def _register_toy_dataset(
dataset_name, image_generator, num_images, num_classes=-1, num_keypoints=0
):
json_dataset, meta_data = create_toy_dataset(
image_generator,
num_images=num_images,
num_classes=num_classes,
num_keypoints=num_keypoints,
)
with make_temp_directory("detectron2go_tmp_dataset") as tmp_dir:
json_file = os.path.join(tmp_dir, "{}.json".format(dataset_name))
with open(json_file, "w") as f:
json.dump(json_dataset, f)
split_dict = {
IM_DIR: image_generator.get_image_dir(),
ANN_FN: json_file,
"meta_data": meta_data,
}
register_dataset_split(dataset_name, split_dict)
try:
yield
finally:
DatasetCatalog.remove(dataset_name)
MetadataCatalog.remove(dataset_name)
def create_local_dataset(
out_dir,
num_images,
image_width,
image_height,
num_classes=-1,
num_keypoints=0,
is_rotated=False,
):
dataset_name = "_test_ds_" + str(uuid.uuid4())
img_gen = LocalImageGenerator(out_dir, image_width, image_height)
json_dataset, meta_data = create_toy_dataset(
img_gen,
num_images=num_images,
num_classes=num_classes,
num_keypoints=num_keypoints,
)
json_file = os.path.join(out_dir, "{}.json".format(dataset_name))
with open(json_file, "w") as f:
json.dump(json_dataset, f)
split_dict = {
IM_DIR: img_gen.get_image_dir(),
ANN_FN: json_file,
"meta_data": meta_data,
}
if is_rotated:
split_dict["evaluator_type"] = "rotated_coco"
register_dataset_split(dataset_name, split_dict)
return dataset_name
def register_catalog(self):
"""
Adhoc COCO (json) dataset assumes the derived dataset can be created by only
changing the json file, currently it supports two sources: 1) the dataset is
registered using standard COCO registering functions in D2 or
register_dataset_split from D2Go, this way it uses `json_file` from the metadata
to access the json file. 2) the load func in DatasetCatalog is an instance of
CallFuncWithJsonFile, which gives access to the json_file. In both cases,
metadata will be the same except for the `name` and potentially `json_file`.
"""
logger.info("Register {} from {}".format(self.new_ds_name,
self.src_ds_name))
metadata = MetadataCatalog.get(self.src_ds_name)
load_func = DatasetCatalog[self.src_ds_name]
src_json_file = (load_func.json_file if isinstance(
load_func, CallFuncWithJsonFile) else metadata.json_file)
# TODO cache ?
with PathManager.open(src_json_file) as f:
json_dict = json.load(f)
assert "images" in json_dict, "Only support COCO-style json!"
json_dict = self.new_json_dict(json_dict)
self.tmp_dir = tempfile.mkdtemp(prefix="detectron2go_tmp_datasets")
tmp_file = os.path.join(self.tmp_dir,
"{}.json".format(self.new_ds_name))
with open(tmp_file, "w") as f:
json.dump(json_dict, f)
# re-register DatasetCatalog
if isinstance(load_func, CallFuncWithJsonFile):
new_func = CallFuncWithJsonFile(func=load_func.func,
json_file=tmp_file)
DatasetCatalog.register(self.new_ds_name, new_func)
else:
# NOTE: only supports COCODataset as DS_TYPE since we cannot reconstruct
# the split_dict
register_dataset_split(
self.new_ds_name,
split_dict={
ANN_FN: tmp_file,
IM_DIR: metadata.image_root
},
)
# re-regisister MetadataCatalog
metadata_dict = metadata.as_dict()
metadata_dict["name"] = self.new_ds_name
if "json_file" in metadata_dict:
metadata_dict["json_file"] = tmp_file
MetadataCatalog.remove(self.new_ds_name)
MetadataCatalog.get(self.new_ds_name).set(**metadata_dict)