def __init__(self, base_path, print_to_screen=True, active_file=None,
overwrite_existing=False, append_existing=False,
print_calling_method=True, no_sub_folder=False,
log_prefix=""):
self.base_path = os.path.abspath(base_path)
if not no_sub_folder:
self.path = os.path.join(self.base_path, "logs")
else:
self.path = self.base_path
create_folders([self.path])
if overwrite_existing and append_existing:
raise ValueError("Cannot set both 'overwrite_existing' and "
"'append_existing' to True.")
self.overwrite_existing = overwrite_existing
self.append_existing = append_existing
self._enabled = True
# Get built in print function
# (if overwritten globally, Logger still maintains a reference to the
# true print function)
self.print_f = __builtins__["print"]
# Print options
self.separator = "-" * 80
self.print_to_screen = print_to_screen
self.print_calling_method = print_calling_method
# Set paths to log files
self.log_files = {}
self.currently_logging = {}
self.prefix = "" if log_prefix is None else str(log_prefix)
self.active_log_file = active_file or "log"
# For using the logger from multiple threads
self.lock = Lock()
def run_sub_experiment(split_dir, out_dir, script, hparams, no_hparams, GPUs,
GPU_queue, lock, logger):
# Create sub-directory
split = os.path.split(split_dir)[-1]
out_dir = os.path.join(out_dir, split)
out_hparams = os.path.join(out_dir, "train_hparams.yaml")
create_folders(out_dir)
# Get list of commands
commands = parse_script(script, GPUs)
# Move hparams and script files into folder
if not no_hparams:
copy_yaml_and_set_data_dirs(in_path=hparams,
out_path=out_hparams,
data_dir=split_dir)
# Change directory and file permissions
os.chdir(out_dir)
# Log
lock.acquire()
s = "[*] Running experiment: %s" % split
logger("\n%s\n%s" % ("-" * len(s), s))
logger("Data dir:", split_dir)
logger("Out dir:", out_dir)
logger("Using GPUs:", GPUs)
logger("\nRunning commands:")
for i, command in enumerate(commands):
logger(" %i) %s" % (i + 1, " ".join(command)))
logger("-" * len(s))
lock.release()
# Run the commands
run_next_command = True
for command in commands:
if not run_next_command:
break
lock.acquire()
logger("[%s - STARTING] %s" % (split, " ".join(command)))
lock.release()
p = subprocess.Popen(command,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
_, err = p.communicate()
rc = p.returncode
lock.acquire()
if rc != 0:
logger("[%s - ERROR - Exit code %i] %s" %
(split, rc, " ".join(command)))
logger("\n----- START error message -----\n%s\n"
"----- END error message -----\n" % err.decode("utf-8"))
run_next_command = False
else:
logger("[%s - FINISHED] %s" % (split, " ".join(command)))
lock.release()
# Add the GPUs back into the queue
GPU_queue.put(GPUs)
def entry_func(args=None):
parser = get_parser()
args = vars(parser.parse_args(args))
# Get arguments
project_folder = os.path.abspath(args["project_folder"])
copy_weights = args["copy_weights"]
weights = os.path.abspath(args["weights_file"]
or get_best_model(project_folder + "/model"))
out_dir = os.path.join(project_folder, args["out_dir"])
# Get main hyperparamter file and check if correct modelt ype
hparams = YAMLHParams(project_folder + "/train_hparams.yaml", no_log=True)
tasks = hparams.get("tasks", False)
if not tasks:
print("[ERROR] Project must be of type 'MultiTask'.")
sys.exit(0)
# Branch out each sub-task
create_folders(out_dir)
for name, hparams_file in zip(tasks["task_names"], tasks["hparam_files"]):
print("\n[*] Branching task %s" % name)
# Reload the hparams in each iteration as we overwrite fields each time
hparams = YAMLHParams(project_folder + "/train_hparams.yaml",
no_log=False)
# Get task specific parameters
task_hparams = YAMLHParams(project_folder + "/%s" % hparams_file)
branch(task_name=name,
out_dir=os.path.join(out_dir, name),
task_hparams=task_hparams,
task_hparams_file=hparams_file,
shared_hparams=hparams,
weights=weights,
copy_weights=copy_weights,
views_file=os.path.join(project_folder, "views.npz"))
def branch(task_name, out_dir, task_hparams, task_hparams_file, shared_hparams,
weights, copy_weights, views_file):
create_folders(out_dir)
# Set the task fields to only the current task under 'build'
shared_hparams.set_value("build",
"task_names",
value='["%s"]' % task_name,
overwrite=True)
shared_hparams.delete_group("tasks") # No longer necessary
# Create a map defining where each task specific parameter should go
mapping = {
"task_specifics/n_classes": "build/n_classes",
"task_specifics/n_channels": "build/n_channels",
"task_specifics/dim": ["build/dim", "fit/dim"],
"task_specifics/out_activation": "build/out_activation",
"task_specifics/real_space_span": "fit/real_space_span"
}
for soruce, targets in mapping.items():
in_key1, in_key2 = soruce.split("/")
value = task_hparams[in_key1][in_key2]
# Set the value at all targets
targets = [targets] if isinstance(targets, str) else targets
for target in targets:
out_key1, out_key2 = target.split("/")
shared_hparams.set_value(out_key1, out_key2, value, overwrite=True)
# Add all data folders
data_folders = ("train_data", "val_data", "test_data", "aug_data")
for df in data_folders:
yaml = task_hparams.get_group(df)
shared_hparams.add_group(yaml_string=yaml)
# Save the updates parameters to a new location
shared_hparams.save_current(os.path.join(out_dir, "train_hparams.yaml"))
# Add weights to folder
weights_folder = os.path.join(out_dir, "model")
create_folders(weights_folder)
out_weights_name = os.path.split(weights)[1]
out_weights_path = os.path.join(weights_folder, out_weights_name)
func = copy if copy_weights else os.symlink
if copy_weights:
print("Copying weights...")
else:
print("Symlinking weights...")
func(weights, out_weights_path)
# Add views (check for existence for future compatibility with 3D models)
if os.path.exists(views_file):
func(views_file, os.path.join(out_dir, "views.npz"))
def save_all_3D(results, detailed_res, out_dir):
txt_res_dir = os.path.join(out_dir, "txt")
csv_res_dir = os.path.join(out_dir, "csv")
# Create folders
create_folders([txt_res_dir, csv_res_dir])
# Save main text/csv results files
results_to_txt(results, txt_res_dir, transpose=True)
results_to_csv(results, csv_res_dir, transpose=True)
results_to_txt(detailed_res, txt_res_dir, fname="detailed")
results_to_csv(detailed_res, csv_res_dir, fname="detailed")
def run_on_split(split_path, test_split, train_val_data, n_val, args):
"""
Add the train/val/test files of a single split to the split directories
Depending on the arguments parsed (--copy, --file_list etc.) either copies,
symlinks or creates a LIST_OF_FILES.txt file of absolute paths in each
split sub-directory.
Args:
split_path: (string) Path to the split directory
test_split: (list) List of paths pointing to split test data
train_val_data: (list) List of paths pointing to the remaining data
n_val: (int) Number of samples in 'train_val_data' to use
for validation - rest is used for training.
args: (tuple) Parsed arguments, see argparser.
"""
# Define train, val and test sub-dirs
train_path = os.path.join(split_path, "train")
val_path = os.path.join(split_path, "val") if n_val else None
test_path = os.path.join(split_path, "test")
# Create folders if not existing
create_folders([train_path, val_path, test_path])
# Copy or symlink?
if args.copy:
from shutil import copyfile
move_func = copyfile
elif args.file_list:
move_func = _add_to_file_list_fallback
else:
move_func = os.symlink
# Extract validation data from the remaining
random.shuffle(train_val_data)
validation = train_val_data[:n_val]
training = train_val_data[n_val:]
# Add training
train_records = add_files(training, train_path, move_func)
# Add test data
test_records = add_files(test_split, test_path, move_func)
if n_val:
# Add validation
val_records = add_files(validation, val_path, move_func)
else:
val_records = 0
return train_records, val_records, test_records
def save_all(results, pc_results, out_dir):
# Get output paths
txt_res_dir = os.path.join(out_dir, "txt")
csv_res_dir = os.path.join(out_dir, "csv")
# Create folders
create_folders([txt_res_dir, csv_res_dir])
# Save main text/csv results files
results_to_txt(results, txt_res_dir)
results_to_csv(results, csv_res_dir)
# Write detailed results
for view in pc_results:
r = pc_results[view]
view_str = str(view).replace("[", "").strip().replace("]", "").replace(" ", "_")
results_to_txt(r, txt_res_dir, fname=view_str)
results_to_csv(r, csv_res_dir, fname=view_str)
def entry_func(args=None):
# Get parser
parser = vars(get_parser().parse_args(args))
# Get parser arguments
cv_dir = os.path.abspath(parser["CV_dir"])
out_dir = os.path.abspath(parser["out_dir"])
create_folders(out_dir)
await_PID = parser["wait_for"]
run_split = parser["run_on_split"]
start_from = parser["start_from"] or 0
num_jobs = parser["num_jobs"] or 1
# GPU settings
num_GPUs = parser["num_GPUs"]
force_GPU = parser["force_GPU"]
ignore_GPU = parser["ignore_GPU"]
monitor_GPUs_every = parser["monitor_GPUs_every"]
# User input assertions
_assert_force_and_ignore_gpus(force_GPU, ignore_GPU)
if run_split:
_assert_run_split(start_from, monitor_GPUs_every, num_jobs)
# Wait for PID?
if await_PID:
from mpunet.utils import await_PIDs
await_PIDs(await_PID)
# Get file paths
script = os.path.abspath(parser["script_prototype"])
hparams = os.path.abspath(parser["hparams_prototype"])
no_hparams = parser["no_hparams"]
# Get list of folders of CV data to run on
cv_folders = get_CV_folders(cv_dir)
if run_split is not None:
if run_split < 0 or run_split >= len(cv_folders):
raise ValueError("--run_on_split should be in range [0-{}], "
"got {}".format(len(cv_folders) - 1, run_split))
cv_folders = [cv_folders[run_split]]
log_appendix = "_split{}".format(run_split)
else:
log_appendix = ""
# Get a logger object
logger = Logger(base_path="./",
active_file="output" + log_appendix,
print_calling_method=False,
overwrite_existing=True)
if force_GPU:
# Only these GPUs fill be chosen from
from mpunet.utils import set_gpu
set_gpu(force_GPU)
if num_GPUs:
# Get GPU sets (up to the number of splits)
gpu_sets = get_free_GPU_sets(num_GPUs, ignore_GPU)[:len(cv_folders)]
elif not num_jobs or num_jobs < 0:
raise ValueError("Should specify a number of jobs to run in parallel "
"with the --num_jobs flag when using 0 GPUs pr. "
"process (--num_GPUs=0 was set).")
else:
gpu_sets = ["''"] * parser["num_jobs"]
# Get process pool, lock and GPU queue objects
lock = Lock()
gpu_queue = Queue()
for gpu in gpu_sets:
gpu_queue.put(gpu)
procs = []
if monitor_GPUs_every is not None and monitor_GPUs_every:
logger("\nOBS: Monitoring GPU pool every %i seconds\n" %
monitor_GPUs_every)
# Start a process monitoring new GPU availability over time
stop_event = Event()
t = Process(target=monitor_GPUs,
args=(monitor_GPUs_every, gpu_queue, num_GPUs, ignore_GPU,
gpu_sets, stop_event))
t.start()
procs.append(t)
else:
stop_event = None
try:
for cv_folder in cv_folders[start_from:]:
gpus = gpu_queue.get()
t = Process(target=run_sub_experiment,
args=(cv_folder, out_dir, script, hparams, no_hparams,
gpus, gpu_queue, lock, logger))
t.start()
procs.append(t)
for t in procs:
if not t.is_alive():
t.join()
except KeyboardInterrupt:
for t in procs:
t.terminate()
if stop_event is not None:
stop_event.set()
for t in procs:
t.join()
def entry_func(args=None):
# Project base path
args = vars(get_argparser().parse_args(args))
basedir = os.path.abspath(args["project_dir"])
overwrite = args["overwrite"]
continue_training = args["continue_training"]
eval_prob = args["eval_prob"]
await_PID = args["wait_for"]
dice_weight = args["dice_weight"]
print("Fitting fusion model for project-folder: %s" % basedir)
# Minimum images in validation set before also using training images
min_val_images = 15
# Fusion model training params
epochs = args['epochs']
fm_batch_size = args["batch_size"]
# Early stopping params
early_stopping = args["early_stopping"]
# Wait for PID?
if await_PID:
from mpunet.utils import await_PIDs
await_PIDs(await_PID)
# Fetch GPU(s)
num_GPUs = args["num_GPUs"]
force_gpu = args["force_GPU"]
# Wait for free GPU
if not force_gpu:
await_and_set_free_gpu(N=num_GPUs, sleep_seconds=120)
else:
set_gpu(force_gpu)
# Get logger
logger = Logger(base_path=basedir,
active_file="train_fusion",
overwrite_existing=overwrite)
# Get YAML hyperparameters
hparams = YAMLHParams(os.path.join(basedir, "train_hparams.yaml"))
# Get some key settings
n_classes = hparams["build"]["n_classes"]
if hparams["build"]["out_activation"] == "linear":
# Trained with logit targets?
hparams["build"][
"out_activation"] = "softmax" if n_classes > 1 else "sigmoid"
# Get views
views = np.load("%s/views.npz" % basedir)["arr_0"]
del hparams["fit"]["views"]
# Get weights and set fusion (output) path
weights = get_best_model("%s/model" % basedir)
weights_name = os.path.splitext(os.path.split(weights)[-1])[0]
fusion_weights = "%s/model/fusion_weights/" \
"%s_fusion_weights.h5" % (basedir, weights_name)
create_folders(os.path.split(fusion_weights)[0])
# Log a few things
log(logger, hparams, views, weights, fusion_weights)
# Check if exists already...
if not overwrite and os.path.exists(fusion_weights):
from sys import exit
print("\n[*] A fusion weights file already exists at '%s'."
"\n Use the --overwrite flag to overwrite." % fusion_weights)
exit(0)
# Load validation data
images = ImagePairLoader(**hparams["val_data"], logger=logger)
is_validation = {m.identifier: True for m in images}
# Define random sets of images to train on simul. (cant be all due
# to memory constraints)
image_IDs = [m.identifier for m in images]
if len(images) < min_val_images:
# Pick N random training images
diff = min_val_images - len(images)
logger("Adding %i training images to set" % diff)
# Load the training data and pick diff images
train = ImagePairLoader(**hparams["train_data"], logger=logger)
indx = np.random.choice(np.arange(len(train)),
diff,
replace=diff > len(train))
# Add the images to the image set set
train_add = [train[i] for i in indx]
for m in train_add:
is_validation[m.identifier] = False
image_IDs.append(m.identifier)
images.add_images(train_add)
# Append to length % sub_size == 0
sub_size = args["images_per_round"]
rest = int(sub_size * np.ceil(len(image_IDs) / sub_size)) - len(image_IDs)
if rest:
image_IDs += list(np.random.choice(image_IDs, rest, replace=False))
# Shuffle and split
random.shuffle(image_IDs)
sets = [
set(s) for s in np.array_split(image_IDs,
len(image_IDs) / sub_size)
]
assert (contains_all_images(sets, image_IDs))
# Define fusion model (named 'org' to store reference to orgiginal model if
# multi gpu model is created below)
fusion_model = FusionModel(n_inputs=len(views),
n_classes=n_classes,
weight=dice_weight,
logger=logger,
verbose=False)
if continue_training:
fusion_model.load_weights(fusion_weights)
print("\n[OBS] CONTINUED TRAINING FROM:\n", fusion_weights)
import tensorflow as tf
with tf.distribute.MirroredStrategy().scope():
# Define model
unet = init_model(hparams["build"], logger)
print("\n[*] Loading weights: %s\n" % weights)
unet.load_weights(weights, by_name=True)
# Compile the model
logger("Compiling...")
metrics = [
"sparse_categorical_accuracy", sparse_fg_precision, sparse_fg_recall
]
fusion_model.compile(optimizer=Adam(lr=1e-3),
loss=fusion_model.loss,
metrics=metrics)
fusion_model._log()
try:
_run_fusion_training(sets, logger, hparams, min_val_images,
is_validation, views, n_classes, unet,
fusion_model, early_stopping, fm_batch_size,
epochs, eval_prob, fusion_weights)
except KeyboardInterrupt:
pass
finally:
if not os.path.exists(os.path.split(fusion_weights)[0]):
os.mkdir(os.path.split(fusion_weights)[0])
# Save fusion model weights
# OBS: Must be original model if multi-gpu is performed!
fusion_model.save_weights(fusion_weights)
def entry_func(args=None):
# Get command line arguments
args = vars(get_argparser().parse_args(args))
base_dir = os.path.abspath(args["project_dir"])
_file = args["f"]
label = args["l"]
N_extra = args["extra"]
try:
N_extra = int(N_extra)
except ValueError:
pass
# Get settings from YAML file
from mpunet.hyperparameters import YAMLHParams
hparams = YAMLHParams(os.path.join(base_dir, "train_hparams.yaml"))
# Set strides
hparams["fit"]["strides"] = args["strides"]
if not _file:
try:
# Data specified from command line?
data_dir = os.path.abspath(args["data_dir"])
# Set with default sub dirs
hparams["test_data"] = {
"base_dir": data_dir,
"img_subdir": "images",
"label_subdir": "labels"
}
except (AttributeError, TypeError):
data_dir = hparams["test_data"]["base_dir"]
else:
data_dir = False
out_dir = os.path.abspath(args["out_dir"])
overwrite = args["overwrite"]
predict_mode = args["no_eval"]
save_only_pred = args["save_only_pred"]
# Check if valid dir structures
validate_folders(base_dir, data_dir, out_dir, overwrite)
# Import all needed modules (folder is valid at this point)
import numpy as np
from mpunet.image import ImagePairLoader, ImagePair
from mpunet.utils import get_best_model, create_folders, \
pred_to_class, await_and_set_free_gpu, set_gpu
from mpunet.utils.fusion import predict_3D_patches, predict_3D_patches_binary, pred_3D_iso
from mpunet.logging import init_result_dict_3D, save_all_3D
from mpunet.evaluate import dice_all
from mpunet.bin.predict import save_nii_files
# Fetch GPU(s)
num_GPUs = args["num_GPUs"]
force_gpu = args["force_GPU"]
# Wait for free GPU
if force_gpu == -1:
await_and_set_free_gpu(N=num_GPUs, sleep_seconds=240)
else:
set_gpu(force_gpu)
# Read settings from the project hyperparameter file
dim = hparams["build"]["dim"]
n_classes = hparams["build"]["n_classes"]
mode = hparams["fit"]["intrp_style"]
# Set ImagePairLoader object
if not _file:
image_pair_loader = ImagePairLoader(predict_mode=predict_mode,
**hparams["test_data"])
else:
predict_mode = not bool(label)
image_pair_loader = ImagePairLoader(predict_mode=predict_mode,
initialize_empty=True)
image_pair_loader.add_image(ImagePair(_file, label))
all_images = {
image.identifier: image
for image in image_pair_loader.images
}
# Set scaler and bg values
image_pair_loader.set_scaler_and_bg_values(
bg_value=hparams.get_from_anywhere('bg_value'),
scaler=hparams.get_from_anywhere('scaler'),
compute_now=False)
# Init LazyQueue and get its sequencer
from mpunet.sequences.utils import get_sequence
seq = get_sequence(data_queue=image_pair_loader,
is_validation=True,
**hparams["fit"],
**hparams["build"])
""" Define UNet model """
from mpunet.models import model_initializer
hparams["build"]["batch_size"] = 1
unet = model_initializer(hparams, False, base_dir)
model_path = get_best_model(base_dir + "/model")
unet.load_weights(model_path)
# Evaluate?
if not predict_mode:
# Prepare dictionary to store results in pd df
results, detailed_res = init_result_dict_3D(all_images, n_classes)
# Save to check correct format
save_all_3D(results, detailed_res, out_dir)
# Define result paths
nii_res_dir = os.path.join(out_dir, "nii_files")
create_folders(nii_res_dir)
image_ids = sorted(all_images)
for n_image, image_id in enumerate(image_ids):
print("\n[*] Running on: %s" % image_id)
with seq.image_pair_queue.get_image_by_id(image_id) as image_pair:
if mode.lower() == "iso_live_3d":
pred = pred_3D_iso(model=unet,
sequence=seq,
image=image_pair,
extra_boxes=N_extra,
min_coverage=None)
else:
# Predict on volume using model
if n_classes > 1:
pred = predict_3D_patches(model=unet,
patches=seq,
image=image_pair,
N_extra=N_extra)
else:
pred = predict_3D_patches_binary(model=unet,
patches=seq,
image_id=image_id,
N_extra=N_extra)
if not predict_mode:
# Get patches for the current image
y = image_pair.labels
# Calculate dice score
print("Mean dice: ", end="", flush=True)
p = pred_to_class(pred, img_dims=3, has_batch_dim=False)
dices = dice_all(y, p, n_classes=n_classes, ignore_zero=True)
mean_dice = dices[~np.isnan(dices)].mean()
print("Dices: ", dices)
print("%s (n=%i)" % (mean_dice, len(dices)))
# Add to results
results[image_id] = [mean_dice]
detailed_res[image_id] = dices
# Overwrite with so-far results
save_all_3D(results, detailed_res, out_dir)
# Save results
save_nii_files(p, image_pair, nii_res_dir, save_only_pred)
if not predict_mode:
# Write final results
save_all_3D(results, detailed_res, out_dir)
def entry_func(args=None):
# Get parser
parser = vars(get_parser().parse_args(args))
# Get arguments
data_dir = os.path.abspath(parser["data_dir"])
n_splits = int(parser["CV"])
if n_splits > 1:
out_dir = os.path.join(data_dir, parser["out_dir"], "%i_CV" % n_splits)
else:
out_dir = os.path.join(data_dir, parser["out_dir"], "fixed_split")
im_dir = os.path.join(data_dir, parser["im_sub_dir"])
lab_dir = os.path.join(data_dir, parser["lab_sub_dir"])
copy = parser["copy"]
file_list = parser["file_list"]
regex = parser["file_regex"]
val_frac = parser["validation_fraction"]
test_frac = parser["test_fraction"]
common_prefix_length = parser["common_prefix_length"]
if n_splits == 1 and not test_frac:
raise ValueError("Must specify --test_fraction with --CV=1.")
if copy and file_list:
raise ValueError("Only one of --copy and --file_list "
"flags must be set.")
# Assert suitable folders
assert_dir_structure(data_dir, im_dir, lab_dir, out_dir)
# Create sub-folders
create_view_folders(out_dir, n_splits)
# Get images and pair by subject identifier if common_prefix_length > 0
images = glob(os.path.join(im_dir, regex))
images = pair_by_names(images, common_prefix_length)
print("-----")
print("Found {} images".format(len(images)))
# Get validation size
N_total = len(images)
if n_splits > 1:
N_test = N_total // n_splits
else:
N_test = int(np.ceil(N_total * test_frac))
N_val = int(np.ceil(N_total * val_frac))
if N_val + N_test >= N_total:
raise ValueError("Too large validation_fraction - "
"No training samples left!")
N_train = N_total - N_test - N_val
print("Total images:".ljust(40), N_total)
print("Train images pr. split:".ljust(40), N_train)
print("Validation images pr. split:".ljust(40), N_val)
print("Test images pr. split:".ljust(40), N_test)
# Shuffle and split the images into CV parts
random.shuffle(images)
splits = np.array_split(images, n_splits)
# Symlink / copy files
for i, split in enumerate(splits):
print(" Split %i/%i" % (i+1, n_splits), end="\r", flush=True)
# Set root path to split folder
if n_splits > 1:
split_path = os.path.join(out_dir, "split_%i" % i)
else:
split_path = out_dir
# Here we kind of hacky force the following code to work with CV=1
# Define a test set and overwrite the current split (which stores
# add the data, as splits was never split with n_splits=1
split = splits[0][:N_test]
# Overwrite the splits variable to a length 2 array with the
# remaining data which will be used as val+train. The loop still
# refers to the old split and thus will only execute once
splits = [split, splits[0][N_test:]]
# Define train, val and test sub-dirs
train_path = os.path.join(split_path, "train")
train_im_path = os.path.join(train_path, parser["im_sub_dir"])
train_label_path = os.path.join(train_path, parser["lab_sub_dir"])
if N_val:
val_path = os.path.join(split_path, "val")
val_im_path = os.path.join(val_path, parser["im_sub_dir"])
val_label_path = os.path.join(val_path, parser["lab_sub_dir"])
else:
val_path, val_im_path, val_label_path = (None,) * 3
test_path = os.path.join(split_path, "test")
test_im_path = os.path.join(test_path, parser["im_sub_dir"])
test_label_path = os.path.join(test_path, parser["lab_sub_dir"])
# Create folders if not existing
create_folders([train_path, val_path, train_im_path, train_label_path,
val_im_path, val_label_path, test_path, test_im_path,
test_label_path])
# Copy or symlink?
if copy:
from shutil import copyfile
move_func = copyfile
elif file_list:
move_func = _add_to_file_list_fallback
else:
move_func = os.symlink
# Add test data to test folder
add_images(split, test_im_path, test_label_path, im_dir, lab_dir, move_func)
# Join remaining splits into train+val
remaining = [x for ind, x in enumerate(splits) if ind != i]
remaining = [item for sublist in remaining for item in sublist]
# Extract validation data from the remaining
random.shuffle(remaining)
validation = remaining[:N_val]
training = remaining[N_val:]
# Add
if validation:
add_images(validation, val_im_path, val_label_path, im_dir, lab_dir, move_func)
add_images(training, train_im_path, train_label_path, im_dir, lab_dir, move_func)
def run(args):
cv_dir = os.path.abspath(args.CV_dir)
# Get list of folders of CV data to run on
cv_folders = get_CV_folders(cv_dir)
assert_args(args, n_splits=len(cv_folders))
out_dir = os.path.abspath(args.out_dir)
hparams_dir = os.path.abspath(args.hparams_prototype_dir)
prepare_hparams_dir(hparams_dir)
create_folders(out_dir)
# Wait for PID?
if args.wait_for:
from mpunet.utils import await_PIDs
await_PIDs(args.wait_for)
if args.run_on_split is not None:
cv_folders = [cv_folders[args.run_on_split]]
log_appendix = "_split{}".format(args.run_on_split)
else:
log_appendix = ""
# Get a logger object
logger = Logger(base_path="./",
active_file="output" + log_appendix,
print_calling_method=False,
overwrite_existing=True)
if args.force_GPU:
# Only these GPUs fill be chosen from
from mpunet.utils import set_gpu
set_gpu(args.force_GPU)
if args.num_GPUs:
# Get GPU sets (up to the number of splits)
gpu_sets = get_free_GPU_sets(args.num_GPUs,
args.ignore_GPU)[:len(cv_folders)]
elif not args.num_jobs or args.num_jobs < 0:
raise ValueError("Should specify a number of jobs to run in parallel "
"with the --num_jobs flag when using 0 GPUs pr. "
"process (--num_GPUs=0 was set).")
else:
gpu_sets = ["''"] * args.num_jobs
# Get process pool, lock and GPU queue objects
lock = Lock()
gpu_queue = Queue()
for gpu in gpu_sets:
gpu_queue.put(gpu)
# Get file paths
script = os.path.abspath(args.script_prototype)
# Get GPU monitor process
running_processes, stop_event = start_gpu_monitor_process(
args, gpu_queue, gpu_sets, logger)
try:
for cv_folder in cv_folders[args.start_from:]:
gpus = gpu_queue.get()
t = Process(target=run_sub_experiment,
args=(cv_folder, out_dir, script, hparams_dir,
args.no_hparams, gpus, gpu_queue, lock, logger))
t.start()
running_processes.append(t)
for t in running_processes:
if not t.is_alive():
t.join()
except KeyboardInterrupt:
for t in running_processes:
t.terminate()
if stop_event is not None:
stop_event.set()
for t in running_processes:
t.join()
