-
Notifications
You must be signed in to change notification settings - Fork 237
Expand file tree
/
Copy pathndarray.py
More file actions
242 lines (190 loc) · 8.05 KB
/
ndarray.py
File metadata and controls
242 lines (190 loc) · 8.05 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
from typing import TYPE_CHECKING, Any, Generic, List, Tuple, Type, TypeVar, Union, cast
import numpy as np
import orjson
from docarray.base_doc.base_node import BaseNode
from docarray.typing.proto_register import _register_proto
from docarray.typing.tensor.abstract_tensor import AbstractTensor
from docarray.utils._internal.misc import ( # noqa
is_jax_available,
is_tf_available,
is_torch_available,
)
jax_available = is_jax_available()
if jax_available:
import jax.numpy as jnp
from docarray.typing.tensor.jaxarray import JaxArray # noqa: F401
torch_available = is_torch_available()
if torch_available:
import torch
from docarray.typing.tensor.torch_tensor import TorchTensor # noqa: F401
tf_available = is_tf_available()
if tf_available:
import tensorflow as tf # type: ignore
from docarray.typing.tensor.tensorflow_tensor import TensorFlowTensor # noqa: F401
if TYPE_CHECKING:
from docarray.computation.numpy_backend import NumpyCompBackend
from docarray.proto import NdArrayProto
T = TypeVar('T', bound='NdArray')
ShapeT = TypeVar('ShapeT')
tensor_base: type = type(BaseNode)
# the mypy error suppression below should not be necessary anymore once the following
# is released in mypy: https://github.com/python/mypy/pull/14135
class metaNumpy(AbstractTensor.__parametrized_meta__, tensor_base): # type: ignore
pass
@_register_proto(proto_type_name='ndarray')
class NdArray(np.ndarray, AbstractTensor, Generic[ShapeT]):
"""
Subclass of `np.ndarray`, intended for use in a Document.
This enables (de)serialization from/to protobuf and json, data validation,
and coercion from compatible types like `torch.Tensor`.
This type can also be used in a parametrized way, specifying the shape of the array.
---
```python
from docarray import BaseDoc
from docarray.typing import NdArray
import numpy as np
class MyDoc(BaseDoc):
arr: NdArray
image_arr: NdArray[3, 224, 224]
square_crop: NdArray[3, 'x', 'x']
random_image: NdArray[3, ...] # first dimension is fixed, can have arbitrary shape
# create a document with tensors
doc = MyDoc(
arr=np.zeros((128,)),
image_arr=np.zeros((3, 224, 224)),
square_crop=np.zeros((3, 64, 64)),
random_image=np.zeros((3, 128, 256)),
)
assert doc.image_arr.shape == (3, 224, 224)
# automatic shape conversion
doc = MyDoc(
arr=np.zeros((128,)),
image_arr=np.zeros((224, 224, 3)), # will reshape to (3, 224, 224)
square_crop=np.zeros((3, 128, 128)),
random_image=np.zeros((3, 64, 128)),
)
assert doc.image_arr.shape == (3, 224, 224)
# !! The following will raise an error due to shape mismatch !!
from pydantic import ValidationError
try:
doc = MyDoc(
arr=np.zeros((128,)),
image_arr=np.zeros((224, 224)), # this will fail validation
square_crop=np.zeros((3, 128, 64)), # this will also fail validation
random_image=np.zeros((4, 64, 128)), # this will also fail validation
)
except ValidationError as e:
pass
```
---
"""
__parametrized_meta__ = metaNumpy
@classmethod
def _docarray_validate(
cls: Type[T],
value: Union[T, np.ndarray, str, List[Any], Tuple[Any], Any],
) -> T:
if isinstance(value, str):
value = orjson.loads(value)
if isinstance(value, np.ndarray):
return cls._docarray_from_native(value)
elif isinstance(value, NdArray):
return cast(T, value)
elif isinstance(value, AbstractTensor):
return cls._docarray_from_native(value._docarray_to_ndarray())
elif torch_available and isinstance(value, torch.Tensor):
return cls._docarray_from_native(value.detach().cpu().numpy())
elif tf_available and isinstance(value, tf.Tensor):
return cls._docarray_from_native(value.numpy())
elif jax_available and isinstance(value, jnp.ndarray):
return cls._docarray_from_native(value.__array__())
elif isinstance(value, list) or isinstance(value, tuple):
try:
arr_from_list: np.ndarray = np.asarray(value)
return cls._docarray_from_native(arr_from_list)
except Exception:
pass # handled below
try:
arr: np.ndarray = np.ndarray(value)
return cls._docarray_from_native(arr)
except Exception:
pass # handled below
raise ValueError(f'Expected a numpy.ndarray compatible type, got {type(value)}')
@classmethod
def _docarray_from_native(cls: Type[T], value: np.ndarray) -> T:
if cls.__unparametrizedcls__: # This is not None if the tensor is parametrized
return cast(T, value.view(cls.__unparametrizedcls__))
return value.view(cls)
def _docarray_to_json_compatible(self) -> np.ndarray:
"""
Convert `NdArray` into a json compatible object
:return: a representation of the tensor compatible with orjson
"""
return self.unwrap()
def unwrap(self) -> np.ndarray:
"""
Return the original ndarray without any memory copy.
The original view rest intact and is still a Document `NdArray`
but the return object is a pure `np.ndarray` but both object share
the same memory layout.
---
```python
from docarray.typing import NdArray
import numpy as np
from pydantic import parse_obj_as
t1 = parse_obj_as(NdArray, np.zeros((3, 224, 224)))
t2 = t1.unwrap()
# here t2 is a pure np.ndarray but t1 is still a Docarray NdArray
# But both share the same underlying memory
```
---
:return: a `numpy.ndarray`
"""
return self.view(np.ndarray)
@classmethod
def from_protobuf(cls: Type[T], pb_msg: 'NdArrayProto') -> 'T':
"""
Read ndarray from a proto msg
:param pb_msg:
:return: a numpy array
"""
source = pb_msg.dense
if source.buffer:
x = np.frombuffer(bytearray(source.buffer), dtype=source.dtype)
return cls._docarray_from_native(x.reshape(source.shape))
elif len(source.shape) > 0:
return cls._docarray_from_native(np.zeros(source.shape))
else:
raise ValueError(f'proto message {pb_msg} cannot be cast to a NdArray')
def to_protobuf(self) -> 'NdArrayProto':
"""
Transform self into a NdArrayProto protobuf message
"""
from docarray.proto import NdArrayProto
nd_proto = NdArrayProto()
nd_proto.dense.buffer = self.tobytes()
nd_proto.dense.ClearField('shape')
nd_proto.dense.shape.extend(list(self.shape))
nd_proto.dense.dtype = self.dtype.str
return nd_proto
@staticmethod
def get_comp_backend() -> 'NumpyCompBackend':
"""Return the computational backend of the tensor"""
from docarray.computation.numpy_backend import NumpyCompBackend
return NumpyCompBackend()
def __class_getitem__(cls, item: Any, *args, **kwargs):
# see here for mypy bug: https://github.com/python/mypy/issues/14123
return AbstractTensor.__class_getitem__.__func__(cls, item) # type: ignore
@classmethod
def _docarray_from_ndarray(cls: Type[T], value: np.ndarray) -> T:
"""Create a `tensor from a numpy array
PS: this function is different from `from_ndarray` because it is private under the docarray namesapce.
This allows us to avoid breaking change if one day we introduce a Tensor backend with a `from_ndarray` method.
"""
return cls._docarray_from_native(value)
def _docarray_to_ndarray(self) -> np.ndarray:
"""Create a `tensor from a numpy array
PS: this function is different from `from_ndarray` because it is private under the docarray namesapce.
This allows us to avoid breaking change if one day we introduce a Tensor backend with a `from_ndarray` method.
"""
return self.unwrap()