MatMul#

MatMul - 13#

Version

  • name: MatMul (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

Matrix product that behaves like numpy.matmul: https://docs.scipy.org/doc/numpy-1.13.0/reference/generated/numpy.matmul.html

Inputs

  • A (heterogeneous) - T: N-dimensional matrix A

  • B (heterogeneous) - T: N-dimensional matrix B

Outputs

  • Y (heterogeneous) - T: Matrix multiply results from A * B

Type Constraints

  • T in ( tensor(bfloat16), tensor(double), tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64) ): Constrain input and output types to float/int tensors.

Examples

default

node = onnx.helper.make_node(
    'MatMul',
    inputs=['a', 'b'],
    outputs=['c'],
)

# 2d
a = np.random.randn(3, 4).astype(np.float32)
b = np.random.randn(4, 3).astype(np.float32)
c = np.matmul(a, b)
expect(node, inputs=[a, b], outputs=[c],
       name='test_matmul_2d')

# 3d
a = np.random.randn(2, 3, 4).astype(np.float32)
b = np.random.randn(2, 4, 3).astype(np.float32)
c = np.matmul(a, b)
expect(node, inputs=[a, b], outputs=[c],
       name='test_matmul_3d')

# 4d
a = np.random.randn(1, 2, 3, 4).astype(np.float32)
b = np.random.randn(1, 2, 4, 3).astype(np.float32)
c = np.matmul(a, b)
expect(node, inputs=[a, b], outputs=[c],
       name='test_matmul_4d')

Differences

00Matrix product that behaves like numpy.matmul: https://docs.scipy.org/doc/numpy-1.13.0/reference/generated/numpy.matmul.htmlMatrix product that behaves like numpy.matmul: https://docs.scipy.org/doc/numpy-1.13.0/reference/generated/numpy.matmul.html
11
22**Inputs****Inputs**
33
44* **A** (heterogeneous) - **T**:* **A** (heterogeneous) - **T**:
55 N-dimensional matrix A N-dimensional matrix A
66* **B** (heterogeneous) - **T**:* **B** (heterogeneous) - **T**:
77 N-dimensional matrix B N-dimensional matrix B
88
99**Outputs****Outputs**
1010
1111* **Y** (heterogeneous) - **T**:* **Y** (heterogeneous) - **T**:
1212 Matrix multiply results from A * B Matrix multiply results from A * B
1313
1414**Type Constraints****Type Constraints**
1515
1616* **T** in (* **T** in (
17 tensor(bfloat16),
1718 tensor(double), tensor(double),
1819 tensor(float), tensor(float),
1920 tensor(float16), tensor(float16),
2021 tensor(int32), tensor(int32),
2122 tensor(int64), tensor(int64),
2223 tensor(uint32), tensor(uint32),
2324 tensor(uint64) tensor(uint64)
2425 ): ):
2526 Constrain input and output types to float/int tensors. Constrain input and output types to float/int tensors.

MatMul - 9#

Version

  • name: MatMul (GitHub)

  • domain: main

  • since_version: 9

  • function: False

  • support_level: SupportType.COMMON

  • shape inference: True

This version of the operator has been available since version 9.

Summary

Matrix product that behaves like numpy.matmul: https://docs.scipy.org/doc/numpy-1.13.0/reference/generated/numpy.matmul.html

Inputs

  • A (heterogeneous) - T: N-dimensional matrix A

  • B (heterogeneous) - T: N-dimensional matrix B

Outputs

  • Y (heterogeneous) - T: Matrix multiply results from A * B

Type Constraints

  • T in ( tensor(double), tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64) ): Constrain input and output types to float/int tensors.

Differences

00Matrix product that behaves like numpy.matmul: https://docs.scipy.org/doc/numpy-1.13.0/reference/generated/numpy.matmul.htmlMatrix product that behaves like numpy.matmul: https://docs.scipy.org/doc/numpy-1.13.0/reference/generated/numpy.matmul.html
11
22**Inputs****Inputs**
33
44* **A** (heterogeneous) - **T**:* **A** (heterogeneous) - **T**:
55 N-dimensional matrix A N-dimensional matrix A
66* **B** (heterogeneous) - **T**:* **B** (heterogeneous) - **T**:
77 N-dimensional matrix B N-dimensional matrix B
88
99**Outputs****Outputs**
1010
1111* **Y** (heterogeneous) - **T**:* **Y** (heterogeneous) - **T**:
1212 Matrix multiply results from A * B Matrix multiply results from A * B
1313
1414**Type Constraints****Type Constraints**
1515
1616* **T** in (* **T** in (
1717 tensor(double), tensor(double),
1818 tensor(float), tensor(float),
1919 tensor(float16) tensor(float16),
20 tensor(int32),
21 tensor(int64),
22 tensor(uint32),
23 tensor(uint64)
2024 ): ):
2125 Constrain input and output types to float tensors. Constrain input and output types to float/int tensors.

MatMul - 1#

Version

  • name: MatMul (GitHub)

  • domain: main

  • since_version: 1

  • function: False

  • support_level: SupportType.COMMON

  • shape inference: True

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

Summary

Matrix product that behaves like numpy.matmul: https://docs.scipy.org/doc/numpy-1.13.0/reference/generated/numpy.matmul.html

Inputs

  • A (heterogeneous) - T: N-dimensional matrix A

  • B (heterogeneous) - T: N-dimensional matrix B

Outputs

  • Y (heterogeneous) - T: Matrix multiply results from A * B

Type Constraints

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