def test_serialize_deserialize():
t = Tensor(
shape=(100, 200),
dtype={
"image":
Image(shape=(300, 400, 3), dtype="uint8"),
"label":
Tensor(
shape=(5000, ),
dtype={
"first": {
"a": "<U20",
"b": "uint32",
"c": ClassLabel(num_classes=3),
},
"second": "float64",
},
),
"bbox":
BBox(dtype="float64"),
"audio":
Audio(shape=(120, ), dtype="uint32"),
"mask":
Mask(shape=(5, 8, 1)),
"polygon":
Polygon(shape=(16, 2)),
"segmentation1":
Segmentation(shape=(5, 9, 1), dtype="uint8", num_classes=5),
"segmentation2":
Segmentation(shape=(5, 9, 1),
dtype="uint8",
names=("apple", "orange", "pineapple")),
"sequence":
Sequence(dtype=Tensor(shape=(None, None),
max_shape=(100, 100),
dtype="uint8"), ),
"text":
Text((None, ), max_shape=(10, )),
"video":
Video((100, 100, 3, 10)),
},
)
original_result = tuple(t._flatten())
original_paths = [r.path for r in original_result]
original_shapes = [r.shape for r in original_result]
origanal_dtypes = [str(r.dtype) for r in original_result]
serialize_t = serialize(t)
deserialize_t = deserialize(serialize_t)
result = tuple(deserialize_t._flatten())
paths = [r.path for r in result]
shapes = [r.shape for r in result]
dtypes = [str(r.dtype) for r in result]
assert paths == original_paths
assert shapes == original_shapes
assert dtypes == origanal_dtypes
def deserialize(inp):
if isinstance(inp, dict):
if inp["type"] == "Audio":
return Audio(
shape=tuple(inp["shape"]),
dtype=deserialize(inp["dtype"]),
file_format=inp["file_format"],
sample_rate=inp["sample_rate"],
max_shape=tuple(inp["max_shape"]),
chunks=inp["chunks"],
compressor=_get_compressor(inp),
)
elif inp["type"] == "BBox":
return BBox(
shape=tuple(inp["shape"]),
dtype=deserialize(inp["dtype"]),
chunks=inp["chunks"],
compressor=_get_compressor(inp),
max_shape=tuple(inp["max_shape"]),
)
elif inp["type"] == "ClassLabel":
if inp["_names"] is not None:
return ClassLabel(
shape=tuple(inp["shape"]),
dtype=deserialize(inp["dtype"]),
names=inp["_names"],
chunks=inp["chunks"],
compressor=_get_compressor(inp),
max_shape=tuple(inp["max_shape"]),
)
else:
return ClassLabel(
shape=tuple(inp["shape"]),
dtype=deserialize(inp["dtype"]),
num_classes=inp["_num_classes"],
chunks=inp["chunks"],
compressor=_get_compressor(inp),
max_shape=tuple(inp["max_shape"]),
)
elif inp["type"] == "SchemaDict" or inp["type"] == "FeatureDict":
d = {}
for k, v in inp["items"].items():
d[k] = deserialize(v)
return SchemaDict(d)
elif inp["type"] == "Image":
return Image(
shape=tuple(inp["shape"]),
dtype=deserialize(inp["dtype"]),
max_shape=tuple(inp["max_shape"]),
chunks=inp["chunks"],
compressor=_get_compressor(inp),
)
elif inp["type"] == "Mask":
return Mask(
shape=tuple(inp["shape"]),
max_shape=tuple(inp["max_shape"]),
chunks=inp["chunks"],
compressor=_get_compressor(inp),
)
elif inp["type"] == "Polygon":
return Polygon(
shape=tuple(inp["shape"]),
max_shape=tuple(inp["max_shape"]),
dtype=deserialize(inp["dtype"]),
chunks=inp["chunks"],
compressor=_get_compressor(inp),
)
elif inp["type"] == "Primitive":
return Primitive(
dtype=deserialize(inp["dtype"]),
chunks=inp["chunks"],
compressor=_get_compressor(inp),
)
elif inp["type"] == "Segmentation":
class_labels = deserialize(inp["class_labels"])
if class_labels._names is not None:
return Segmentation(
shape=tuple(inp["shape"]),
dtype=deserialize(inp["dtype"]),
names=class_labels._names,
max_shape=tuple(inp["max_shape"]),
chunks=inp["chunks"],
compressor=_get_compressor(inp),
)
else:
return Segmentation(
shape=tuple(inp["shape"]),
dtype=deserialize(inp["dtype"]),
num_classes=class_labels._num_classes,
max_shape=tuple(inp["max_shape"]),
chunks=inp["chunks"],
compressor=_get_compressor(inp),
)
elif inp["type"] == "Sequence":
return Sequence(
shape=tuple(inp["shape"]),
dtype=deserialize(inp["dtype"]),
max_shape=tuple(inp["max_shape"]),
chunks=inp["chunks"],
compressor=_get_compressor(inp),
)
elif inp["type"] == "Tensor":
return Tensor(
tuple(inp["shape"]),
deserialize(inp["dtype"]),
max_shape=tuple(inp["max_shape"]),
chunks=inp["chunks"],
compressor=_get_compressor(inp),
)
elif inp["type"] == "Text":
return Text(
tuple(inp["shape"]),
deserialize(inp["dtype"]),
max_shape=tuple(inp["max_shape"]),
chunks=inp["chunks"],
compressor=_get_compressor(inp),
)
elif inp["type"] == "Video":
return Video(
shape=tuple(inp["shape"]),
dtype=deserialize(inp["dtype"]),
max_shape=tuple(inp["max_shape"]),
chunks=inp["chunks"],
compressor=_get_compressor(inp),
)
else:
return inp
def test_audio_repr():
audio = Audio((100,))
text = "Audio(shape=(100,), dtype='int64')"
assert audio.__repr__() == text
def test_audio():
with pytest.raises(ValueError):
audio = Audio((1920, 3), "float32")
def deserialize(inp):
if isinstance(inp, dict):
if inp["type"] == "Audio":
return Audio(
shape=tuple(inp["shape"]),
dtype=deserialize(inp["dtype"]),
file_format=inp["file_format"],
sample_rate=inp["sample_rate"],
max_shape=tuple(inp["max_shape"]),
chunks=inp["chunks"],
compressor=_get_compressor(inp),
)
elif inp["type"] == "BBox":
return BBox(
dtype=deserialize(inp["dtype"]),
chunks=inp["chunks"],
compressor=_get_compressor(inp),
)
elif inp["type"] == "ClassLabel":
if "_num_classes" in inp.keys():
return ClassLabel(
num_classes=inp["_num_classes"],
chunks=inp["chunks"],
compressor=_get_compressor(inp),
)
else:
return ClassLabel(
names=inp["names"],
chunks=inp["chunks"],
compressor=_get_compressor(inp),
)
elif inp["type"] == "SchemaDict" or inp["type"] == "FeatureDict":
d = {}
for k, v in inp["items"].items():
d[k] = deserialize(v)
return SchemaDict(d)
elif inp["type"] == "Image":
return Image(
shape=tuple(inp["shape"]),
dtype=deserialize(inp["dtype"]),
# TODO uncomment back when image encoding will be added
# encoding_format=inp["encoding_format"],
max_shape=tuple(inp["max_shape"]),
chunks=inp["chunks"],
compressor=_get_compressor(inp),
)
elif inp["type"] == "Mask":
return Mask(
shape=tuple(inp["shape"]),
max_shape=tuple(inp["max_shape"]),
chunks=inp["chunks"],
compressor=_get_compressor(inp),
)
elif inp["type"] == "Polygon":
return Polygon(
shape=tuple(inp["shape"]),
max_shape=tuple(inp["max_shape"]),
dtype=deserialize(inp["dtype"]),
chunks=inp["chunks"],
compressor=_get_compressor(inp),
)
elif inp["type"] == "Segmentation":
class_labels = deserialize(inp["class_labels"])
if hasattr(class_labels, "_num_classes"):
return Segmentation(
shape=tuple(inp["shape"]),
dtype=deserialize(inp["dtype"]),
num_classes=class_labels._num_classes,
max_shape=tuple(inp["max_shape"]),
chunks=inp["chunks"],
compressor=_get_compressor(inp),
)
else:
return Segmentation(
shape=tuple(inp["shape"]),
dtype=deserialize(inp["dtype"]),
names=class_labels.names,
max_shape=tuple(inp["max_shape"]),
chunks=inp["chunks"],
compressor=_get_compressor(inp),
)
elif inp["type"] == "Sequence":
return Sequence(
shape=tuple(inp["shape"]),
dtype=deserialize(inp["dtype"]),
max_shape=tuple(inp["max_shape"]),
chunks=inp["chunks"],
compressor=_get_compressor(inp),
)
elif inp["type"] == "Tensor":
return Tensor(
tuple(inp["shape"]),
deserialize(inp["dtype"]),
max_shape=tuple(inp["max_shape"]),
chunks=inp["chunks"],
compressor=_get_compressor(inp),
)
elif inp["type"] == "Text":
return Text(
tuple(inp["shape"]),
deserialize(inp["dtype"]),
max_shape=tuple(inp["max_shape"]),
chunks=inp["chunks"],
compressor=_get_compressor(inp),
)
elif inp["type"] == "Video":
return Video(
shape=tuple(inp["shape"]),
dtype=deserialize(inp["dtype"]),
# TODO uncomment back when image encoding will be added
# encoding_format=inp["encoding_format"],
max_shape=tuple(inp["max_shape"]),
chunks=inp["chunks"],
compressor=_get_compressor(inp),
)
else:
return inp