def __setitem__(self, slice_, value):
"""| Sets a slice or slices with a value
| Usage:
>>> ds["image", 5, 0:1920, 0:1080, 0:3] = np.zeros((1920, 1080, 3), "uint8")
>>> images = ds["image"]
>>> image = images[5]
>>> image[0:1920, 0:1080, 0:3] = np.zeros((1920, 1080, 3), "uint8")
"""
if "r" in self._mode:
raise ReadModeException("__setitem__")
self._auto_checkout()
if not isinstance(slice_, abc.Iterable) or isinstance(slice_, str):
slice_ = [slice_]
slice_ = list(slice_)
subpath, slice_list = slice_split(slice_)
if not subpath:
raise ValueError("Can't assign to dataset sliced without subpath")
elif subpath not in self.keys:
raise KeyError(f"Key {subpath} not found in the dataset")
assign_value = get_value(value)
schema_dict = self.schema
if subpath[1:] in schema_dict.dict_.keys():
schema_key = schema_dict.dict_.get(subpath[1:], None)
else:
for schema_key in subpath[1:].split("/"):
schema_dict = schema_dict.dict_.get(schema_key, None)
if not isinstance(schema_dict, SchemaDict):
schema_key = schema_dict
if isinstance(schema_key, ClassLabel):
assign_value = check_class_label(assign_value, schema_key)
if isinstance(
schema_key,
(Text, bytes)) or (isinstance(assign_value, Iterable) and any(
isinstance(val, str) for val in assign_value)):
# handling strings and bytes
assign_value = str_to_int(assign_value, self.tokenizer)
if not slice_list:
self._tensors[subpath][:] = assign_value
else:
self._tensors[subpath][slice_list] = assign_value
def __setitem__(self, slice_, value):
"""| Sets a slice or slices with a value
| Usage:
>>> images_tensorview = ds["image"]
>>> images_tensorview[7, 0:1920, 0:1080, 0:3] = np.zeros((1920, 1080, 3), "uint8") # sets 7th image
"""
self.dataset._auto_checkout()
if not isinstance(slice_, abc.Iterable) or isinstance(slice_, str):
slice_ = [slice_]
slice_ = list(slice_)
slice_ = self.slice_fill(slice_)
subpath, slice_list = slice_split(slice_)
if subpath:
raise ValueError("Can't setitem of TensorView with subpath")
assign_value = get_value(value)
schema_dict = self.dataset.schema
if subpath[1:] in schema_dict.dict_.keys():
schema_key = schema_dict.dict_.get(subpath[1:], None)
else:
for schema_key in subpath[1:].split("/"):
schema_dict = schema_dict.dict_.get(schema_key, None)
if not isinstance(schema_dict, SchemaDict):
schema_key = schema_dict
if isinstance(schema_key, ClassLabel):
assign_value = check_class_label(assign_value, schema_key)
if isinstance(
schema_key,
(Text, bytes)) or (isinstance(assign_value, Iterable) and any(
isinstance(val, str) for val in assign_value)):
# handling strings and bytes
assign_value = str_to_int(assign_value, self.dataset.tokenizer)
new_nums = self.nums.copy()
new_offsets = self.offsets.copy()
if isinstance(self.indexes, list):
new_indexes = self.indexes[slice_list[0]]
if self.is_contiguous and new_indexes:
new_indexes = slice(new_indexes[0], new_indexes[-1] + 1)
elif isinstance(self.indexes, int):
new_indexes = self.indexes
else:
ofs = self.indexes.start or 0
num = self.indexes.stop - ofs if self.indexes.stop else None
new_indexes = self._combine(slice_list[0], num, ofs)
slice_list[0] = new_indexes
if len(new_nums) < len(slice_list):
new_nums.extend([None] * (len(slice_list) - len(new_nums)))
new_offsets.extend([0] * (len(slice_list) - len(new_offsets)))
for i in range(1, len(slice_list)):
slice_list[i] = self._combine(slice_list[i], new_nums[i],
new_offsets[i])
for i in range(len(slice_list), len(new_nums)):
cur_slice = (slice(new_offsets[i], new_offsets[i] + new_nums[i])
if not self.squeeze_dims[i] else new_offsets[i])
slice_list.append(cur_slice)
if isinstance(slice_list[0], (int, slice)):
self.dataset._tensors[self.subpath][slice_list] = assign_value
else:
for i, index in enumerate(slice_list[0]):
current_slice = [index] + slice_list[1:]
self.dataset._tensors[subpath][current_slice] = assign_value[i]
def __setitem__(self, slice_, value):
"""| Sets a slice or slices with a value
| Usage:
>>> ds_view = ds[5:15]
>>> ds_view["image", 3, 0:1920, 0:1080, 0:3] = np.zeros((1920, 1080, 3), "uint8") # sets the 8th image
"""
self.dataset._auto_checkout()
if not isinstance(slice_, abc.Iterable) or isinstance(slice_, str):
slice_ = [slice_]
slice_ = list(slice_)
subpath, slice_list = slice_split(slice_)
slice_list = [0] + slice_list if isinstance(self.indexes,
int) else slice_list
assign_value = get_value(value)
schema_dict = self.dataset.schema
if subpath[1:] in schema_dict.dict_.keys():
schema_key = schema_dict.dict_.get(subpath[1:], None)
else:
for schema_key in subpath[1:].split("/"):
schema_dict = schema_dict.dict_.get(schema_key, None)
if not isinstance(schema_dict, SchemaDict):
schema_key = schema_dict
if isinstance(schema_key, ClassLabel):
assign_value = check_class_label(assign_value, schema_key)
if isinstance(
schema_key,
(Text, bytes)) or (isinstance(assign_value, Iterable) and any(
isinstance(val, str) for val in assign_value)):
# handling strings and bytes
assign_value = str_to_int(assign_value, self.dataset.tokenizer)
if not subpath:
raise ValueError("Can't assign to dataset sliced without key")
elif subpath not in self.keys:
raise KeyError(f"Key {subpath} not found in dataset")
if not slice_list:
slice_ = (slice(self.indexes[0], self.indexes[-1] +
1) if self.is_contiguous else self.indexes)
if not isinstance(slice_, list):
self.dataset._tensors[subpath][slice_] = assign_value
else:
for i, index in enumerate(slice_):
self.dataset._tensors[subpath][index] = assign_value[i]
else:
if isinstance(self.indexes, list):
indexes = self.indexes[slice_list[0]]
if self.is_contiguous and isinstance(indexes,
list) and indexes:
slice_list[0] = slice(indexes[0], indexes[-1] + 1)
else:
slice_list[0] = indexes
else:
slice_list[0] = self.indexes
if not isinstance(slice_list[0], list):
self.dataset._tensors[subpath][slice_list] = assign_value
else:
for i, index in enumerate(slice_list[0]):
current_slice = [index] + slice_list[1:]
self.dataset._tensors[subpath][
current_slice] = assign_value[i]