def test_copy_fusion_segment(self, accesskey, url, tmp_path):
gas_client = GAS(access_key=accesskey, url=url)
dataset_name = get_dataset_name()
gas_client.create_dataset(dataset_name, is_fusion=True)
dataset = FusionDataset(name=dataset_name)
segment = dataset.create_segment("Segment1")
segment.sensors.add(Sensor.loads(LIDAR_DATA))
dataset._catalog = Catalog.loads(CATALOG)
path = tmp_path / "sub"
path.mkdir()
for i in range(10):
frame = Frame()
local_path = path / f"hello{i}.txt"
local_path.write_text("CONTENT")
data = Data(local_path=str(local_path))
data.label = Label.loads(LABEL)
frame[LIDAR_DATA["name"]] = data
segment.append(frame)
dataset_client = gas_client.upload_dataset(dataset)
segment_client = dataset_client.copy_segment("Segment1", "Segment2")
assert segment_client.name == "Segment2"
with pytest.raises(InvalidParamsError):
dataset_client.copy_segment("Segment1", "Segment3", strategy="push")
segment2 = FusionSegment("Segment2", client=dataset_client)
assert segment2[0][LIDAR_DATA["name"]].path == "hello0.txt"
assert (
segment2[0][LIDAR_DATA["name"]].path
== segment[0][LIDAR_DATA["name"]].target_remote_path
)
assert segment2[0][LIDAR_DATA["name"]].label
gas_client.delete_dataset(dataset_name)
def test_import_cloud_files_to_fusiondataset(self, accesskey, url, config_name):
gas_client = GAS(access_key=accesskey, url=url)
try:
cloud_client = gas_client.get_cloud_client(config_name)
except ResourceNotExistError:
pytest.skip(f"skip this case because there's no {config_name} config")
auth_data = cloud_client.list_auth_data("tests")[:5]
dataset_name = get_dataset_name()
dataset_client = gas_client.create_dataset(dataset_name, True, config_name=config_name)
dataset = FusionDataset(name=dataset_name)
segment = dataset.create_segment("Segment1")
lidar = Lidar("LIDAR")
segment.sensors.add(lidar)
for data in auth_data:
data.label.classification = Classification("cat", attributes={"color": "red"})
frame = Frame()
frame["LIDAR"] = data
segment.append(frame)
dataset_client = gas_client.upload_dataset(dataset, jobs=5)
dataset_client.commit("import data")
segment1 = FusionSegment("Segment1", client=dataset_client)
assert len(segment1) == len(segment)
assert segment1[0]["LIDAR"].path == segment[0]["LIDAR"].path.split("/")[-1]
assert segment1[0]["LIDAR"].label.classification.category == "cat"
assert segment1[0]["LIDAR"].label.classification.attributes["color"] == "red"
assert len(auth_data) == len(segment)
gas_client.delete_dataset(dataset_name)
def test_create_and_upload_dataset_with_config(self, accesskey, url, tmp_path):
gas_client = GAS(access_key=accesskey, url=url)
dataset_name = get_dataset_name()
try:
gas_client.get_auth_storage_config(name=_LOCAL_CONFIG_NAME)
except ResourceNotExistError:
pytest.skip(f"skip this case because there's no {_LOCAL_CONFIG_NAME} config")
gas_client.create_dataset(dataset_name, config_name=_LOCAL_CONFIG_NAME)
dataset = Dataset(name=dataset_name)
segment = dataset.create_segment("Segment1")
# When uploading label, upload catalog first.
dataset._catalog = Catalog.loads(CATALOG)
path = tmp_path / "sub"
path.mkdir()
for i in range(5):
local_path = path / f"hello{i}.txt"
local_path.write_text("CONTENT")
data = Data(local_path=str(local_path))
data.label = Label.loads(LABEL)
segment.append(data)
dataset_client = gas_client.upload_dataset(dataset)
assert dataset_client.get_catalog()
segment1 = Segment("Segment1", client=dataset_client)
assert len(segment1) == 5
for i in range(5):
assert segment1[i].path == f"hello{i}.txt"
assert segment1[i].label
gas_client.delete_dataset(dataset_name)
def test_upload_dataset_only_with_file(self, accesskey, url, tmp_path):
gas_client = GAS(access_key=accesskey, url=url)
dataset_name = get_dataset_name()
gas_client.create_dataset(dataset_name)
dataset = Dataset(name=dataset_name)
dataset.notes.is_continuous = True
segment = dataset.create_segment("Segment1")
path = tmp_path / "sub"
path.mkdir()
for i in range(10):
local_path = path / f"hello{i}.txt"
local_path.write_text("CONTENT")
segment.append(Data(local_path=str(local_path)))
dataset_client = gas_client.upload_dataset(dataset)
assert dataset_client.status.branch_name == DEFAULT_BRANCH
assert dataset_client.status.draft_number
assert not dataset_client.status.commit_id
assert dataset_client.get_notes().is_continuous is True
assert not dataset_client.get_catalog()
segment1 = Segment("Segment1", client=dataset_client)
assert len(segment1) == 10
assert segment1[0].path == "hello0.txt"
assert not segment1[0].label
gas_client.delete_dataset(dataset_name)
def test_copy_data(self, accesskey, url, tmp_path):
gas_client = GAS(access_key=accesskey, url=url)
dataset_name = get_dataset_name()
gas_client.create_dataset(dataset_name)
dataset = Dataset(name=dataset_name)
segment = dataset.create_segment("Segment1")
dataset._catalog = Catalog.loads(CATALOG)
path = tmp_path / "sub"
path.mkdir()
for i in range(10):
local_path = path / f"hello{i}.txt"
local_path.write_text("CONTENT")
data = Data(local_path=str(local_path))
data.label = Label.loads(LABEL)
segment.append(data)
dataset_client = gas_client.upload_dataset(dataset)
segment_client = dataset_client.get_segment("Segment1")
segment_client.copy_data("hello0.txt", "goodbye0.txt")
segment_client.copy_data("hello1.txt", "hello10.txt")
with pytest.raises(InvalidParamsError):
segment_client.copy_data("hello2.txt", "see_you.txt", strategy="push")
segment2 = Segment("Segment1", client=dataset_client)
assert segment2[0].path == "goodbye0.txt"
assert segment2[3].path == "hello10.txt"
assert segment2[1].label
gas_client.delete_dataset(dataset_name)
def test_move_segment(self, accesskey, url, tmp_path):
gas_client = GAS(access_key=accesskey, url=url)
dataset_name = get_dataset_name()
gas_client.create_dataset(dataset_name)
dataset = Dataset(name=dataset_name)
segment = dataset.create_segment("Segment1")
dataset._catalog = Catalog.loads(CATALOG)
path = tmp_path / "sub"
path.mkdir()
for i in range(10):
local_path = path / f"hello{i}.txt"
local_path.write_text("CONTENT")
data = Data(local_path=str(local_path))
data.label = Label.loads(LABEL)
segment.append(data)
dataset_client = gas_client.upload_dataset(dataset)
segment_client = dataset_client.move_segment("Segment1", "Segment2")
assert segment_client.name == "Segment2"
with pytest.raises(InvalidParamsError):
dataset_client.move_segment("Segment1", "Segment3", strategy="push")
segment2 = Segment("Segment2", client=dataset_client)
assert segment2[0].path == "hello0.txt"
assert segment2[0].path == segment[0].target_remote_path
assert segment2[0].label
gas_client.delete_dataset(dataset_name)
def test_copy_data_between_datasets(self, accesskey, url, tmp_path):
gas_client = GAS(access_key=accesskey, url=url)
dataset_name_1 = get_dataset_name()
gas_client.create_dataset(dataset_name_1)
dataset_1 = Dataset(name=dataset_name_1)
segment_1 = dataset_1.create_segment("Segment1")
dataset_1._catalog = Catalog.loads(CATALOG)
path = tmp_path / "sub"
path.mkdir()
for i in range(10):
local_path = path / f"hello{i}.txt"
local_path.write_text("CONTENT")
data = Data(local_path=str(local_path))
data.label = Label.loads(LABEL)
segment_1.append(data)
dataset_client_1 = gas_client.upload_dataset(dataset_1)
dataset_client_1.commit("upload data")
segment_client_1 = dataset_client_1.get_segment("Segment1")
dataset_name_2 = dataset_name_1 + "_2"
dataset_client_2 = gas_client.create_dataset(dataset_name_2)
dataset_client_2.create_draft("draft_2")
dataset_client_2.create_segment("Segment1")
segment_client_2 = dataset_client_2.get_segment("Segment1")
segment_client_2.copy_data("hello0.txt", "hello0.txt", source_client=segment_client_1)
segment2 = Segment("Segment1", client=dataset_client_2)
assert segment2[0].path == "hello0.txt"
assert segment2[0].label
gas_client.delete_dataset(dataset_name_1)
gas_client.delete_dataset(dataset_name_2)
def test_copy_segment_abort(self, accesskey, url, tmp_path):
gas_client = GAS(access_key=accesskey, url=url)
dataset_name = get_dataset_name()
gas_client.create_dataset(dataset_name)
dataset = Dataset(name=dataset_name)
segment1 = dataset.create_segment("Segment1")
dataset._catalog = Catalog.loads(CATALOG)
path = tmp_path / "sub"
path.mkdir()
for i in range(10):
local_path = path / f"hello{i}.txt"
local_path.write_text("CONTENT")
data = Data(local_path=str(local_path))
data.label = Label.loads(LABEL)
segment1.append(data)
segment2 = dataset.create_segment("Segment2")
for i in range(10):
local_path = path / f"hello{i}.txt"
local_path.write_text("CONTENT")
data = Data(local_path=str(local_path))
data.label = Label.loads(LABEL)
segment2.append(data)
dataset_client = gas_client.upload_dataset(dataset)
with pytest.raises(InternalServerError):
dataset_client.copy_segment("Segment1", "Segment2")
gas_client.delete_dataset(dataset_name)
def test_copy_segment_skip(self, accesskey, url, tmp_path):
gas_client = GAS(access_key=accesskey, url=url)
dataset_name = get_dataset_name()
gas_client.create_dataset(dataset_name)
dataset = Dataset(name=dataset_name)
segment1 = dataset.create_segment("Segment1")
dataset._catalog = Catalog.loads(CATALOG)
path = tmp_path / "sub"
path.mkdir()
for i in range(10):
local_path = path / f"hello{i}.txt"
local_path.write_text("CONTENT")
data = Data(local_path=str(local_path))
data.label = Label.loads(LABEL)
segment1.append(data)
segment2 = dataset.create_segment("Segment2")
for i in range(10, 20):
local_path = path / f"hello{i}.txt"
local_path.write_text("CONTENT")
data = Data(local_path=str(local_path))
data.label = Label.loads(LABEL)
segment2.append(data)
dataset_client = gas_client.upload_dataset(dataset)
dataset_client.copy_segment("Segment1", "Segment2", strategy="skip")
segment_copied = Segment("Segment2", client=dataset_client)
assert segment_copied[0].path == "hello10.txt"
assert segment_copied[0].path == segment2[0].target_remote_path
assert segment_copied[0].label
gas_client.delete_dataset(dataset_name)
def test_move_data_skip(self, accesskey, url, tmp_path):
gas_client = GAS(access_key=accesskey, url=url)
dataset_name = get_dataset_name()
gas_client.create_dataset(dataset_name)
dataset = Dataset(name=dataset_name)
segment = dataset.create_segment("Segment1")
dataset._catalog = Catalog.loads(CATALOG)
path = tmp_path / "sub"
path.mkdir()
for i in range(10):
local_path = path / f"hello{i}.txt"
local_path.write_text(f"CONTENT_{i}")
data = Data(local_path=str(local_path))
data.label = Label.loads(LABEL)
segment.append(data)
dataset_client = gas_client.upload_dataset(dataset)
segment_client = dataset_client.get_segment("Segment1")
segment_client.move_data("hello0.txt", "hello1.txt", strategy="skip")
segment_moved = Segment("Segment1", client=dataset_client)
assert segment_moved[0].path == "hello1.txt"
assert segment_moved[0].open().read() == b"CONTENT_1"
gas_client.delete_dataset(dataset_name)
def test_import_cloud_files(self, accesskey, url, config_name):
gas_client = GAS(access_key=accesskey, url=url)
try:
cloud_client = gas_client.get_cloud_client(config_name)
except ResourceNotExistError:
pytest.skip(
f"skip this case because there's no {config_name} config")
auth_data = cloud_client.list_auth_data("tests")
dataset_name = get_dataset_name()
dataset_client = gas_client.create_dataset(dataset_name,
config_name=config_name)
dataset = Dataset(name=dataset_name)
segment = dataset.create_segment("Segment1")
for data in auth_data:
segment.append(data)
dataset_client = gas_client.upload_dataset(dataset, jobs=5)
dataset_client.commit("import data")
segment1 = Segment("Segment1", client=dataset_client)
assert len(segment1) == len(segment)
assert segment1[0].path == segment[0].path.split("/")[-1]
assert not segment1[0].label
assert len(auth_data) == len(segment)
gas_client.delete_dataset(dataset_name)
def test_upload_dataset_with_label(self, accesskey, url, tmp_path):
gas_client = GAS(access_key=accesskey, url=url)
dataset_name = get_dataset_name()
gas_client.create_dataset(dataset_name)
dataset = Dataset(name=dataset_name)
segment = dataset.create_segment("Segment1")
# When uploading label, upload catalog first.
dataset._catalog = Catalog.loads(CATALOG_CONTENTS)
path = tmp_path / "sub"
path.mkdir()
local_path = path / "hello.txt"
local_path.write_text("CONTENT")
data = Data(local_path=str(local_path))
data.label = Label.loads(LABEL)
segment.append(data)
dataset_client = gas_client.upload_dataset(dataset)
dataset_client.commit("upload dataset with label")
dataset = Dataset(dataset_name, gas_client)
assert dataset.catalog == Catalog.loads(CATALOG_CONTENTS)
assert dataset[0][0].label == Label.loads(LABEL)
statistics1 = dataset_client.get_label_statistics()
assert statistics1 == Statistics(STATISTICS)
total_size = dataset_client.get_total_size()
assert total_size == TOTALSIZE
gas_client.delete_dataset(dataset_name)
def test_upload_dataset_with_label(self, accesskey, url, tmp_path):
gas_client = GAS(access_key=accesskey, url=url)
dataset_name = get_dataset_name()
gas_client.create_dataset(dataset_name)
dataset = Dataset(name=dataset_name)
segment = dataset.create_segment("Segment1")
# When uploading label, upload catalog first.
dataset._catalog = Catalog.loads(CATALOG)
path = tmp_path / "sub"
path.mkdir()
for i in range(10):
local_path = path / f"hello{i}.txt"
local_path.write_text("CONTENT")
data = Data(local_path=str(local_path))
data.label = Label.loads(LABEL)
segment.append(data)
dataset_client = gas_client.upload_dataset(dataset)
assert dataset_client.get_catalog()
segment1 = Segment("Segment1", client=dataset_client)
assert len(segment1) == 10
assert segment1[0].path == "hello0.txt"
assert segment1[0].label
gas_client.delete_dataset(dataset_name)
def test_upload_dataset_after_commit(self, accesskey, url, tmp_path):
gas_client = GAS(access_key=accesskey, url=url)
dataset_name = get_dataset_name()
gas_client.create_dataset(dataset_name)
dataset = Dataset(name=dataset_name)
dataset._catalog = Catalog.loads(CATALOG)
dataset.notes.is_continuous = True
segment = dataset.create_segment("Segment1")
path = tmp_path / "sub"
path.mkdir()
for i in range(10):
local_path = path / f"hello{i}.txt"
local_path.write_text("CONTENT")
data = Data(local_path=str(local_path))
data.label = Label.loads(LABEL)
segment.append(data)
dataset_client = gas_client.upload_dataset(dataset)
dataset_client.commit("test")
dataset_remote = Dataset(name=dataset_name, gas=gas_client)
assert dataset_remote.notes.is_continuous == dataset.notes.is_continuous
assert dataset_remote.catalog == dataset.catalog
segment_remote = dataset_remote[0]
assert len(segment_remote) == len(segment)
for remote_data, data in zip(segment_remote, segment):
assert remote_data.path == data.target_remote_path
assert remote_data.label == data.label
gas_client.delete_dataset(dataset_name)
def test_upload_dataset_to_given_branch(self, accesskey, url, tmp_path):
gas_client = GAS(access_key=accesskey, url=url)
dataset_name = get_dataset_name()
dataset_client_1 = gas_client.create_dataset(dataset_name)
dataset_client_1.create_draft("test")
dataset_client_1.commit("test1")
dataset_client_1.create_branch("dev")
dataset = Dataset(name=dataset_name)
segment = dataset.create_segment("Segment1")
path = tmp_path / "sub"
path.mkdir()
for i in range(10):
local_path = path / f"hello{i}.txt"
local_path.write_text("CONTENT")
segment.append(Data(local_path=str(local_path)))
dataset_client_2 = gas_client.upload_dataset(dataset,
branch_name="dev")
assert dataset_client_2.status.branch_name == "dev"
assert dataset_client_2.status.draft_number
assert not dataset_client_2.status.commit_id
segment1 = Segment("Segment1", client=dataset_client_2)
assert len(segment1) == 10
assert segment1[0].path == "hello0.txt"
assert not segment1[0].label
dataset_client_2.commit("test2")
draft_number = dataset_client_2.create_draft("test2")
for i in range(10):
local_path = path / f"goodbye{i}.txt"
local_path.write_text("CONTENT")
segment.append(Data(local_path=str(local_path)))
dataset_client_2 = gas_client.upload_dataset(dataset,
branch_name="dev")
assert dataset_client_2.status.branch_name == "dev"
assert dataset_client_2.status.draft_number == draft_number
assert not dataset_client_2.status.commit_id
with pytest.raises(ResourceNotExistError):
gas_client.upload_dataset(dataset, branch_name="wrong")
gas_client.delete_dataset(dataset_name)
def test_copy_data_from_commits(self, accesskey, url, tmp_path):
gas_client = GAS(access_key=accesskey, url=url)
dataset_name = get_dataset_name()
gas_client.create_dataset(dataset_name)
dataset = Dataset(name=dataset_name)
segment = dataset.create_segment("Segment1")
dataset._catalog = Catalog.loads(CATALOG)
path = tmp_path / "sub"
path.mkdir()
for i in range(10):
local_path = path / f"hello{i}.txt"
local_path.write_text("CONTENT")
data = Data(local_path=str(local_path))
data.label = Label.loads(LABEL)
segment.append(data)
dataset_client = gas_client.upload_dataset(dataset)
dataset_client.commit("commit_1")
for i in range(10, 20):
local_path = path / f"hello{i}.txt"
local_path.write_text("CONTENT")
data = Data(local_path=str(local_path))
data.label = Label.loads(LABEL)
segment.append(data)
dataset_client = gas_client.upload_dataset(dataset)
dataset_client.commit("commit_2")
dataset_client_1 = gas_client.get_dataset(dataset_name)
commit_id = dataset_client_1.list_commits()[-1].commit_id
dataset_client_1.checkout(revision=commit_id)
dataset_client.create_draft("draft_3")
segment_client_1 = dataset_client_1.get_segment("Segment1")
segment_client_2 = dataset_client.get_segment("Segment1")
segment_client_2.copy_data("hello0.txt",
"goodbye0.txt",
source_client=segment_client_1)
segment2 = Segment("Segment1", client=dataset_client)
assert segment2[0].path == "goodbye0.txt"
assert segment2[0].path != segment[0].target_remote_path
assert segment2[0].label
assert len(segment2) == 21
gas_client.delete_dataset(dataset_name)
def test_cache_dataset(self, accesskey, url, tmp_path):
gas_client = GAS(access_key=accesskey, url=url)
dataset_name = get_dataset_name()
gas_client.create_dataset(dataset_name)
dataset = Dataset(name=dataset_name)
segment = dataset.create_segment("Segment1")
# When uploading label, upload catalog first.
dataset._catalog = Catalog.loads(_CATALOG)
path = tmp_path / "sub"
semantic_path = tmp_path / "semantic_mask"
instance_path = tmp_path / "instance_mask"
path.mkdir()
semantic_path.mkdir()
instance_path.mkdir()
for i in range(_SEGMENT_LENGTH):
local_path = path / f"hello{i}.txt"
local_path.write_text("CONTENT")
data = Data(local_path=str(local_path))
data.label = Label.loads(_LABEL)
semantic_mask = semantic_path / f"semantic_mask{i}.png"
semantic_mask.write_text("SEMANTIC_MASK")
data.label.semantic_mask = SemanticMask(str(semantic_mask))
instance_mask = instance_path / f"instance_mask{i}.png"
instance_mask.write_text("INSTANCE_MASK")
data.label.instance_mask = InstanceMask(str(instance_mask))
segment.append(data)
dataset_client = gas_client.upload_dataset(dataset)
dataset_client.commit("commit-1")
cache_path = tmp_path / "cache_test"
dataset_client.enable_cache(str(cache_path))
segment1 = Segment("Segment1", client=dataset_client)
for data in segment1:
data.open()
data.label.semantic_mask.open()
data.label.instance_mask.open()
segment_cache_path = (cache_path / dataset_client.dataset_id /
dataset_client.status.commit_id / "Segment1")
semantic_mask_cache_path = segment_cache_path / "semantic_mask"
instance_mask_cache_path = segment_cache_path / "instance_mask"
for cache_dir, extension in (
(segment_cache_path, "txt"),
(semantic_mask_cache_path, "png"),
(instance_mask_cache_path, "png"),
):
assert set(cache_dir.glob(f"*.{extension}")) == set(
cache_dir / f"hello{i}.{extension}"
for i in range(_SEGMENT_LENGTH))
gas_client.delete_dataset(dataset_name)
def test_copy_between_datasets_override(self, accesskey, url, tmp_path):
gas_client = GAS(access_key=accesskey, url=url)
dataset_name_1 = get_dataset_name()
gas_client.create_dataset(dataset_name_1)
dataset_1 = Dataset(name=dataset_name_1)
segment_1 = dataset_1.create_segment("Segment")
path = tmp_path / "sub"
path.mkdir()
for i in range(10):
local_path = path / f"hello{i}.txt"
local_path.write_text("CONTENT")
data = Data(local_path=str(local_path))
segment_1.append(data)
dataset_client_1 = gas_client.upload_dataset(dataset_1)
dataset_client_1.commit("upload data")
dataset_name_2 = dataset_name_1 + "_2"
dataset_client_2 = gas_client.create_dataset(dataset_name_2)
dataset_2 = Dataset(name=dataset_name_2)
segment_2 = dataset_2.create_segment("Segment")
for i in range(10, 15):
local_path = path / f"hello{i}.txt"
local_path.write_text("CONTENT")
data = Data(local_path=str(local_path))
segment_2.append(data)
dataset_client_2 = gas_client.upload_dataset(dataset_2)
dataset_client_2.commit("upload data")
dataset_client_2.create_draft("draft 2")
dataset_client_2.copy_segment(
"Segment", source_client=dataset_client_1, strategy="override"
)
dataset_client_2.commit("copy segmnet")
segment = Segment("Segment", client=dataset_client_2)
assert len(segment) == 10
assert segment[0].path == "hello0.txt"
gas_client.delete_dataset(dataset_name_1)
gas_client.delete_dataset(dataset_name_2)
def test_upload_dataset_with_mask(self, accesskey, url, tmp_path, mask_file):
gas_client = GAS(access_key=accesskey, url=url)
dataset_name = get_dataset_name()
gas_client.create_dataset(dataset_name)
dataset = Dataset(name=dataset_name)
segment = dataset.create_segment("Segment1")
# When uploading label, upload catalog first.
dataset._catalog = Catalog.loads(CATALOG_CONTENTS)
path = tmp_path / "sub"
path.mkdir()
local_path = path / "hello.txt"
local_path.write_text("CONTENT")
data = Data(local_path=str(local_path))
remote_semantic_mask = SemanticMask(str(mask_file))
remote_semantic_mask.all_attributes = {0: {"occluded": True}, 1: {"occluded": False}}
data.label.semantic_mask = remote_semantic_mask
instance_mask = InstanceMask(str(mask_file))
instance_mask.all_attributes = {0: {"occluded": True}, 1: {"occluded": False}}
data.label.instance_mask = instance_mask
panoptic_mask = PanopticMask(str(mask_file))
panoptic_mask.all_category_ids = {100: 0, 101: 1}
data.label.panoptic_mask = panoptic_mask
segment.append(data)
dataset_client = gas_client.upload_dataset(dataset)
dataset_client.commit("upload dataset with label")
dataset = Dataset(dataset_name, gas_client)
remote_semantic_mask = dataset[0][0].label.semantic_mask
semantic_mask = RemoteSemanticMask.from_response_body(SEMANTIC_MASK_LABEL)
assert dataset.catalog == Catalog.loads(CATALOG_CONTENTS)
assert remote_semantic_mask.path == semantic_mask.path
assert remote_semantic_mask.all_attributes == semantic_mask.all_attributes
remote_instance_mask = dataset[0][0].label.instance_mask
instance_mask = RemoteInstanceMask.from_response_body(INSTANCE_MASK_LABEL)
assert dataset.catalog == Catalog.loads(CATALOG_CONTENTS)
assert remote_instance_mask.path == instance_mask.path
assert remote_instance_mask.all_attributes == instance_mask.all_attributes
remote_panoptic_mask = dataset[0][0].label.panoptic_mask
panoptic_mask = RemotePanopticMask.from_response_body(PANOPTIC_MASK_LABEL)
assert dataset.catalog == Catalog.loads(CATALOG_CONTENTS)
assert remote_panoptic_mask.path == panoptic_mask.path
assert remote_panoptic_mask.all_category_ids == panoptic_mask.all_category_ids
gas_client.delete_dataset(dataset_name)
def test_upload_label(self, accesskey, url, tmp_path):
gas_client = GAS(access_key=accesskey, url=url)
dataset_name = get_dataset_name()
gas_client.create_dataset(dataset_name)
dataset = Dataset(name=dataset_name)
segment = dataset.create_segment("Segment1")
# When uploading label, upload catalog first.
dataset._catalog = Catalog.loads(CATALOG_CONTENTS)
path = tmp_path / "sub"
path.mkdir()
local_path = path / "hello.txt"
local_path.write_text("CONTENT")
data = Data(local_path=str(local_path))
data.label = Label.loads(LABEL)
segment.append(data)
dataset_client = gas_client.upload_dataset(dataset)
dataset_client.commit("upload dataset with label")
dataset = Dataset(dataset_name, gas_client)
assert dataset[0][0].label == Label.loads(LABEL)
dataset_client.create_draft("update label")
segment_client = dataset_client.get_segment(segment.name)
upload_data = []
new_label = Label.loads(LABEL)
new_label.multi_polygon[0].category = "dog"
for data in segment:
data.label = new_label
upload_data.append(data)
segment_client.upload_label(upload_data)
dataset_client.commit("update label")
dataset = Dataset(dataset_name, gas_client)
assert dataset.catalog == Catalog.loads(CATALOG_CONTENTS)
assert dataset[0][0].label == new_label
gas_client.delete_dataset(dataset_name)
def test_move_segment_override(self, accesskey, url, tmp_path):
gas_client = GAS(access_key=accesskey, url=url)
dataset_name = get_dataset_name()
gas_client.create_dataset(dataset_name)
dataset = Dataset(name=dataset_name)
segment1 = dataset.create_segment("Segment1")
dataset._catalog = Catalog.loads(CATALOG)
path = tmp_path / "sub"
path.mkdir()
for i in range(10):
local_path = path / f"hello{i}.txt"
local_path.write_text("CONTENT_1")
data = Data(local_path=str(local_path))
data.label = Label.loads(LABEL)
segment1.append(data)
segment2 = dataset.create_segment("Segment2")
for i in range(10, 20):
local_path = path / f"hello{i}.txt"
local_path.write_text("CONTENT_2")
data = Data(local_path=str(local_path))
data.label = Label.loads(LABEL)
segment2.append(data)
dataset_client = gas_client.upload_dataset(dataset)
dataset_client.move_segment("Segment1",
"Segment2",
strategy="override")
with pytest.raises(ResourceNotExistError):
dataset_client.get_segment("Segment1")
segment_moved = Segment("Segment2", client=dataset_client)
assert segment_moved[0].path == "hello0.txt"
assert segment_moved[0].path == segment1[0].target_remote_path
assert segment_moved[0].open().read() == b"CONTENT_1"
assert segment_moved[0].label
gas_client.delete_dataset(dataset_name)
def test_upload_fusion_dataset_after_commit(self, accesskey, url, tmp_path):
gas_client = GAS(access_key=accesskey, url=url)
dataset_name = get_dataset_name()
gas_client.create_dataset(dataset_name, is_fusion=True)
dataset = FusionDataset(name=dataset_name)
dataset._catalog = Catalog.loads(CATALOG)
dataset.notes.is_continuous = True
segment = dataset.create_segment("Segment1")
segment.sensors = Sensors.loads([LIDAR_DATA])
path = tmp_path / "sub"
path.mkdir()
for i in range(10):
remote_frame = Frame()
local_path = path / f"hello{i}.txt"
local_path.write_text("CONTENT")
data = Data(local_path=str(local_path))
data.label = Label.loads(LABEL)
remote_frame[LIDAR_NAME] = data
segment.append(remote_frame)
dataset_client = gas_client.upload_dataset(dataset)
dataset_client.commit("test")
dataset_remote = FusionDataset(name=dataset_name, gas=gas_client)
assert dataset_remote.notes.is_continuous == dataset.notes.is_continuous
assert dataset_remote.catalog == dataset.catalog
segment_remote = dataset_remote[0]
assert len(segment_remote) == len(segment)
assert segment_remote.sensors == segment.sensors
for remote_frame, frame in zip(segment_remote, segment):
assert remote_frame[LIDAR_NAME].path == frame[LIDAR_NAME].target_remote_path
assert remote_frame[LIDAR_DATA["name"]].label == frame[LIDAR_NAME].label
gas_client.delete_dataset(dataset_name)
"""List Dataset Names"""
dataset_list = list(gas.list_dataset_names())
""""""
"""Upload Images to the Dataset"""
from tensorbay.dataset import Data, Dataset
# Organize the local dataset by the "Dataset" class before uploading.
dataset = Dataset("DatasetName")
# TensorBay uses "segment" to separate different parts in a dataset.
segment = dataset.create_segment()
segment.append(Data("0000001.jpg"))
segment.append(Data("0000002.jpg"))
dataset_client = gas.upload_dataset(dataset)
# TensorBay provides dataset version control feature, commit the uploaded data before using it.
dataset_client.commit("Initial commit")
""""""
"""Read Images from the Dataset"""
from PIL import Image
from tensorbay.dataset import Segment
dataset_client = gas.get_dataset("DatasetName")
segment = Segment("", dataset_client)
for data in segment:
with data.open() as fp:
image = Image.open(fp)
"""Create Dataset"""
gas.create_dataset("LeedsSportsPose")
""""""
"""List Dataset Names"""
list(gas.list_dataset_names())
""""""
from tensorbay.opendataset import LeedsSportsPose
dataset = LeedsSportsPose("path/to/dataset/directory")
"""Upload Dataset"""
# dataset is the one you initialized in "Organize Dataset" section
dataset_client = gas.upload_dataset(dataset, jobs=8, skip_uploaded_files=False)
dataset_client.commit("LeedsSportsPose")
""""""
"""Read Dataset / get dataset"""
dataset_client = gas.get_dataset("LeedsSportsPose")
""""""
"""Read Dataset / get segment"""
from tensorbay.dataset import Segment
default_segment = Segment("", dataset_client)
""""""
"""Read Dataset / get data"""
data = default_segment[0]
from tensorbay.dataset import Dataset
from tensorbay.label import Classification
# Use AuthData to organize a dataset by the "Dataset" class before importing.
dataset = Dataset("<DATASET_NAME>")
# TensorBay uses "segment" to separate different parts in a dataset.
segment = dataset.create_segment()
images = cloud_client.list_auth_data("<data/images/>")
labels = cloud_client.list_auth_data("<data/labels/>")
for auth_data, label in zip(images, labels):
with label.open() as fp:
auth_data.label.classification = Classification.loads(json.load(fp))
segment.append(auth_data)
dataset_client = gas.upload_dataset(dataset, jobs=8)
""""""
"""Create local storage config"""
gas.create_local_storage_config(
name="<LOCAL_STORAGE_CONFIG>",
file_path="<path/to/dataset>",
endpoint="<external IP address of the local storage service>",
)
""""""
"""Create authorized local storage dataset"""
dataset_client = gas.create_dataset("<DATASET_NAME>",
config_name="<LOCAL_STORAGE_CONFIG>")
""""""
"""Create Fusion Dataset"""
gas.create_dataset("CADC", is_fusion=True)
""""""
"""List Dataset Names"""
gas.list_dataset_names()
""""""
from tensorbay.opendataset import CADC
fusion_dataset = CADC("<path/to/dataset>")
"""Upload Fusion Dataset"""
# fusion_dataset is the one you initialized in "Organize Fusion Dataset" section
fusion_dataset_client = gas.upload_dataset(fusion_dataset, jobs=8)
fusion_dataset_client.commit("initial commit")
""""""
"""Read Fusion Dataset / get fusion dataset"""
fusion_dataset = FusionDataset("CADC", gas)
""""""
"""Read Fusion Dataset / list fusion segment names"""
fusion_dataset.keys()
""""""
"""Read Fusion Dataset / get fusion segment"""
fusion_segment = fusion_dataset["2018_03_06/0001"]
fusion_segment = fusion_dataset[0]
""""""
dataset = Dataset("<DATASET_NAME>", gas)
for segment in dataset:
update_data = []
for data in segment:
data.label.classification = Classification(
"NEW_CATEGORY") # set new label
update_data.append(data)
segment_client = dataset_client.get_segment(segment.name)
segment_client.upload_label(update_data)
""""""
"""Update label / commit dataset"""
dataset_client.commit("update labels")
""""""
"""Update data/ upload dataset"""
gas.upload_dataset(dataset, jobs=8, skip_uploaded_files=True)
""""""
"""Update data/ overwrite dataset"""
gas.upload_dataset(dataset, jobs=8)
""""""
"""Update data/ delete segment"""
dataset_client.create_draft("draft-3")
dataset_client.delete_segment("<SEGMENT_NAME>")
""""""
"""Update data/ delete data"""
segment_client = dataset_client.get_segment("<SEGMENT_NAME>")
segment_client.delete_data("a.png")
""""""
"""Delete frame"""
segment_client.delete_frame("00000000003W09TEMC1HXYMC74")
""""""