def test(self):
from cvpods.data import DatasetCatalog, MetadataCatalog # noqa
from cvpods.data.datasets.coco import convert_to_coco_dict, load_coco_json # noqa
# Make a dummy dataset.
mask = make_mask()
DatasetCatalog.register("test_dataset", lambda: make_dataset_dicts(mask))
MetadataCatalog.get("test_dataset").set(thing_classes=["test_label"])
# Dump to json.
json_dict = convert_to_coco_dict("test_dataset")
with tempfile.TemporaryDirectory() as tmpdir:
json_file_name = os.path.join(tmpdir, "test.json")
with open(json_file_name, "w") as f:
json.dump(json_dict, f)
# Load from json.
dicts = load_coco_json(json_file_name, "")
# Check the loaded mask matches the original.
anno = dicts[0]["annotations"][0]
loaded_mask = mask_util.decode(anno["segmentation"])
self.assertTrue(np.array_equal(loaded_mask, mask))
def get_evaluator(cfg, dataset_name, output_folder=None):
"""
Create evaluator(s) for a given dataset.
This uses the special metadata "evaluator_type" associated with each builtin dataset.
For your own dataset, you can simply create an evaluator manually in your
script and do not have to worry about the hacky if-else logic here.
"""
if output_folder is None:
output_folder = os.path.join(cfg.OUTPUT_DIR, "inference")
evaluator_list = []
evaluator_type = MetadataCatalog.get(dataset_name).evaluator_type
if evaluator_type in ["sem_seg", "coco_panoptic_seg"]:
evaluator_list.append(
SemSegEvaluator(
dataset_name,
distributed=True,
num_classes=cfg.MODEL.SEM_SEG_HEAD.NUM_CLASSES,
ignore_label=cfg.MODEL.SEM_SEG_HEAD.IGNORE_VALUE,
output_dir=output_folder,
))
if evaluator_type in ["coco", "coco_panoptic_seg"]:
evaluator_list.append(
COCOEvaluator(dataset_name, cfg, True, output_folder))
if evaluator_type == "coco_panoptic_seg":
evaluator_list.append(
COCOPanopticEvaluator(dataset_name, output_folder))
if evaluator_type == "cityscapes":
assert (
torch.cuda.device_count() >= comm.get_rank()
), "CityscapesEvaluator currently do not work with multiple machines."
return CityscapesEvaluator(dataset_name)
if evaluator_type == "pascal_voc":
return PascalVOCDetectionEvaluator(dataset_name)
if evaluator_type == "lvis":
return LVISEvaluator(dataset_name, cfg, True, output_folder)
if len(evaluator_list) == 0:
raise NotImplementedError(
"no Evaluator for the dataset {} with the type {}".format(
dataset_name, evaluator_type))
if len(evaluator_list) == 1:
return evaluator_list[0]
return DatasetEvaluators(evaluator_list)
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
return parser.parse_args(in_args)
if __name__ == "__main__":
args = parse_args()
logger = setup_logger()
logger.info("Arguments: " + str(args))
cfg = setup(args)
dirname = args.output_dir
os.makedirs(dirname, exist_ok=True)
metadata = MetadataCatalog.get(cfg.DATASETS.TRAIN[0])
def output(vis, fname):
if args.show:
print(fname)
cv2.imshow("window", vis.get_image()[:, :, ::-1])
cv2.waitKey()
else:
filepath = os.path.join(dirname, fname)
print("Saving to {} ...".format(filepath))
vis.save(filepath)
scale = 2.0 if args.show else 1.0
if args.source == "dataloader":
train_data_loader = build_train_loader(cfg)
for batch in train_data_loader: