Concat

Concat - 13

Version

• name: Concat (GitHub)

• domain: main

• since_version: 13

• function: False

• support_level: SupportType.COMMON

• shape inference: True

This version of the operator has been available since version 13.

Summary

Concatenate a list of tensors into a single tensor. All input tensors must have the same shape, except for the dimension size of the axis to concatenate on.

Attributes

• axis (required): Which axis to concat on. A negative value means counting dimensions from the back. Accepted range is [-r, r-1] where r = rank(inputs)..

Inputs

Between 1 and 2147483647 inputs.

• inputs (variadic, heterogeneous) - T: List of tensors for concatenation

Outputs

• concat_result (heterogeneous) - T: Concatenated tensor

Type Constraints

• 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) ): Constrain output types to any tensor type.

Examples

Differences

0	0	Concatenate a list of tensors into a single tensor. All input tensors must have the same shape, except for the dimension size of the axis to concatenate on.	Concatenate a list of tensors into a single tensor. All input tensors must have the same shape, except for the dimension size of the axis to concatenate on.
1	1
2	2	**Attributes**	**Attributes**
3	3
4	4	* **axis** (required):	* **axis** (required):
5	5	Which axis to concat on. A negative value means counting dimensions	Which axis to concat on. A negative value means counting dimensions
6	6	from the back. Accepted range is [-r, r-1] where r = rank(inputs)..	from the back. Accepted range is [-r, r-1] where r = rank(inputs)..
7	7
8	8	**Inputs**	**Inputs**
9	9
10	10	Between 1 and 2147483647 inputs.	Between 1 and 2147483647 inputs.
11	11
12	12	* **inputs** (variadic, heterogeneous) - **T**:	* **inputs** (variadic, heterogeneous) - **T**:
13	13	List of tensors for concatenation	List of tensors for concatenation
14	14
15	15	**Outputs**	**Outputs**
16	16
17	17	* **concat_result** (heterogeneous) - **T**:	* **concat_result** (heterogeneous) - **T**:
18	18	Concatenated tensor	Concatenated tensor
19	19
20	20	**Type Constraints**	**Type Constraints**
21	21
22	22	* **T** in (	* **T** in (
	23		tensor(bfloat16),
23	24	tensor(bool),	tensor(bool),
24	25	tensor(complex128),	tensor(complex128),
25	26	tensor(complex64),	tensor(complex64),
26	27	tensor(double),	tensor(double),
27	28	tensor(float),	tensor(float),
28	29	tensor(float16),	tensor(float16),
29	30	tensor(int16),	tensor(int16),
30	31	tensor(int32),	tensor(int32),
31	32	tensor(int64),	tensor(int64),
32	33	tensor(int8),	tensor(int8),
33	34	tensor(string),	tensor(string),
34	35	tensor(uint16),	tensor(uint16),
35	36	tensor(uint32),	tensor(uint32),
36	37	tensor(uint64),	tensor(uint64),
37	38	tensor(uint8)	tensor(uint8)
38	39	):	):
39	40	Constrain output types to any tensor type.	Constrain output types to any tensor type.

Concat - 11

Version

• name: Concat (GitHub)

• domain: main

• since_version: 11

• function: False

• support_level: SupportType.COMMON

• shape inference: True

This version of the operator has been available since version 11.

Summary

Concatenate a list of tensors into a single tensor. All input tensors must have the same shape, except for the dimension size of the axis to concatenate on.

Attributes

• axis (required): Which axis to concat on. A negative value means counting dimensions from the back. Accepted range is [-r, r-1] where r = rank(inputs)..

Inputs

Between 1 and 2147483647 inputs.

• inputs (variadic, heterogeneous) - T: List of tensors for concatenation

Outputs

• concat_result (heterogeneous) - T: Concatenated tensor

Type Constraints

• 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) ): Constrain output types to any tensor type.

Differences

0	0	Concatenate a list of tensors into a single tensor	Concatenate a list of tensors into a single tensor. All input tensors must have the same shape, except for the dimension size of the axis to concatenate on.
1	1
2	2	**Attributes**	**Attributes**
3	3
4	4	* **axis** (required):	* **axis** (required):
	5		Which axis to concat on. A negative value means counting dimensions
5	6	Which axis to concat on	from the back. Accepted range is [-r, r-1] where r = rank(inputs)..
6	7
7	8	**Inputs**	**Inputs**
8	9
9	10	Between 1 and 2147483647 inputs.	Between 1 and 2147483647 inputs.
10	11
11	12	* **inputs** (variadic, heterogeneous) - **T**:	* **inputs** (variadic, heterogeneous) - **T**:
12	13	List of tensors for concatenation	List of tensors for concatenation
13	14
14	15	**Outputs**	**Outputs**
15	16
16	17	* **concat_result** (heterogeneous) - **T**:	* **concat_result** (heterogeneous) - **T**:
17	18	Concatenated tensor	Concatenated tensor
18	19
19	20	**Type Constraints**	**Type Constraints**
20	21
21	22	* **T** in (	* **T** in (
22	23	tensor(bool),	tensor(bool),
23	24	tensor(complex128),	tensor(complex128),
24	25	tensor(complex64),	tensor(complex64),
25	26	tensor(double),	tensor(double),
26	27	tensor(float),	tensor(float),
27	28	tensor(float16),	tensor(float16),
28	29	tensor(int16),	tensor(int16),
29	30	tensor(int32),	tensor(int32),
30	31	tensor(int64),	tensor(int64),
31	32	tensor(int8),	tensor(int8),
32	33	tensor(string),	tensor(string),
33	34	tensor(uint16),	tensor(uint16),
34	35	tensor(uint32),	tensor(uint32),
35	36	tensor(uint64),	tensor(uint64),
36	37	tensor(uint8)	tensor(uint8)
37	38	):	):
38	39	Constrain output types to any tensor type.	Constrain output types to any tensor type.

Concat - 4

Version

• name: Concat (GitHub)

• domain: main

• since_version: 4

• function: False

• support_level: SupportType.COMMON

• shape inference: True

This version of the operator has been available since version 4.

Summary

Concatenate a list of tensors into a single tensor

Attributes

• axis (required): Which axis to concat on

Inputs

Between 1 and 2147483647 inputs.

• inputs (variadic, heterogeneous) - T: List of tensors for concatenation

Outputs

• concat_result (heterogeneous) - T: Concatenated tensor

Type Constraints

• 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) ): Constrain output types to any tensor type.

Differences

0	0	Concatenate a list of tensors into a single tensor	Concatenate a list of tensors into a single tensor
1	1
2	2	**Attributes**	**Attributes**
3	3
4	4	* **axis**:	* **axis** (required):
5	5	Which axis to concat on. Default value is 1.	Which axis to concat on
6	6
7	7	**Inputs**	**Inputs**
8	8
9	9	Between 1 and 2147483647 inputs.	Between 1 and 2147483647 inputs.
10	10
11	11	* **inputs** (variadic, heterogeneous) - **T**:	* **inputs** (variadic, heterogeneous) - **T**:
12	12	List of tensors for concatenation	List of tensors for concatenation
13	13
14	14	**Outputs**	**Outputs**
15	15
16	16	* **concat_result** (heterogeneous) - **T**:	* **concat_result** (heterogeneous) - **T**:
17	17	Concatenated tensor	Concatenated tensor
18	18
19	19	**Type Constraints**	**Type Constraints**
20	20
21	21	* **T** in (	* **T** in (
	22		tensor(bool),
	23		tensor(complex128),
	24		tensor(complex64),
22	25	tensor(double),	tensor(double),
23	26	tensor(float),	tensor(float),
24	27	tensor(float16)	tensor(float16),
	28		tensor(int16),
	29		tensor(int32),
	30		tensor(int64),
	31		tensor(int8),
	32		tensor(string),
	33		tensor(uint16),
	34		tensor(uint32),
	35		tensor(uint64),
	36		tensor(uint8)
25	37	):	):
26	38	Constrain output types to float tensors.	Constrain output types to any tensor type.

Concat - 1

Version

• name: Concat (GitHub)

• domain: main

• since_version: 1

• function: False

• support_level: SupportType.COMMON

• shape inference: False

This version of the operator has been available since version 1.

Summary

Concatenate a list of tensors into a single tensor

Attributes

• axis: Which axis to concat on. Default value is 1.

Inputs

Between 1 and 2147483647 inputs.

• inputs (variadic, heterogeneous) - T: List of tensors for concatenation

Outputs

• concat_result (heterogeneous) - T: Concatenated tensor

Type Constraints

• T in ( tensor(double), tensor(float), tensor(float16) ): Constrain output types to float tensors.

previous

Compress

next

ConcatFromSequence