Constant - 13 vs 21

Next section compares an older to a newer version of the same operator after both definition are converted into markdown text. Green means an addition to the newer version, red means a deletion. Anything else is unchanged.

Files changed (1) hide show
  1. Constant13 → Constant21 +1 -1
Constant13 → Constant21 RENAMED
@@ -1 +1 @@
1
1
  This operator produces a constant tensor. Exactly one of the provided attributes, either value, sparse_value,
2
2
  or value_* must be specified.
3
3
  ### Attributes
4
4
  * **sparse_value - SPARSE_TENSOR** :
5
5
  The value for the elements of the output tensor in sparse format.
6
6
  * **value - TENSOR** :
7
7
  The value for the elements of the output tensor.
8
8
  * **value_float - FLOAT** :
9
9
  The value for the sole element for the scalar, float32, output tensor.
10
10
  * **value_floats - FLOATS** :
11
11
  The values for the elements for the 1D, float32, output tensor.
12
12
  * **value_int - INT** :
13
13
  The value for the sole element for the scalar, int64, output tensor.
14
14
  * **value_ints - INTS** :
15
15
  The values for the elements for the 1D, int64, output tensor.
16
16
  * **value_string - STRING** :
17
17
  The value for the sole element for the scalar, UTF-8 string, output tensor.
18
18
  * **value_strings - STRINGS** :
19
19
  The values for the elements for the 1D, UTF-8 string, output tensor.
20
20
  ### Outputs
21
21
  - **output** (heterogeneous) - **T**:
22
22
  Output tensor containing the same value of the provided tensor.
23
23
  ### Type Constraints
24
- * **T** in ( tensor(bfloat16), tensor(bool), tensor(complex128), tensor(complex64), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(string), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8) ):
24
+ * **T** in ( tensor(bfloat16), tensor(bool), tensor(complex128), tensor(complex64), tensor(double), tensor(float), tensor(float16), tensor(float8e4m3fn), tensor(float8e4m3fnuz), tensor(float8e5m2), tensor(float8e5m2fnuz), tensor(int16), tensor(int32), tensor(int4), tensor(int64), tensor(int8), tensor(string), tensor(uint16), tensor(uint32), tensor(uint4), tensor(uint64), tensor(uint8) ):
25
25
  Constrain input and output types to all tensor types.