def main():
args.dump_dir = ensure_path(
osp.join('dumps', args.series_name, args.desc_name,
(args.training_target + ('-curriculum_' + args.curriculum) +
('-qtrans_' + args.question_transform
if args.question_transform is not None else '') +
('-' + args.expr if args.expr is not None else '') +
('-lr_' + str(args.lr)))))
if not args.debug:
args.ckpt_dir = ensure_path(osp.join(args.dump_dir, 'checkpoints'))
args.meta_dir = ensure_path(osp.join(args.dump_dir, 'meta'))
args.meta_file = osp.join(args.meta_dir, args.run_name + '.json')
args.log_file = osp.join(args.meta_dir, args.run_name + '.log')
args.meter_file = osp.join(args.meta_dir,
args.run_name + '.meter.json')
logger.critical('Writing logs to file: "{}".'.format(args.log_file))
set_output_file(args.log_file)
logger.critical('Writing metainfo to file: "{}".'.format(
args.meta_file))
with open(args.meta_file, 'w') as f:
f.write(dump_metainfo(args=args.__dict__, configs=configs))
# Initialize the tensorboard.
if args.use_tb:
args.tb_dir_root = ensure_path(
osp.join(args.dump_dir, 'tensorboard'))
args.tb_dir = ensure_path(osp.join(args.tb_dir_root,
args.run_name))
initialize_dataset(args.dataset)
build_dataset = get_dataset_builder(args.dataset)
dataset = build_dataset(args, configs, args.data_image_root,
args.data_scenes_json, args.data_questions_json)
dataset_trim = int(len(dataset) *
args.data_trim) if args.data_trim <= 1 else int(
args.data_trim)
if dataset_trim > 0:
dataset = dataset.trim_length(dataset_trim)
dataset_split = int(len(dataset) *
args.data_split) if args.data_split <= 1 else int(
args.data_split)
train_dataset, validation_dataset = dataset.split_trainval(dataset_split)
extra_dataset = None
if args.extra_data_dir is not None:
extra_dataset = build_dataset(args, configs,
args.extra_data_image_root,
args.extra_data_scenes_json,
args.extra_data_questions_json)
main_train(train_dataset, validation_dataset, extra_dataset)
def get_data(batch_size=1, dataset_size=500):
initialize_dataset(args.dataset)
build_dataset = get_dataset_builder(args.dataset)
#use validation set
dataset = build_dataset(args, configs, args.extra_data_image_root,
args.extra_data_scenes_json,
args.extra_data_questions_json)
if dataset_size is not None:
dataset = dataset.trim_length(dataset_size)
dataloader = dataset.make_dataloader(batch_size=batch_size,
shuffle=False,
drop_last=False,
nr_workers=1)
train_iter = iter(dataloader)
return train_iter, dataset_size
def main():
args.dump_dir = ensure_path(
osp.join(
"dumps",
args.series_name,
args.desc_name,
(args.training_target + ("-curriculum_" + args.curriculum) +
("-qtrans_" + args.question_transform
if args.question_transform is not None else "") +
("-" + args.expr if args.expr is not None else "")),
))
if not args.debug:
args.ckpt_dir = ensure_path(osp.join(args.dump_dir, "checkpoints"))
args.meta_dir = ensure_path(osp.join(args.dump_dir, "meta"))
args.meta_file = osp.join(args.meta_dir, args.run_name + ".json")
args.log_file = osp.join(args.meta_dir, args.run_name + ".log")
args.meter_file = osp.join(args.meta_dir,
args.run_name + ".meter.json")
logger.critical('Writing logs to file: "{}".'.format(args.log_file))
set_output_file(args.log_file)
logger.critical('Writing metainfo to file: "{}".'.format(
args.meta_file))
with open(args.meta_file, "w") as f:
f.write(dump_metainfo(args=args.__dict__, configs=configs))
# Initialize the tensorboard.
if args.use_tb:
args.tb_dir_root = ensure_path(
osp.join(args.dump_dir, "tensorboard"))
args.tb_dir = ensure_path(osp.join(args.tb_dir_root,
args.run_name))
if args.train_split is not None:
with open(osp.join(args.data_dir, args.train_split)) as f:
train_idxs = set(json.load(f))
else:
train_idxs = None
if args.val_split is not None and args.val_data_dir is not None:
with open(osp.join(args.val_data_dir, args.val_split)) as f:
val_idxs = set(json.load(f))
else:
val_idxs = None
if args.test_split is not None and args.test_data_dir is not None:
with open(osp.join(args.test_data_dir, args.test_split)) as f:
test_idxs = set(json.load(f))
else:
test_idxs = None
initialize_dataset(args.dataset)
build_dataset = get_dataset_builder(args.dataset)
dataset = build_dataset(
args,
configs,
args.data_image_root,
args.data_depth_root,
args.data_scenes_json,
args.data_questions_json,
)
# dataset_trim = (
# int(len(dataset) * args.data_trim)
# if args.data_trim <= 1
# else int(args.data_trim)
# )
# if dataset_trim > 0:
# dataset = dataset.trim_length(dataset_trim)
# # dataset_split = (
# # int(len(dataset) * args.data_split)
# # if args.data_split <= 1
# # else int(args.data_split)
# # )
# # train_dataset, validation_dataset = dataset.split_trainval(dataset_split)
# if args.mv:
# ood_views = set(args.ood_views)
# id_views = set(range(args.num_views)) - ood_views
train_dataset = dataset
# if train_idxs:
# train_dataset = dataset.filter(
# lambda question: question["image_index"] in train_idxs,
# "filter_train_size_{}".format(len(train_idxs)),
# )
val_dataset = None
if args.val_data_dir is not None:
val_dataset = build_dataset(
args,
configs,
args.val_data_image_root,
args.val_data_depth_root,
args.val_data_scenes_json,
args.val_data_questions_json,
)
# if val_idxs:
# val_dataset = val_dataset.filter(
# lambda question: question["image_index"] in val_idxs,
# "filter_val_size_{}".format(len(val_idxs)),
# )
test_dataset = None
if args.test_data_dir is not None:
test_dataset = build_dataset(
args,
configs,
args.test_data_image_root,
args.test_data_depth_root,
args.test_data_scenes_json,
args.test_data_questions_json,
)
# if test_idxs:
# test_dataset = test_dataset.filter(
# lambda question: question["image_index"] in test_idxs,
# "filter_val_size_{}".format(len(test_idxs)),
# )
# test_dataset = {"test": test_dataset}
# if args.mv:
# # train_dataset = train_dataset.filter(
# # lambda question: question["view_id"] in id_views, "id_view"
# # )
# if val_dataset:
# val_dataset = val_dataset.filter(
# lambda question: question["view_id"] in id_views, "id_view"
# )
# if test_dataset:
# id_test = test_dataset["test"].filter(
# lambda question: question["view_id"] in id_views, "id_view"
# )
# ood_test = test_dataset["test"].filter(
# lambda question: question["view_id"] in ood_views, "ood_view"
# )
# test_dataset = {"id_test": id_test, "ood_test": ood_test}
prototype_dataset = create_prototype_dataset(
"/projects/data/clevr_nscl/one_shot_protos")
one_shot_root = "/projects/data/clevr_nscl/one_shot_test_only"
one_shot_dataset = build_dataset(
args,
configs,
one_shot_root + "/images",
one_shot_root + "/depth",
one_shot_root + "/CLEVR_scenes_annotated_aligned.json",
one_shot_root + "/CLEVR_questions.json",
)
main_train(train_dataset, val_dataset, test_dataset, prototype_dataset,
one_shot_dataset)
def main():
args.dump_dir = ensure_path(
osp.join(
"dumps",
args.series_name,
args.desc_name,
(args.training_target + ("-curriculum_" + args.curriculum) +
("-qtrans_" + args.question_transform
if args.question_transform is not None else "") +
("-" + args.expr if args.expr is not None else "")),
))
if not args.debug:
args.ckpt_dir = ensure_path(osp.join(args.dump_dir, "checkpoints"))
args.meta_dir = ensure_path(osp.join(args.dump_dir, "meta"))
args.meta_file = osp.join(args.meta_dir, args.run_name + ".json")
args.log_file = osp.join(args.meta_dir, args.run_name + ".log")
args.meter_file = osp.join(args.meta_dir,
args.run_name + ".meter.json")
logger.critical('Writing logs to file: "{}".'.format(args.log_file))
set_output_file(args.log_file)
logger.critical('Writing metainfo to file: "{}".'.format(
args.meta_file))
with open(args.meta_file, "w") as f:
f.write(dump_metainfo(args=args.__dict__, configs=configs))
# Initialize the tensorboard.
if args.use_tb:
args.tb_dir_root = ensure_path(
osp.join(args.dump_dir, "tensorboard"))
args.tb_dir = ensure_path(osp.join(args.tb_dir_root,
args.run_name))
initialize_dataset(args.dataset)
build_dataset = get_dataset_builder(args.dataset)
dataset = build_dataset(
args,
configs,
args.data_image_root,
args.data_scenes_json,
args.data_questions_json,
)
dataset_trim = (int(len(dataset) * args.data_trim)
if args.data_trim <= 1 else int(args.data_trim))
if dataset_trim > 0:
dataset = dataset.trim_length(dataset_trim)
dataset_split = (int(len(dataset) * args.data_split)
if args.data_split <= 1 else int(args.data_split))
# from IPython import embed
# embed()
train_dataset, validation_dataset = dataset.split_trainval(dataset_split)
extra_dataset = None
if args.extra_data_dir is not None:
extra_dataset = build_dataset(
args,
configs,
args.extra_data_image_root,
args.extra_data_scenes_json,
args.extra_data_questions_json,
)
main_train(train_dataset, validation_dataset, extra_dataset)