_training=bool(args.resume_training))
import sys
import os
import shutil
from ivadomed.utils import init_ivadomed, __ivadomed_dir__
from ivadomed.scripts import download_data as ivadomed_download_data
__test_dir__ = os.path.join(__ivadomed_dir__, 'testing/unit_tests')
__data_testing_dir_ref__ = "data_testing"
__tmp_dir__ = "tmp"
__data_testing_dir__ = os.path.join(__tmp_dir__, __data_testing_dir_ref__)
init_ivadomed()
class bcolors(object):
"""Class for different colours."""
normal = '\033[0m'
red = '\033[91m'
green = '\033[92m'
yellow = '\033[93m'
blue = '\033[94m'
magenta = '\033[95m'
cyan = '\033[96m'
bold = '\033[1m'
underline = '\033[4m'
def printv(string, verbose=1, type='normal'):
"""Print color-coded messages, depending on verbose status.
