Squeeze - 11 vs 23

Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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. Squeeze11 → Squeeze23 +7 -9
Squeeze11 → Squeeze23 RENAMED
@@ -1 +1 @@
1
1
  Remove single-dimensional entries from the shape of a tensor.
2
- Takes a parameter axes with a list of axes to squeeze.
2
+ Takes an input axes with a list of axes to squeeze.
3
3
  If axes is not provided, all the single dimensions will be removed from
4
4
  the shape. If an axis is selected with shape entry not equal to one, an error is raised.
5
- ### Attributes
5
+ ### Inputs
6
+ Between 1 and 2 inputs.
6
- * **axes - INTS** :
7
-
8
- List of integers indicating the dimensions to squeeze. Negative value means counting dimensions from the back. Accepted range is [-r, r-1] where r = rank(data).
9
-
10
- ### Inputs
11
7
  - **data** (heterogeneous) - **T**:
12
8
  Tensors with at least max(dims) dimensions.
9
+ - **axes** (optional, heterogeneous) - **tensor(int64)**:
10
+
11
+ List of integers indicating the dimensions to squeeze. Negative value means counting dimensions from the back. Accepted range is [-r, r-1] where r = rank(data).
13
12
  ### Outputs
14
13
  - **squeezed** (heterogeneous) - **T**:
15
14
  Reshaped tensor with same data as input.
16
15
  ### Type Constraints
17
- * **T** in ( 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) ):
16
+ * **T** in ( tensor(bfloat16), tensor(bool), tensor(complex128), tensor(complex64), tensor(double), tensor(float), tensor(float16), tensor(float4e2m1), 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) ):
18
- Constrain input and output types to all tensor types.+ Constrain input and output types to all tensor types up to IRv11.? ++++++++++++