def register_lvis_instances(name, metadata, json_file, image_root):
"""
Register a dataset in LVIS's json annotation format for instance detection.
Args:
name (str): a name that identifies the dataset, e.g. "lvis_v0.5_train".
metadata (dict): extra metadata associated with this dataset. It can be an empty dict.
json_file (str): path to the json instance annotation file.
image_root (str): directory which contains all the images.
"""
DatasetCatalog.register(
name, lambda: load_lvis_json(json_file, image_root, name))
MetadataCatalog.get(name).set(json_file=json_file,
image_root=image_root,
evaluator_type="lvis",
**metadata)
def register_meta_pascal_voc(
name, metadata, dirname, split, year, keepclasses, sid):
if keepclasses.startswith('base_novel'):
thing_classes = metadata["thing_classes"][sid]
elif keepclasses.startswith('base'):
thing_classes = metadata["base_classes"][sid]
elif keepclasses.startswith('novel'):
thing_classes = metadata["novel_classes"][sid]
DatasetCatalog.register(
name, lambda: load_filtered_voc_instances(
name, dirname, split, thing_classes)
)
MetadataCatalog.get(name).set(
thing_classes=thing_classes, dirname=dirname, year=year, split=split,
base_classes=metadata["base_classes"][sid],
novel_classes=metadata["novel_classes"][sid]
)
def register_meta_coco(name, metadata, imgdir, annofile):
DatasetCatalog.register(
name,
lambda: load_coco_json(annofile, imgdir, metadata, name),
)
if '_base' in name or '_novel' in name:
split = 'base' if '_base' in name else 'novel'
metadata['thing_dataset_id_to_contiguous_id'] = \
metadata['{}_dataset_id_to_contiguous_id'.format(split)]
metadata['thing_classes'] = metadata['{}_classes'.format(split)]
MetadataCatalog.get(name).set(
json_file=annofile,
image_root=imgdir,
evaluator_type="coco",
dirname="datasets/coco",
**metadata,
)
def register_coco_instances(name, metadata, json_file, image_root):
"""
Register a dataset in COCO's json annotation format for instance detection.
This is an example of how to register a new dataset.
You can do something similar to this function, to register new datasets.
Args:
name (str): the name that identifies a dataset, e.g. "coco_2014_train".
metadata (dict): extra metadata associated with this dataset. You can
leave it as an empty dict.
json_file (str): path to the json instance annotation file.
image_root (str): directory which contains all the images.
"""
# 1. register a function which returns dicts
DatasetCatalog.register(name, lambda: load_coco_json(json_file, image_root, name))
# 2. Optionally, add metadata about this dataset,
# since they might be useful in evaluation, visualization or logging
MetadataCatalog.get(name).set(
json_file=json_file, image_root=image_root, evaluator_type="coco", **metadata
)
parser.add_argument("--input", required=True, help="JSON file produced by the model")
parser.add_argument("--output", required=True, help="output directory")
parser.add_argument("--dataset", help="name of the dataset", default="coco_2017_val")
parser.add_argument("--conf-threshold", default=0.5, type=float, help="confidence threshold")
args = parser.parse_args()
logger = setup_logger()
with PathManager.open(args.input, "r") as f:
predictions = json.load(f)
pred_by_image = defaultdict(list)
for p in predictions:
pred_by_image[p["image_id"]].append(p)
dicts = list(DatasetCatalog.get(args.dataset))
metadata = MetadataCatalog.get(args.dataset)
if hasattr(metadata, "thing_dataset_id_to_contiguous_id"):
def dataset_id_map(ds_id):
return metadata.thing_dataset_id_to_contiguous_id[ds_id]
elif "lvis" in args.dataset:
# LVIS results are in the same format as COCO results, but have a different
# mapping from dataset category id to contiguous category id in [0, #categories - 1]
def dataset_id_map(ds_id):
return ds_id - 1
else:
raise ValueError("Unsupported dataset: {}".format(args.dataset))
def register_pascal_voc(name, dirname, split, year):
DatasetCatalog.register(name, lambda: load_voc_instances(dirname, split))
MetadataCatalog.get(name).set(thing_classes=CLASS_NAMES,
dirname=dirname,
year=year,
split=split)
for per_image in batch:
# Pytorch tensor is in (C, H, W) format
img = per_image["image"].permute(1, 2, 0)
if cfg.INPUT.FORMAT == "BGR":
img = img[:, :, [2, 1, 0]]
else:
img = np.asarray(
Image.fromarray(img,
mode=cfg.INPUT.FORMAT).convert("RGB"))
visualizer = Visualizer(img, metadata=metadata, scale=scale)
target_fields = per_image["instances"].get_fields()
labels = [
metadata.thing_classes[i]
for i in target_fields["gt_classes"]
]
vis = visualizer.overlay_instances(
labels=labels,
boxes=target_fields.get("gt_boxes", None),
)
output(vis, str(per_image["image_id"]) + ".jpg")
else:
dicts = list(
chain.from_iterable(
[DatasetCatalog.get(k) for k in cfg.DATASETS.TRAIN]))
for dic in dicts:
img = utils.read_image(dic["file_name"], "RGB")
visualizer = Visualizer(img, metadata=metadata, scale=scale)
vis = visualizer.draw_dataset_dict(dic)
output(vis, os.path.basename(dic["file_name"]))