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
0 | 0 | Matrix product that behaves like numpy.matmul: https://docs.scipy.org/doc/numpy-1.13.0/reference/generated/numpy.matmul.html | Matrix product that behaves like numpy.matmul: https://docs.scipy.org/doc/numpy-1.13.0/reference/generated/numpy.matmul.html |
1 | 1 | | |
2 | 2 | **Inputs** | **Inputs** |
3 | 3 | | |
4 | 4 | * **A** (heterogeneous) - **T**: | * **A** (heterogeneous) - **T**: |
5 | 5 | N-dimensional matrix A | N-dimensional matrix A |
6 | 6 | * **B** (heterogeneous) - **T**: | * **B** (heterogeneous) - **T**: |
7 | 7 | N-dimensional matrix B | N-dimensional matrix B |
8 | 8 | | |
9 | 9 | **Outputs** | **Outputs** |
10 | 10 | | |
11 | 11 | * **Y** (heterogeneous) - **T**: | * **Y** (heterogeneous) - **T**: |
12 | 12 | Matrix multiply results from A * B | Matrix multiply results from A * B |
13 | 13 | | |
14 | 14 | **Type Constraints** | **Type Constraints** |
15 | 15 | | |
16 | 16 | * **T** in ( | * **T** in ( |
17 | tensor(bfloat16), | ||
17 | 18 | tensor(double), | tensor(double), |
18 | 19 | tensor(float), | tensor(float), |
19 | 20 | tensor(float16), | tensor(float16), |
20 | 21 | tensor(int32), | tensor(int32), |
21 | 22 | tensor(int64), | tensor(int64), |
22 | 23 | tensor(uint32), | tensor(uint32), |
23 | 24 | tensor(uint64) | tensor(uint64) |
24 | 25 | ): | ): |
25 | 26 | 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
0 | 0 | Matrix product that behaves like numpy.matmul: https://docs.scipy.org/doc/numpy-1.13.0/reference/generated/numpy.matmul.html | Matrix product that behaves like numpy.matmul: https://docs.scipy.org/doc/numpy-1.13.0/reference/generated/numpy.matmul.html |
1 | 1 | | |
2 | 2 | **Inputs** | **Inputs** |
3 | 3 | | |
4 | 4 | * **A** (heterogeneous) - **T**: | * **A** (heterogeneous) - **T**: |
5 | 5 | N-dimensional matrix A | N-dimensional matrix A |
6 | 6 | * **B** (heterogeneous) - **T**: | * **B** (heterogeneous) - **T**: |
7 | 7 | N-dimensional matrix B | N-dimensional matrix B |
8 | 8 | | |
9 | 9 | **Outputs** | **Outputs** |
10 | 10 | | |
11 | 11 | * **Y** (heterogeneous) - **T**: | * **Y** (heterogeneous) - **T**: |
12 | 12 | Matrix multiply results from A * B | Matrix multiply results from A * B |
13 | 13 | | |
14 | 14 | **Type Constraints** | **Type Constraints** |
15 | 15 | | |
16 | 16 | * **T** in ( | * **T** in ( |
17 | 17 | tensor(double), | tensor(double), |
18 | 18 | tensor(float), | tensor(float), |
19 | 19 | tensor(float16) | |
20 | tensor(int32), | ||
21 | tensor(int64), | ||
22 | tensor(uint32), | ||
23 | tensor(uint64) | ||
20 | 24 | ): | ): |
21 | 25 | Constrain input and output types to float 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.