def get_vids(cf, dataset) -> Dict[str, List[Vid_daly]]:
v_fraction = cf['dataset.val_split.fraction']
v_nsamplings = cf['dataset.val_split.nsamplings']
v_seed = cf['dataset.val_split.seed']
val, train = split_off_validation_set(dataset, v_fraction,
v_nsamplings, v_seed)
vgroup = {
'train': train,
'val': val,
'trainval': get_daly_split_vids(dataset, 'train'),
'test': get_daly_split_vids(dataset, 'test'),
}
return vgroup
def eval_daly_object(workfolder, cfg_dict, add_args):
"""
Evaluation code with hacks
"""
out, = snippets.get_subfolders(workfolder, ['out'])
cfg = snippets.YConfig(cfg_dict)
_set_defcfg_detectron(cfg)
_set_defcfg_detectron_test(cfg)
_set_defcfg_object_hacks(cfg)
cfg.set_deftype("""
what_to_eval: [~, str]
eval_hacks:
model_to_eval: ['what', ['what', 'what+foldname']]
""")
cf = cfg.parse()
cf_add_d2 = cfg.without_prefix('d2.')
# DALY Dataset
dataset = Dataset_daly_ocv()
dataset.populate_from_folder(cf['dataset.cache_folder'])
split_label = cf['dataset.subset']
split_vids = get_daly_split_vids(dataset, split_label)
datalist: Datalist = simplest_daly_to_datalist_v2(dataset, split_vids)
cls_names, datalist_converter = \
_datalist_hacky_converter(cf, dataset)
datalist = datalist_converter(datalist)
TEST_DATASET_NAME = 'daly_objaction_test'
model_to_eval = _eval_foldname_hack(cf)
_eval_routine(cf, cf_add_d2, out, cls_names,
TEST_DATASET_NAME, datalist, model_to_eval)
def train_daly_object(workfolder, cfg_dict, add_args):
out, = snippets.get_subfolders(workfolder, ['out'])
cfg = snippets.YConfig(cfg_dict)
_set_defcfg_detectron(cfg)
_set_defcfg_detectron_train(cfg)
_set_defcfg_object_hacks(cfg)
cf = cfg.parse()
cf_add_d2 = cfg.without_prefix('d2.')
cf_add_d2 = d2dict_gpu_scaling(cf, cf_add_d2, cf['num_gpus'])
dataset = Dataset_daly_ocv()
dataset.populate_from_folder(cf['dataset.cache_folder'])
o100_objects, category_map = get_category_map_o100(dataset)
assert len(o100_objects) == 16
split_label = cf['dataset.subset']
split_vids = get_daly_split_vids(dataset, split_label)
datalist: Datalist = simplest_daly_to_datalist_v2(dataset, split_vids)
cls_names, datalist_converter = \
_datalist_hacky_converter(cf, dataset)
datalist = datalist_converter(datalist)
TRAIN_DATASET_NAME = 'daly_objaction_train'
_train_routine(cf, cf_add_d2, out,
cls_names, TRAIN_DATASET_NAME, datalist, add_args)
def resolve_dataset_tubes(cf):
dataset = Dataset_daly_ocv(cf['dataset.mirror'])
dataset.populate_from_folder(cf['dataset.cache_folder'])
split_label = cf['dataset.subset']
split_vids: List[Vid_daly] = \
get_daly_split_vids(dataset, split_label)
dgt_tubes: Dict[I_dgt, T_dgt] = \
get_daly_gt_tubes(dataset)
dgt_tubes = dtindex_filter_split(dgt_tubes, split_vids)
av_gt_tubes: AV_dict[T_dgt] = push_into_avdict(dgt_tubes)
return dataset, split_vids, av_gt_tubes
def train_daly_action(workfolder, cfg_dict, add_args):
out, = snippets.get_subfolders(workfolder, ['out'])
cfg = snippets.YConfig(cfg_dict)
_set_defcfg_detectron(cfg)
_set_defcfg_detectron_train(cfg)
cf = cfg.parse()
cf_add_d2 = cfg.without_prefix('d2.')
cf_add_d2 = d2dict_gpu_scaling(cf, cf_add_d2, cf['num_gpus'])
dataset = Dataset_daly_ocv()
dataset.populate_from_folder(cf['dataset.cache_folder'])
split_label = cf['dataset.subset']
split_vids = get_daly_split_vids(dataset, split_label)
datalist: Datalist = daly_to_datalist_pfadet(dataset, split_vids)
cls_names = dataset.action_names
TRAIN_DATASET_NAME = 'daly_pfadet_train'
_train_routine(cf, cf_add_d2, out,
cls_names, TRAIN_DATASET_NAME, datalist, add_args)