def do_camelyon16():
"""
camelyon16.
The train/valid/test sets are already provided.
:return:
"""
# ===============
# Reproducibility
# ===============
# ===========================
reproducibility.init_seed()
# ===========================
ds = constants.CAM16
announce_msg("Processing dataset: {}".format(ds))
args = {
"baseurl": get_rootpath_2_dataset(Dict2Obj({'dataset': ds})),
"dataset": ds,
"fold_folder": "folds/{}".format(ds),
"img_extension": "jpg",
"path_encoding": "folds/{}/encoding-origine.yaml".format(ds)
}
# Convert masks into binary masks: already done.
# create_bin_mask_Oxford_flowers_102(Dict2Obj(args))
reproducibility.init_seed()
al_split_camelyon16(Dict2Obj(args))
def do_Oxford_flowers_102():
"""
Oxford-flowers-102.
The train/valid/test sets are already provided.
:return:
"""
# ===============
# Reproducibility
# ===============
# ===========================
reproducibility.init_seed()
# ===========================
announce_msg("Processing dataset: {}".format(constants.OXF))
args = {
"baseurl": get_rootpath_2_dataset(Dict2Obj({'dataset':
constants.OXF})),
"dataset": "Oxford-flowers-102",
"fold_folder": "folds/Oxford-flowers-102",
"img_extension": "jpg",
"path_encoding": "folds/Oxford-flowers-102/encoding-origine.yaml"
}
# Convert masks into binary masks: already done.
# create_bin_mask_Oxford_flowers_102(Dict2Obj(args))
reproducibility.init_seed()
al_split_Oxford_flowers_102(Dict2Obj(args))
get_stats(Dict2Obj(args), split=0, fold=0, subset='train')
def do_glas():
"""
GlaS.
:return:
"""
# ===============
# Reproducibility
# ===============
reproducibility.init_seed()
announce_msg("Processing dataset: {}".format(constants.GLAS))
args = {
"baseurl": get_rootpath_2_dataset(Dict2Obj({'dataset':
constants.GLAS})),
"folding": {
"vl": 20
}, # 80 % for train, 20% for validation.
"dataset": "glas",
"fold_folder": "folds/glas",
"img_extension": "bmp",
# nbr_splits: how many times to perform the k-folds over
# the available train samples.
"nbr_splits": 1
}
args["nbr_folds"] = math.ceil(100. / args["folding"]["vl"])
reproducibility.init_seed()
al_split_glas(Dict2Obj(args))
get_stats(Dict2Obj(args), split=0, fold=0, subset='train')
def parse_input():
"""
Parse the input.
and
initialize some modules for reproducibility.
"""
parser = argparse.ArgumentParser()
# mandatory: --yaml basefilename
parser.add_argument("--yaml",
type=str,
help="yaml configuration basefile.")
input_args, _ = parser.parse_known_args()
args, args_dict = get_yaml_args(input_args)
# Reproducibility control: this will use the seed in `os.environ['MYSEED']`.
reproducibility.init_seed()
# todo: remove input_args. useless. can be accessed from args.
return args, args_dict, input_args
def do_Caltech_UCSD_Birds_200_2011():
"""
Caltech-UCSD-Birds-200-2011.
:return:
"""
# ===============
# Reproducibility
# ===============
# ===========================
reproducibility.init_seed()
# ===========================
announce_msg("Processing dataset: {}".format(constants.CUB))
args = {
"baseurl": get_rootpath_2_dataset(Dict2Obj({'dataset':
constants.CUB})),
"folding": {
"vl": 20
}, # 80 % for train, 20% for validation.
"dataset": "Caltech-UCSD-Birds-200-2011",
"fold_folder": "folds/Caltech-UCSD-Birds-200-2011",
"img_extension": "bmp",
"nbr_splits": 1, # how many times to perform the k-folds over
# the available train samples.
"path_encoding":
"folds/Caltech-UCSD-Birds-200-2011/encoding-origine.yaml",
"nbr_classes": None # Keep only 5 random classes. If you want
# to use the entire dataset, set this to None.
}
args["nbr_folds"] = math.ceil(100. / args["folding"]["vl"])
reproducibility.init_seed()
al_split_Caltech_UCSD_Birds_200_2011(Dict2Obj(args))
get_stats(Dict2Obj(args), split=0, fold=0, subset='train')
# args.num_workers * this_factor. Useful when setting set_for_eval to False,
# batch size =1.
FACTOR_MUL_WORKERS = 2
# and we are in an evaluation mode (to go faster and coop with the lag
# between the CPU and GPU).
# Can be activated only for "Caltech-UCSD-Birds-200-2011" or
# "Oxford-flowers-102"
DEBUG_MODE = False
# dataset to go fast. If True, we select only few samples for training
# , validation, and test.
PLOT_STATS = True
# use the default seed. Copy the see into the os.environ("MYSEED")
reproducibility.init_seed()
NBRGPUS = torch.cuda.device_count()
ALLOW_MULTIGPUS = check_if_allow_multgpu_mode()
def _init_fn(worker_id):
"""
Init. function for the worker in dataloader.
:param worker_id:
:return:
"""
pass # no longer necessary since we override the process seed.