def build_detection_val_loader(cfg, dataset_name: str, mapper=None):
dataset_dicts = get_detection_dataset_dicts(
[dataset_name],
filter_empty=False,
proposal_files=[
cfg.DATASETS.PROPOSAL_FILES_TEST[list(cfg.DATASETS.TEST).index(dataset_name)]
]
if cfg.MODEL.LOAD_PROPOSALS
else None,
)
# dataset_dicts = get_detection_dataset_dicts(
# [dataset_name],
# filter_empty=cfg.DATALOADER.FILTER_EMPTY_ANNOTATIONS,
# min_keypoints=cfg.MODEL.ROI_KEYPOINT_HEAD.MIN_KEYPOINTS_PER_IMAGE
# if cfg.MODEL.KEYPOINT_ON
# else 0,
# proposal_files=cfg.DATASETS.PROPOSAL_FILES_TRAIN if cfg.MODEL.LOAD_PROPOSALS else None,
# )
dataset = DatasetFromList(dataset_dicts)
if mapper is None:
mapper = DatasetMapper(cfg, True)
dataset = MapDataset(dataset, mapper)
sampler = InferenceSampler(len(dataset))
batch_sampler = torch.utils.data.sampler.BatchSampler(sampler, 1, drop_last=False)
data_loader = torch.utils.data.DataLoader(
dataset,
num_workers=cfg.DATALOADER.NUM_WORKERS,
batch_sampler=batch_sampler,
collate_fn=trivial_batch_collator,
)
return data_loader
def build_detection_test_loader(cfg, dataset_name, mapper=None):
dataset_dicts = get_detection_dataset_dicts(
[dataset_name],
filter_empty=False,
proposal_files=[
cfg.DATASETS.PROPOSAL_FILES_TEST[list(
cfg.DATASETS.TEST).index(dataset_name)]
] if cfg.MODEL.LOAD_PROPOSALS else None,
)
dataset = DatasetFromList(dataset_dicts)
if mapper is None:
mapper = DatasetMapper(cfg, False)
dataset = MapDataset(dataset, mapper)
sampler = InferenceSampler(len(dataset))
batch_sampler = torch.utils.data.sampler.BatchSampler(sampler,
1,
drop_last=False)
data_loader = torch.utils.data.DataLoader(
dataset,
num_workers=cfg.DATALOADER.NUM_WORKERS,
batch_sampler=batch_sampler,
collate_fn=trivial_batch_collator,
)
return data_loader
def do_test(cfg, model):
results = OrderedDict()
for dataset_name in cfg.DATASETS.TEST:
mapper = None if cfg.INPUT.TEST_INPUT_TYPE == 'default' else \
DatasetMapper(
cfg, False, augmentations=build_custom_augmentation(cfg, False))
data_loader = build_detection_test_loader(cfg,
dataset_name,
mapper=mapper)
output_folder = os.path.join(cfg.OUTPUT_DIR,
"inference_{}".format(dataset_name))
evaluator_type = MetadataCatalog.get(dataset_name).evaluator_type
if evaluator_type == "lvis":
evaluator = LVISEvaluator(dataset_name, cfg, True, output_folder)
elif evaluator_type == 'coco':
evaluator = COCOEvaluator(dataset_name, cfg, True, output_folder)
else:
assert 0, evaluator_type
results[dataset_name] = inference_on_dataset(model, data_loader,
evaluator)
if comm.is_main_process():
logger.info("Evaluation results for {} in csv format:".format(
dataset_name))
print_csv_format(results[dataset_name])
if len(results) == 1:
results = list(results.values())[0]
return results
def build_hooks(self) -> List[HookBase]:
"""
This method overwrites the default one from DefaultTrainer.
It adds (if necessary) the `LossEvalHook` that allows evaluating the loss on the
validation set.
Returns:
List[HookBase]: The augmented list of hooks.
"""
# Build a list of default hooks, including timing, evaluation,
# checkpointing, lr scheduling, precise BN, writing events.
hooks = super().build_hooks()
# We add our custom validation hook
if self.cfg.DATASETS.VALIDATION != "":
data_set_mapper: DatasetMapper = DatasetMapper.from_config(
cfg=self.cfg, is_train=True)
data_loader: DataLoader = build_detection_test_loader(
cfg=self.cfg,
dataset_name=self.cfg.DATASETS.VALIDATION,
mapper=data_set_mapper)
loss_eval_hook: LossEvalHook = LossEvalHook(
eval_period=self.cfg.VALIDATION.VALIDATION_PERIOD,
model=self.model,
data_loader=data_loader)
hooks.insert(index=-1, obj=loss_eval_hook)
return hooks
def build_test_loader(cls, cfg, dataset_name):
"""
Custom dataloader to provide model with ground truth bounding boxes
"""
# returns a list of dicts. Every entry in the list corresponds to one sample, represented by a dict.
dataset_dicts = detectron2.data.get_detection_dataset_dicts(
dataset_name)
# add proposal boxes
for i, s in enumerate(dataset_dicts):
s["proposal_boxes"] = np.array(
[ann["bbox"] for ann in dataset_dicts[i]["annotations"]]
) # np.array([[xmin, ymin, xmax, ymax],[xmin, ymin, xmax, ...], ...]) # kx4 matrix for k proposed bounding boxes
s["proposal_objectness_logits"] = np.full(
(s["proposal_boxes"].shape[0], ),
10) # logit of 10 is 99.999...%
s["proposal_bbox_mode"] = detectron2.structures.BoxMode.XYWH_ABS # 1 # (x0, y0, w, h) in absolute floating points coordinates
print("Proposal boxes for test data added.")
return build_detection_test_loader(dataset_dicts,
mapper=DatasetMapper(
is_train=False,
augmentations=[],
image_format=cfg.INPUT.FORMAT,
precomputed_proposal_topk=500))
def build_detection_meta_loader(cfg, mapper=None):
"""
build the meta set from training data with Class Balanced Sampling
"""
dataset_dicts = get_detection_dataset_dicts(
cfg.DATASETS.TRAIN,
filter_empty=cfg.DATALOADER.FILTER_EMPTY_ANNOTATIONS,
min_keypoints=cfg.MODEL.ROI_KEYPOINT_HEAD.MIN_KEYPOINTS_PER_IMAGE
if cfg.MODEL.KEYPOINT_ON else 0,
proposal_files=cfg.DATASETS.PROPOSAL_FILES_TRAIN
if cfg.MODEL.LOAD_PROPOSALS else None,
)
dataset = DatasetFromList(dataset_dicts, copy=False)
if mapper is None:
mapper = DatasetMapper(cfg, True)
dataset = MapDataset(dataset, mapper)
logger = logging.getLogger(__name__)
logger.info("Using training sampler Class Balanced Sampler")
repeat_factors = ClassBalancedTrainingSampler.repeat_factors_by_inverse_category_frequency(
dataset_dicts)
sampler = ClassBalancedTrainingSampler(repeat_factors)
return build_batch_data_loader(
dataset,
sampler,
cfg.SOLVER.IMS_PER_BATCH,
aspect_ratio_grouping=cfg.DATALOADER.ASPECT_RATIO_GROUPING,
num_workers=cfg.DATALOADER.NUM_WORKERS,
)
def build_train_loader(cls, cfg):
"""
custom dataloader to provide model with ground truth bounding boxes
"""
# returns a list of dicts. Every entry in the list corresponds to one sample, represented by a dict.
dataset_dicts = detectron2.data.get_detection_dataset_dicts(
cfg.DATASETS.TRAIN[0])
# add proposal boxes
for i, s in enumerate(dataset_dicts):
s["proposal_boxes"] = np.array(
[ann["bbox"] for ann in dataset_dicts[i]["annotations"]]
) # np.array([[xmin, ymin, xmax, ymax],[xmin, ymin, xmax, ...], ...]) # kx4 matrix for k proposed bounding boxes
s["proposal_objectness_logits"] = np.full(
(s["proposal_boxes"].shape[0], ),
10) # logit of 10 is 99.999...%
s["proposal_bbox_mode"] = detectron2.structures.BoxMode.XYWH_ABS # 1 # (x0, y0, w, h) in absolute floating points coordinates
print("Proposal boxes added.")
return build_detection_train_loader(
dataset_dicts,
mapper=DatasetMapper(is_train=True,
augmentations=[],
image_format=cfg.INPUT.FORMAT,
precomputed_proposal_topk=500),
total_batch_size=cfg.SOLVER.IMS_PER_BATCH,
aspect_ratio_grouping=cfg.DATALOADER.ASPECT_RATIO_GROUPING,
num_workers=cfg.DATALOADER.NUM_WORKERS)
def build_detection_val_loader(cfg,
dataset_name,
total_batch_size,
mapper=None):
"""
Similar to `build_detection_train_loader`.
But this function uses the given `dataset_name` argument (instead of the names in cfg),
and uses batch size 1.
Args:
cfg: a detectron2 CfgNode
dataset_name (str): a name of the dataset that's available in the DatasetCatalog
mapper (callable): a callable which takes a sample (dict) from dataset
and returns the format to be consumed by the model.
By default it will be `DatasetMapper(cfg, False)`.
Returns:
DataLoader: a torch DataLoader, that loads the given detection
dataset, with test-time transformation and batching.
"""
world_size = comm.get_world_size()
assert (
total_batch_size > 0 and total_batch_size % world_size == 0
), "Total batch size ({}) must be divisible by the number of gpus ({}).".format(
total_batch_size, world_size)
batch_size = total_batch_size // world_size
dataset_dicts = get_detection_dataset_dicts(
[dataset_name],
filter_empty=False,
proposal_files=[
cfg.DATASETS.PROPOSAL_FILES_TEST[list(
cfg.DATASETS.TEST).index(dataset_name)]
] if cfg.MODEL.LOAD_PROPOSALS else None,
)
dataset = DatasetFromList(dataset_dicts)
if mapper is None:
mapper = DatasetMapper(cfg, True)
dataset = MapDataset(dataset, mapper)
# sampler = InferenceSampler(len(dataset))
sampler = DistributedSampler(dataset, shuffle=False)
# logger.info("Start Computing Validation Loss on {} images".format(len(dataset)))
# drop_last so the batch always have the same size
batch_sampler = torch.utils.data.sampler.BatchSampler(sampler,
batch_size,
drop_last=False)
# batch_sampler = torch.utils.data.sampler.BatchSampler(sampler, 1, drop_last=False)
data_loader = torch.utils.data.DataLoader(
dataset,
num_workers=cfg.DATALOADER.NUM_WORKERS,
batch_sampler=batch_sampler,
collate_fn=trivial_batch_collator,
)
return data_loader
def build_train_loader(cls, cfg):
"""
Returns:
iterable
It calls :func:`detectron2.data.build_detection_train_loader` with a customized
DatasetMapper, which adds categorical labels as a semantic mask.
"""
mapper = DatasetMapper(cfg, True)
return build_detection_train_loader(cfg, mapper)
def build_train_loader(cls, cfg):
"""
Returns:
iterable
It now calls :func:`detectron2.data.build_detection_train_loader`.
Overwrite it if you'd like a different data loader.
"""
return build_detection_train_loader(cfg,
mapper=DatasetMapper(cfg, True))
def build_detection_test_query_loader(cfg, dataset_name, mapper=None):
"""
Similar to `build_detection_train_loader`.
But this function uses the given `dataset_name` argument (instead of the names in cfg),
and uses batch size 1.
Args:
cfg: a detectron2 CfgNode
dataset_name (str): a name of the dataset that's available in the DatasetCatalog
mapper (callable): a callable which takes a sample (dict) from dataset
and returns the format to be consumed by the model.
By default it will be `DatasetMapper(cfg, False)`.
Returns:
DataLoader: a torch DataLoader, that loads the given detection
dataset, with test-time transformation and batching.
"""
num_workers = get_world_size()
images_per_batch = cfg.SOLVER.IMS_PER_BATCH
assert (
images_per_batch % num_workers == 0
), "SOLVER.IMS_PER_BATCH ({}) must be divisible by the number of workers ({}).".format(
images_per_batch, num_workers)
assert (
images_per_batch >= num_workers
), "SOLVER.IMS_PER_BATCH ({}) must be larger than the number of workers ({}).".format(
images_per_batch, num_workers)
images_per_worker = images_per_batch // num_workers
dataset_dicts = get_detection_dataset_dicts(
[dataset_name],
filter_empty=False,
proposal_files=[
cfg.DATASETS.PROPOSAL_FILES_TEST[list(
cfg.DATASETS.TEST).index(dataset_name)]
] if cfg.MODEL.LOAD_PROPOSALS else None,
)
dataset = DatasetFromList(dataset_dicts)
if mapper is None:
mapper = DatasetMapper(cfg, False)
dataset = MapDataset(dataset, mapper)
sampler = samplers.InferenceSampler(len(dataset))
# Always use 1 image per worker during inference since this is the
# standard when reporting inference time in papers.
batch_sampler = torch.utils.data.sampler.BatchSampler(sampler,
images_per_worker,
drop_last=False)
data_loader = torch.utils.data.DataLoader(
dataset,
num_workers=cfg.DATALOADER.NUM_WORKERS,
batch_sampler=batch_sampler,
collate_fn=trivial_batch_collator,
)
return data_loader
def build_detection_train_loader(cfg, mapper=None):
"""
A data loader is created by the following steps:
1. Use the dataset names in config to query :class:`DatasetCatalog`, and obtain a list of dicts.
2. Coordinate a random shuffle order shared among all processes (all GPUs)
3. Each process spawn another few workers to process the dicts. Each worker will:
* Map each metadata dict into another format to be consumed by the model.
* Batch them by simply putting dicts into a list.
The batched ``list[mapped_dict]`` is what this dataloader will yield.
Args:
cfg (CfgNode): the config
mapper (callable): a callable which takes a sample (dict) from dataset and
returns the format to be consumed by the model.
By default it will be ``DatasetMapper(cfg, True)``.
Returns:
an infinite iterator of training data
"""
dataset_dicts = get_detection_dataset_dicts(
cfg.DATASETS.TRAIN,
filter_empty=cfg.DATALOADER.FILTER_EMPTY_ANNOTATIONS,
min_keypoints=cfg.MODEL.ROI_KEYPOINT_HEAD.MIN_KEYPOINTS_PER_IMAGE
if cfg.MODEL.KEYPOINT_ON
else 0,
proposal_files=cfg.DATASETS.PROPOSAL_FILES_TRAIN if cfg.MODEL.LOAD_PROPOSALS else None,
)
dataset = DatasetFromList(dataset_dicts, copy=False)
if mapper is None:
mapper = DatasetMapper(cfg, True)
dataset = MapDataset(dataset, mapper)
sampler_name = cfg.DATALOADER.SAMPLER_TRAIN
logger = logging.getLogger(__name__)
logger.info("Using training sampler {}".format(sampler_name))
# TODO avoid if-else?
if sampler_name == "TrainingSampler":
sampler = TrainingSampler(len(dataset))
elif sampler_name == "RepeatFactorTrainingSampler":
repeat_factors = RepeatFactorTrainingSampler.repeat_factors_from_category_frequency(
dataset_dicts, cfg.DATALOADER.REPEAT_THRESHOLD
)
sampler = RepeatFactorTrainingSampler(repeat_factors)
else:
raise ValueError("Unknown training sampler: {}".format(sampler_name))
return build_batch_data_loader(
dataset,
sampler,
cfg.SOLVER.IMS_PER_BATCH,
aspect_ratio_grouping=cfg.DATALOADER.ASPECT_RATIO_GROUPING,
num_workers=cfg.DATALOADER.NUM_WORKERS,
)
def build_hooks(self):
hooks = super().build_hooks()
hooks.insert(-1,LossEvalHook(
self.cfg.TEST.EVAL_PERIOD,
self.model,
build_detection_val_loader(self.cfg ,
self.cfg.DATASETS.TEST[0],
DatasetMapper(self.cfg,True) # label 필요
)
))
return hooks
#--------------------
def build_mapper(cls, cfg, is_train=True):
augs = detection_utils.build_augmentation(cfg, is_train)
#if cfg.INPUT.CROP.ENABLED and is_train:
# augs.insert(0, T.RandomCrop(cfg.INPUT.CROP.TYPE, cfg.INPUT.CROP.SIZE))
# Define a sequence of augmentations: TODO
augs.append(T.RandomBrightness(0.9, 1.1))
augs.append(MyColorAugmentation())
# augs.append(T.RandomRotation([5,10,15,20,25,30], expand=True, center=None))
# T.RandomCrop("absolute", (640, 640)),
# MyCustomResize()
# type: T.Augmentation
return DatasetMapper(cfg, is_train=is_train, augmentations=augs)
def build_detection_semisup_train_loader(cfg, mapper=None):
dataset_dicts = get_detection_dataset_dicts(
cfg.DATASETS.TRAIN,
filter_empty=cfg.DATALOADER.FILTER_EMPTY_ANNOTATIONS,
min_keypoints=cfg.MODEL.ROI_KEYPOINT_HEAD.MIN_KEYPOINTS_PER_IMAGE
if cfg.MODEL.KEYPOINT_ON else 0,
proposal_files=cfg.DATASETS.PROPOSAL_FILES_TRAIN
if cfg.MODEL.LOAD_PROPOSALS else None,
)
# Divide into labeled and unlabeled sets according to supervision percentage
label_dicts, unlabel_dicts = divide_label_unlabel(
dataset_dicts,
cfg.DATALOADER.SUP_PERCENT,
cfg.DATALOADER.RANDOM_DATA_SEED,
cfg.DATALOADER.RANDOM_DATA_SEED_PATH,
)
dataset = DatasetFromList(label_dicts, copy=False)
if mapper is None:
mapper = DatasetMapper(cfg, True)
dataset = MapDataset(dataset, mapper)
sampler_name = cfg.DATALOADER.SAMPLER_TRAIN
logger = logging.getLogger(__name__)
logger.info("Using training sampler {}".format(sampler_name))
if sampler_name == "TrainingSampler":
sampler = TrainingSampler(len(dataset))
elif sampler_name == "RepeatFactorTrainingSampler":
repeat_factors = (
RepeatFactorTrainingSampler.repeat_factors_from_category_frequency(
label_dicts, cfg.DATALOADER.REPEAT_THRESHOLD))
sampler = RepeatFactorTrainingSampler(repeat_factors)
else:
raise ValueError("Unknown training sampler: {}".format(sampler_name))
# list num of labeled and unlabeled
logger.info("Number of training samples " + str(len(dataset)))
logger.info("Supervision percentage " + str(cfg.DATALOADER.SUP_PERCENT))
return build_batch_data_loader(
dataset,
sampler,
cfg.SOLVER.IMS_PER_BATCH,
aspect_ratio_grouping=cfg.DATALOADER.ASPECT_RATIO_GROUPING,
num_workers=cfg.DATALOADER.NUM_WORKERS,
)
def build_train_loader(cls, cfg):
"""
Returns:
iterable
It calls :func:`detectron2.data.build_detection_train_loader` with a customized
DatasetMapper, which adds categorical labels as a semantic mask.
"""
register_coco_instances("fruits_nuts", {},
"./fruit_nuts/trainval.json",
"./fruit_nuts/images")
fruits_nuts_metadata = MetadataCatalog.get("fruits_nuts")
mapper = DatasetMapper(cfg, True)
return build_detection_train_loader(cfg, mapper)
def build_weighted_detection_train_loader(cfg: CfgNode, mapper=None):
dataset_repeat_factors = get_train_datasets_repeat_factors(cfg)
# OrderedDict to guarantee order of values() consistent with repeat factors
dataset_name_to_dicts = OrderedDict(
{
name: get_detection_dataset_dicts(
[name],
filter_empty=cfg.DATALOADER.FILTER_EMPTY_ANNOTATIONS,
min_keypoints=cfg.MODEL.ROI_KEYPOINT_HEAD.MIN_KEYPOINTS_PER_IMAGE
if cfg.MODEL.KEYPOINT_ON
else 0,
proposal_files=cfg.DATASETS.PROPOSAL_FILES_TRAIN
if cfg.MODEL.LOAD_PROPOSALS
else None,
)
for name in cfg.DATASETS.TRAIN
}
)
# Repeat factor for every sample in the dataset
repeat_factors = [
[dataset_repeat_factors[dsname]] * len(dataset_name_to_dicts[dsname])
for dsname in cfg.DATASETS.TRAIN
]
repeat_factors = list(itertools.chain.from_iterable(repeat_factors))
dataset_dicts = dataset_name_to_dicts.values()
dataset_dicts = list(itertools.chain.from_iterable(dataset_dicts))
dataset = DatasetFromList(dataset_dicts, copy=False)
if mapper is None:
mapper = DatasetMapper(cfg, True)
dataset = MapDataset(dataset, mapper)
logger.info(
"Using WeightedTrainingSampler with repeat_factors={}".format(
cfg.DATASETS.TRAIN_REPEAT_FACTOR
)
)
sampler = RepeatFactorTrainingSampler(torch.tensor(repeat_factors))
return build_batch_data_loader(
dataset,
sampler,
cfg.SOLVER.IMS_PER_BATCH,
aspect_ratio_grouping=cfg.DATALOADER.ASPECT_RATIO_GROUPING,
num_workers=cfg.DATALOADER.NUM_WORKERS,
)
def build_detection_train_loader(cfg):
"""Builds a data loader for the baseline trainer with support of training on the subset of labeled data only.
Most of code comes from `d2.data.build.build_detection_train_loader()`, see it for more details.
"""
# CSD: check config is supported
assert cfg.DATALOADER.SAMPLER_TRAIN == "TrainingSampler", "Unsupported training sampler: {}".format(
cfg.DATALOADER.SAMPLER_TRAIN)
# Original code
dataset = get_detection_dataset_dicts(
cfg.DATASETS.TRAIN,
filter_empty=cfg.DATALOADER.FILTER_EMPTY_ANNOTATIONS,
min_keypoints=cfg.MODEL.ROI_KEYPOINT_HEAD.MIN_KEYPOINTS_PER_IMAGE
if cfg.MODEL.KEYPOINT_ON else 0,
proposal_files=cfg.DATASETS.PROPOSAL_FILES_TRAIN
if cfg.MODEL.LOAD_PROPOSALS else None,
)
# CSD: subsample the dataset if needed
dataset = check_subsample_dataset(dataset, cfg)
if comm.is_main_process(): # Log counts
logger = setup_logger(name=__name__)
logger.debug("Number of images in the dataset: {}".format(
len(dataset)))
_log_api_usage("dataset." + cfg.DATASETS.TRAIN[0])
# Original code
mapper = DatasetMapper(cfg, True)
sampler = TrainingSampler(len(dataset))
dataset = DatasetFromList(dataset, copy=False)
dataset = MapDataset(dataset, mapper)
sampler = TrainingSampler(len(dataset))
assert isinstance(sampler, torch.utils.data.sampler.Sampler)
return build_batch_data_loader(
dataset,
sampler,
cfg.SOLVER.IMS_PER_BATCH,
aspect_ratio_grouping=cfg.DATALOADER.ASPECT_RATIO_GROUPING,
num_workers=cfg.DATALOADER.NUM_WORKERS,
)
def build_custom_train_loader(cfg, mapper=None):
"""
Modified from detectron2.data.build.build_custom_train_loader, but supports
different samplers
"""
dataset_dicts = get_detection_dataset_dicts(
cfg.DATASETS.TRAIN,
filter_empty=cfg.DATALOADER.FILTER_EMPTY_ANNOTATIONS,
min_keypoints=cfg.MODEL.ROI_KEYPOINT_HEAD.MIN_KEYPOINTS_PER_IMAGE
if cfg.MODEL.KEYPOINT_ON else 0,
proposal_files=cfg.DATASETS.PROPOSAL_FILES_TRAIN
if cfg.MODEL.LOAD_PROPOSALS else None,
)
dataset = DatasetFromList(dataset_dicts, copy=False)
if mapper is None:
mapper = DatasetMapper(cfg, True)
dataset = MapDataset(dataset, mapper)
sampler_name = cfg.DATALOADER.SAMPLER_TRAIN
logger = logging.getLogger(__name__)
logger.info("Using training sampler {}".format(sampler_name))
# TODO avoid if-else?
if sampler_name == "TrainingSampler":
sampler = TrainingSampler(len(dataset))
elif sampler_name == "RepeatFactorTrainingSampler":
repeat_factors = RepeatFactorTrainingSampler.repeat_factors_from_category_frequency(
dataset_dicts, cfg.DATALOADER.REPEAT_THRESHOLD)
sampler = RepeatFactorTrainingSampler(repeat_factors)
elif sampler_name == "ClassAwareSampler":
sampler = ClassAwareSampler(dataset_dicts)
else:
raise ValueError("Unknown training sampler: {}".format(sampler_name))
return build_batch_data_loader(
dataset,
sampler,
cfg.SOLVER.IMS_PER_BATCH,
aspect_ratio_grouping=cfg.DATALOADER.ASPECT_RATIO_GROUPING,
num_workers=cfg.DATALOADER.NUM_WORKERS,
)
def build_classification_test_loader(cfg, dataset_name, mapper=None):
"""
Similar to `build_detection_train_loader`.
But this function uses the given `dataset_name` argument (instead of the names in cfg),
and uses batch size 1.
Args:
cfg: a detectron2 CfgNode
dataset_name (str): a name of the dataset that's available in the DatasetCatalog
mapper (callable): a callable which takes a sample (dict) from dataset
and returns the format to be consumed by the model.
By default it will be `DatasetMapper(cfg, False)`.
Returns:
DataLoader: a torch DataLoader, that loads the given detection
dataset, with test-time transformation and batching.
"""
dataset_dicts = get_classification_dataset_dicts([dataset_name])
dataset = DatasetFromList(dataset_dicts)
if mapper is None:
mapper = DatasetMapper(cfg, False)
dataset = MapDataset(dataset, mapper)
sampler = samplers.InferenceSampler(len(dataset))
# Always use 1 image per worker during inference since this is the
# standard when reporting inference time in papers.
batch_sampler = torch.utils.data.sampler.BatchSampler(sampler,
1,
drop_last=False)
data_loader = torch.utils.data.DataLoader(
dataset,
num_workers=cfg.DATALOADER.NUM_WORKERS,
batch_sampler=batch_sampler,
collate_fn=trivial_batch_collator,
)
return data_loader
def my_build_detection_train_loader(cfg,
mapper=None,
isShuffleData=True,
curriculum_fraction=0):
"""
A data loader is created by the following steps:
1. Use the dataset names in config to query :class:`DatasetCatalog`, and obtain a list of dicts.
2. Start workers to work on the dicts. Each worker will:
* Map each metadata dict into another format to be consumed by the model.
* Batch them by simply putting dicts into a list.
The batched ``list[mapped_dict]`` is what this dataloader will return.
Args:
cfg (CfgNode): the config
mapper (callable): a callable which takes a sample (dict) from dataset and
returns the format to be consumed by the model.
By default it will be `DatasetMapper(cfg, True)`.
Returns:
an infinite iterator of training data
"""
num_workers = get_world_size()
images_per_batch = cfg.SOLVER.IMS_PER_BATCH
assert (
images_per_batch % num_workers == 0
), "SOLVER.IMS_PER_BATCH ({}) must be divisible by the number of workers ({}).".format(
images_per_batch, num_workers)
assert (
images_per_batch >= num_workers
), "SOLVER.IMS_PER_BATCH ({}) must be larger than the number of workers ({}).".format(
images_per_batch, num_workers)
images_per_worker = images_per_batch // num_workers
dataset_dicts = get_detection_dataset_dicts(
cfg.DATASETS.TRAIN,
filter_empty=cfg.DATALOADER.FILTER_EMPTY_ANNOTATIONS,
min_keypoints=cfg.MODEL.ROI_KEYPOINT_HEAD.MIN_KEYPOINTS_PER_IMAGE
if cfg.MODEL.KEYPOINT_ON else 0,
proposal_files=cfg.DATASETS.PROPOSAL_FILES_TRAIN
if cfg.MODEL.LOAD_PROPOSALS else None,
)
dataset = DatasetFromList(dataset_dicts, copy=False)
if mapper is None:
mapper = DatasetMapper(cfg, True)
dataset = MapDataset(dataset, mapper)
sampler_name = cfg.DATALOADER.SAMPLER_TRAIN
logger = logging.getLogger(__name__)
logger.info("Using training sampler {}".format(sampler_name))
if sampler_name == "TrainingSampler":
# If the fraction is the default 0, use the whole dataset
if (curriculum_fraction == 0):
sampler = samplers.TrainingSampler(len(dataset),
shuffle=isShuffleData)
# If the fraction is not 0, then take that fraction of the dataset as a subset
else:
new_len = int(round(len(dataset) * curriculum_fraction))
sampler = samplers.TrainingSampler(new_len, shuffle=isShuffleData)
elif sampler_name == "RepeatFactorTrainingSampler":
sampler = samplers.RepeatFactorTrainingSampler(
dataset_dicts, cfg.DATALOADER.REPEAT_THRESHOLD)
else:
raise ValueError("Unknown training sampler: {}".format(sampler_name))
if cfg.DATALOADER.ASPECT_RATIO_GROUPING:
data_loader = torch.utils.data.DataLoader(
dataset,
sampler=sampler,
num_workers=cfg.DATALOADER.NUM_WORKERS,
batch_sampler=None,
collate_fn=operator.itemgetter(
0), # don't batch, but yield individual elements
worker_init_fn=worker_init_reset_seed,
) # yield individual mapped dict
data_loader = AspectRatioGroupedDataset(data_loader, images_per_worker)
else:
batch_sampler = torch.utils.data.sampler.BatchSampler(
sampler, images_per_worker, drop_last=True)
# drop_last so the batch always have the same size
data_loader = torch.utils.data.DataLoader(
dataset,
num_workers=cfg.DATALOADER.NUM_WORKERS,
batch_sampler=batch_sampler,
collate_fn=trivial_batch_collator,
worker_init_fn=worker_init_reset_seed,
)
return data_loader
def get_lvis_train_dataloader(cfg, h, w):
default_mapper = DatasetMapper(cfg, is_train=True)
mapper = partial(wrapper, default_m=default_mapper, h=h, w=w)
dl = build_detection_train_loader(cfg, mapper=mapper)
return dl
def build_hooks(self):
cfg = self.cfg.clone()
cfg.defrost()
cfg.DATALOADER.NUM_WORKERS = 0 # save some memory and time for PreciseBN
ret = [
hooks.IterationTimer(),
hooks.LRScheduler(self.optimizer, self.scheduler),
hooks.PreciseBN(
# Run at the same freq as (but before) evaluation.
cfg.TEST.EVAL_PERIOD,
self.model,
# Build a new data loader to not affect training
self.build_train_loader(cfg),
cfg.TEST.PRECISE_BN.NUM_ITER,
) if cfg.TEST.PRECISE_BN.ENABLED and get_bn_modules(self.model)
else None,
]
# Do PreciseBN before checkpointer, because it updates the model and need to
# be saved by checkpointer.
# This is not always the best: if checkpointing has a different frequency,
# some checkpoints may have more precise statistics than others.
if comm.is_main_process():
ret.append(
hooks.PeriodicCheckpointer(self.checkpointer,
cfg.SOLVER.CHECKPOINT_PERIOD))
def test_and_save_results_student():
self._last_eval_results_student = self.test(self.cfg, self.model)
_last_eval_results_student = {
k + "_student": self._last_eval_results_student[k]
for k in self._last_eval_results_student.keys()
}
return _last_eval_results_student
def test_and_save_results_teacher():
self._last_eval_results_teacher = self.test(
self.cfg, self.model_teacher)
return self._last_eval_results_teacher
ret.append(
hooks.EvalHook(cfg.TEST.EVAL_PERIOD,
test_and_save_results_student))
ret.append(
hooks.EvalHook(cfg.TEST.EVAL_PERIOD,
test_and_save_results_teacher))
if cfg.TEST.VAL_LOSS: # default is True # save training time if not applied
ret.append(
LossEvalHook(
cfg.TEST.EVAL_PERIOD,
self.model,
build_detection_test_loader(
self.cfg,
self.cfg.DATASETS.TEST[0],
DatasetMapper(self.cfg, True),
),
model_output="loss_proposal",
model_name="student",
))
ret.append(
LossEvalHook(
cfg.TEST.EVAL_PERIOD,
self.model_teacher,
build_detection_test_loader(
self.cfg,
self.cfg.DATASETS.TEST[0],
DatasetMapper(self.cfg, True),
),
model_output="loss_proposal",
model_name="",
))
if comm.is_main_process():
# run writers in the end, so that evaluation metrics are written
ret.append(hooks.PeriodicWriter(self.build_writers(), period=20))
return ret
def get_lvis_test_dataloader(cfg, h, w):
default_mapper = DatasetMapper(cfg, is_train=False)
mapper = partial(wrapper, default_m=default_mapper, h=h, w=w)
dl = build_detection_test_loader(cfg, 'lvis_v0.5_val', mapper=mapper)
return dl
def build_classification_train_loader(cfg, mapper=None, multiplier=1):
"""
A data loader is created by the following steps:
1. Use the dataset names in config to query :class:`DatasetCatalog`, and obtain a list of dicts.
2. Start workers to work on the dicts. Each worker will:
* Map each metadata dict into another format to be consumed by the model.
* Batch them by simply putting dicts into a list.
The batched ``list[mapped_dict]`` is what this dataloader will return.
Args:
cfg (CfgNode): the config
mapper (callable): a callable which takes a sample (dict) from dataset and
returns the format to be consumed by the model.
By default it will be `DatasetMapper(cfg, True)`.
Returns:
an infinite iterator of training data
"""
num_workers = get_world_size()
images_per_batch = cfg.SOLVER.IMS_PER_BATCH
sample_num = cfg.DATASETS.WEAK_CLASSIFIER_SAMPLE_NUM
assert (
images_per_batch % num_workers == 0
), "SOLVER.IMS_PER_BATCH ({}) must be divisible by the number of workers ({}).".format(
images_per_batch, num_workers)
assert (
images_per_batch >= num_workers
), "SOLVER.IMS_PER_BATCH ({}) must be larger than the number of workers ({}).".format(
images_per_batch, num_workers)
images_per_worker = images_per_batch // num_workers
images_per_worker = int(images_per_worker * multiplier)
if sample_num > 0:
np.random.seed(cfg.DATASETS.SAMPLE_SEED)
print("Setting sampling seed:", cfg.DATASETS.SAMPLE_SEED)
dataset_names = cfg.DATASETS.CLASSIFIER_TRAIN
if isinstance(dataset_names, str):
dataset_names = [dataset_names]
dataset_dicts = [
DatasetCatalog.get(dataset_name) for dataset_name in dataset_names
]
dataset_dicts = list(itertools.chain.from_iterable(dataset_dicts))
label_to_annotation_dict = {
e: []
for e in range(cfg.MODEL.ROI_HEADS.NUM_CLASSES)
}
for e in dataset_dicts:
per_label_record = {}
for ann in e['annotations']:
if ann['category_id'] in per_label_record:
per_label_record[ann['category_id']]['annotations'].append(
ann)
else:
record = copy.deepcopy(e)
# filter annotations
annotations_filtered = [ann]
record['annotations'] = annotations_filtered
per_label_record[ann['category_id']] = record
for key in per_label_record.keys():
label_to_annotation_dict[key].append(per_label_record[key])
label_to_annotation_dict_sampled = {}
for id_class, ann_list in label_to_annotation_dict.items():
if id_class in cfg.DATASETS.FEWSHOT.BASE_CLASSES_ID:
if not cfg.DATASETS.OVER_SAMPLE:
if cfg.DATASETS.BASE_MULTIPLIER > 0:
try:
ann_list_sampled = np.random.choice(
ann_list,
size=int(sample_num *
cfg.DATASETS.BASE_MULTIPLIER),
replace=False)
except:
ann_list_sampled = np.random.choice(
ann_list,
size=int(sample_num *
cfg.DATASETS.BASE_MULTIPLIER),
replace=True)
else:
ann_list_sampled = ann_list
else:
print("BASE OVER SAMPLING")
ann_list_sampled = ann_list
label_to_annotation_dict_sampled[id_class] = ann_list_sampled
else:
if not cfg.DATASETS.OVER_SAMPLE:
if cfg.DATASETS.BASE_MULTIPLIER > 0:
try:
ann_list_sampled = np.random.choice(
ann_list, size=sample_num, replace=False)
except:
ann_list_sampled = np.random.choice(
ann_list, size=sample_num, replace=True)
if cfg.DATASETS.NOVEL_MULTIPLER > 0:
ann_list_sampled = np.repeat(
ann_list_sampled, cfg.DATASETS.NOVEL_MULTIPLER)
else:
ann_list_sampled = []
else:
try:
ann_list_sampled_temp = np.random.choice(
ann_list, size=sample_num, replace=False)
if not cfg.DATASETS.SAMPLE_WITH_REPLACEMENT:
print("OVER SAMPLING")
ann_list_sampled = np.random.choice(
ann_list_sampled_temp,
size=len(ann_list),
replace=True)
else:
ann_list_sampled_temp = np.random.choice(
ann_list, size=sample_num, replace=False)
num_repeat = len(ann_list) // len(
ann_list_sampled_temp)
num_remainder = len(ann_list) % len(
ann_list_sampled_temp)
ann_list_sampled = np.repeat(
ann_list_sampled_temp, num_repeat)
if num_remainder > 0:
ann_list_sampled = np.hstack(
(ann_list_sampled,
np.random.choice(ann_list_sampled_temp,
size=num_remainder,
replace=True)))
print("OVER SAMPLING FIXED NEW",
len(ann_list_sampled_temp),
len(ann_list_sampled))
except:
ann_list_sampled = ann_list
label_to_annotation_dict_sampled[id_class] = ann_list_sampled
dataset_dicts = []
for k, v in label_to_annotation_dict_sampled.items():
dataset_dicts.extend(v)
DatasetCatalog.register("classifier_train_sampled",
lambda: dataset_dicts)
MetadataCatalog.get("classifier_train_sampled").set(
thing_classes=MetadataCatalog.get(dataset_names[0]).thing_classes,
evaluator_type='pascal_voc')
dataset_name = ('classifier_train_sampled', )
# print([(x['image_id'], len(x['annotations'])) for x in dataset_dicts[:50]])
# print_instances_class_histogram_1(dataset_dicts, MetadataCatalog.get(dataset_names[0]).thing_classes)
else:
dataset_name = cfg.DATASETS.CLASSIFIER_TRAIN
dataset_dicts = get_detection_dataset_dicts(
dataset_name,
filter_empty=cfg.DATALOADER.FILTER_EMPTY_ANNOTATIONS,
min_keypoints=cfg.MODEL.ROI_KEYPOINT_HEAD.MIN_KEYPOINTS_PER_IMAGE
if cfg.MODEL.KEYPOINT_ON else 0,
proposal_files=cfg.DATASETS.PROPOSAL_FILES_CLASSIFIER_TRAIN
if cfg.MODEL.LOAD_PROPOSALS else None)
dataset = DatasetFromList(dataset_dicts, copy=False)
# # filtering
# dataset_filtered = []
# for sample in dataset:
# e_class_ids = set([e['category_id'] for e in sample['annotations']])
# for e_class_ids_ in e_class_ids:
# if e_class_ids_ in cfg.DATASETS.FEWSHOT.NOVEL_CLASSES_ID:
# dataset_filtered.append(sample)
# break
# dataset = dataset_filtered
if mapper is None:
mapper = DatasetMapper(cfg, True)
dataset = MapDataset(dataset, mapper)
sampler_name = cfg.DATALOADER.SAMPLER_TRAIN
logger = logging.getLogger(__name__)
logger.info("Using training sampler {}".format(sampler_name))
if sampler_name == "TrainingSampler":
sampler = samplers.TrainingSampler(len(dataset))
elif sampler_name == "RepeatFactorTrainingSampler":
sampler = samplers.RepeatFactorTrainingSampler(
dataset_dicts, cfg.DATALOADER.REPEAT_THRESHOLD)
else:
raise ValueError("Unknown training sampler: {}".format(sampler_name))
if cfg.DATALOADER.ASPECT_RATIO_GROUPING:
data_loader = torch.utils.data.DataLoader(
dataset,
sampler=sampler,
num_workers=cfg.DATALOADER.NUM_WORKERS,
batch_sampler=None,
collate_fn=operator.itemgetter(
0), # don't batch, but yield individual elements
worker_init_fn=worker_init_reset_seed,
) # yield individual mapped dict
data_loader = AspectRatioGroupedDataset(data_loader, images_per_worker)
else:
batch_sampler = torch.utils.data.sampler.BatchSampler(
sampler, images_per_worker, drop_last=True)
# drop_last so the batch always have the same size
data_loader = torch.utils.data.DataLoader(
dataset,
num_workers=cfg.DATALOADER.NUM_WORKERS,
batch_sampler=batch_sampler,
collate_fn=trivial_batch_collator,
worker_init_fn=worker_init_reset_seed,
)
return data_loader
def build_detection_query_loader(cfg,
dataset_names_tuple,
dataset_proposal_files_tuple,
mapper=None,
is_train=True):
"""
- Modified from detectron2.data.build_detection_train_loader
- `dataset_names_tuple`: since we need to provide dataset names using
different variables (meta-setup) and cfg could not be modified
(CfgNode is immutable)
- `is_train`: will create duplicated entries according to annotations
So if an image contains five annotations, it will appear in the dataset
five times with different annotations
"""
num_workers = get_world_size()
images_per_batch = cfg.SOLVER.IMS_PER_BATCH
assert (
images_per_batch % num_workers == 0
), "SOLVER.IMS_PER_BATCH ({}) must be divisible by the number of workers ({}).".format(
images_per_batch, num_workers)
assert (
images_per_batch >= num_workers
), "SOLVER.IMS_PER_BATCH ({}) must be larger than the number of workers ({}).".format(
images_per_batch, num_workers)
images_per_worker = images_per_batch // num_workers
dataset_dicts = get_detection_dataset_dicts(
dataset_names_tuple,
filter_empty=cfg.DATALOADER.FILTER_EMPTY_ANNOTATIONS,
min_keypoints=cfg.MODEL.ROI_KEYPOINT_HEAD.MIN_KEYPOINTS_PER_IMAGE
if cfg.MODEL.KEYPOINT_ON else 0,
proposal_files=dataset_proposal_files_tuple
if cfg.MODEL.LOAD_PROPOSALS else None,
)
logger = logging.getLogger(__name__)
# Train: split annotations class-wise
if is_train:
print(
"Query dataset num instances before annotation-wise duplication: {}"
.format(len(dataset_dicts)))
dataset_dicts = duplicate_data_acc_to_annotation_categories(
dataset_dicts)
print(
"Query dataset num instances after annotation-wise duplication: {}"
.format(len(dataset_dicts)))
dataset = DatasetFromList(dataset_dicts, copy=False)
if mapper is None:
mapper = DatasetMapper(cfg, is_train=is_train)
dataset = MapDataset(dataset, mapper)
sampler_name = cfg.DATALOADER.SAMPLER_TRAIN
logger.info("Using training sampler {}".format(sampler_name))
if sampler_name == "TrainingSampler":
sampler = samplers.TrainingSampler(len(dataset))
elif sampler_name == "RepeatFactorTrainingSampler":
sampler = samplers.RepeatFactorTrainingSampler(
dataset_dicts, cfg.DATALOADER.REPEAT_THRESHOLD)
else:
raise ValueError("Unknown training sampler: {}".format(sampler_name))
if cfg.DATALOADER.ASPECT_RATIO_GROUPING:
data_loader = torch.utils.data.DataLoader(
dataset,
sampler=sampler,
num_workers=cfg.DATALOADER.NUM_WORKERS,
batch_sampler=None,
collate_fn=operator.itemgetter(
0), # don't batch, but yield individual elements
worker_init_fn=worker_init_reset_seed,
) # yield individual mapped dict
data_loader = AspectRatioGroupedDataset(data_loader, images_per_worker)
else:
batch_sampler = torch.utils.data.sampler.BatchSampler(
sampler, images_per_worker, drop_last=True)
# drop_last so the batch always have the same size
data_loader = torch.utils.data.DataLoader(
dataset,
num_workers=cfg.DATALOADER.NUM_WORKERS,
batch_sampler=batch_sampler,
collate_fn=trivial_batch_collator,
worker_init_fn=worker_init_reset_seed,
)
return data_loader
def build_detection_train_loader_drop_ids(cfg, drop_image_ids, mapper=None):
"""
A rewrite for the detectron2.data.build.build_detection_train_loader
function, as it supports drop images of certian_ids specified by
drop_image_ids.
Returns:
an infinite iterator of training data
"""
num_workers = get_world_size()
images_per_batch = cfg.SOLVER.IMS_PER_BATCH
assert (
images_per_batch % num_workers == 0
), "SOLVER.IMS_PER_BATCH ({}) must be divisible by the number of workers ({}).".format(
images_per_batch, num_workers)
assert (
images_per_batch >= num_workers
), "SOLVER.IMS_PER_BATCH ({}) must be larger than the number of workers ({}).".format(
images_per_batch, num_workers)
images_per_worker = images_per_batch // num_workers
dataset_dicts = get_detection_dataset_dicts(
cfg.DATASETS.TRAIN,
filter_empty=cfg.DATALOADER.FILTER_EMPTY_ANNOTATIONS,
min_keypoints=cfg.MODEL.ROI_KEYPOINT_HEAD.MIN_KEYPOINTS_PER_IMAGE
if cfg.MODEL.KEYPOINT_ON else 0,
proposal_files=cfg.DATASETS.PROPOSAL_FILES_TRAIN
if cfg.MODEL.LOAD_PROPOSALS else None,
)
dataset = DatasetFromList(
[dd for dd in dataset_dicts if dd['image_id'] not in drop_image_ids],
copy=False)
if mapper is None:
mapper = DatasetMapper(cfg, True)
dataset = MapDataset(dataset, mapper)
sampler_name = cfg.DATALOADER.SAMPLER_TRAIN
logger = logging.getLogger(__name__)
logger.info("Using training sampler {}".format(sampler_name))
if sampler_name == "TrainingSampler":
sampler = samplers.TrainingSampler(len(dataset))
elif sampler_name == "RepeatFactorTrainingSampler":
sampler = samplers.RepeatFactorTrainingSampler(
dataset_dicts, cfg.DATALOADER.REPEAT_THRESHOLD)
else:
raise ValueError("Unknown training sampler: {}".format(sampler_name))
if cfg.DATALOADER.ASPECT_RATIO_GROUPING:
data_loader = torch.utils.data.DataLoader(
dataset,
sampler=sampler,
num_workers=cfg.DATALOADER.NUM_WORKERS,
batch_sampler=None,
collate_fn=operator.itemgetter(
0), # don't batch, but yield individual elements
worker_init_fn=worker_init_reset_seed,
) # yield individual mapped dict
data_loader = AspectRatioGroupedDataset(data_loader, images_per_worker)
else:
batch_sampler = torch.utils.data.sampler.BatchSampler(
sampler, images_per_worker, drop_last=True)
# drop_last so the batch always have the same size
data_loader = torch.utils.data.DataLoader(
dataset,
num_workers=cfg.DATALOADER.NUM_WORKERS,
batch_sampler=batch_sampler,
collate_fn=trivial_batch_collator,
worker_init_fn=worker_init_reset_seed,
)
return data_loader
def test_recognition(model_yaml, checkpoint, dataset, annotations, imagedir, outdir=None, use_rpn=False, record_individual_scores=False):
"""
Computes detections and uses them to compute recognition accuracies.
Arguments:
model_yaml: Path to model config in yaml format.
dataset: Dataset name, used to name output files.
annotations: Path to ground truth annotations (json file with COCO-style annotations).
imagedir: Path to image directory.
outdir: Directory where output files are stored. When None is passed, the output directory specified in the model's config file is used.
use_rpn: If True, the region proposal network of the model is used instead of bounding boxes from the ground truth.
"""
# Register testset
register_coco_instances(dataset, {}, annotations, imagedir)
# Load model
cfg = get_cfg()
with open(model_yaml) as f:
cfg = cfg.load_cfg(f)
print("Numer of classes: {}".format(cfg.MODEL.ROI_HEADS.NUM_CLASSES))
cfg.DATASETS.TEST = (dataset,)
model = build_model(cfg)
# Create outdir
if outdir == None:
outdir = cfg.OUTPUT_DIR
pathlib.Path(outdir).mkdir(exist_ok=True)
print("Evaluation output directory: " + outdir)
# Create data loader
if not use_rpn:
# returns a list of dicts. Every entry in the list corresponds to one sample, represented by a dict.
dataset_dicts = detectron2.data.get_detection_dataset_dicts(dataset)
# add proposal boxes
for i, s in enumerate(dataset_dicts):
s["proposal_boxes"] = np.array([ ann["bbox"] for ann in dataset_dicts[i]["annotations"] ]) # np.array([[xmin, ymin, xmax, ymax],[xmin, ymin, xmax, ...], ...]) # kx4 matrix for k proposed bounding boxes
s["proposal_objectness_logits"] = np.full((s["proposal_boxes"].shape[0],), 10) # logit of 10 is 99.999...%
s["proposal_bbox_mode"] = detectron2.structures.BoxMode.XYWH_ABS # 1 # (x0, y0, w, h) in absolute floating points coordinates
print("Proposal boxes added.")
model.proposal_generator = None # deactivate such that precomputed proposals are used
print("Region proposal deactivated, ground truth bounding boxes are used.")
val_loader = build_detection_test_loader(dataset_dicts, mapper=DatasetMapper(is_train=False, augmentations=[], image_format= cfg.INPUT.FORMAT, precomputed_proposal_topk=500))
else:
val_loader = build_detection_test_loader(cfg, dataset)
# load model state (weights) from checkpoint
DetectionCheckpointer(model).load(checkpoint)
# evaluate detections
evaluator = COCOEvaluator(dataset, ("bbox",), False, output_dir=outdir)
result = inference_on_dataset(model, val_loader, evaluator)
print_csv_format(result)
with open(os.path.join(outdir, "evaluation_" + dataset + ".json"), "w") as outfile:
json.dump(result, outfile)
# compute accuracies
detection2accuracy(detections=os.path.join(outdir,"coco_instances_results.json"), groundtruth=annotations, outdir=outdir, record_individual_scores=record_individual_scores)
def build_train_loader(cls, cfg):
return build_detection_train_loader(cfg, mapper=DatasetMapper(cfg, True, augmentations=build_train_aug(cfg)))
def build_test_loader(cls, cfg, dataset_name):
return build_detection_test_loader(cfg, dataset_name, mapper=DatasetMapper(cfg, False))
