Transpose#

Transpose - 13 #

Version

name: Transpose (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

Transpose the input tensor similar to numpy.transpose. For example, when perm=(1, 0, 2), given an input tensor of shape (1, 2, 3), the output shape will be (2, 1, 3).

Attributes

perm: A list of integers. By default, reverse the dimensions, otherwise permute the axes according to the values given.

Inputs

data (heterogeneous) - T: An input tensor.

Outputs

transposed (heterogeneous) - T: Transposed output.

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 input and output types to all tensor types.

Examples

_default

import numpy as np
import onnx

shape = (2, 3, 4)
data = np.random.random_sample(shape).astype(np.float32)

node = onnx.helper.make_node(
    "Transpose", inputs=["data"], outputs=["transposed"]
)

transposed = np.transpose(data)
expect(node, inputs=[data], outputs=[transposed], name="test_transpose_default")

_all_permutations

import numpy as np
import onnx

shape = (2, 3, 4)
data = np.random.random_sample(shape).astype(np.float32)
permutations = list(itertools.permutations(np.arange(len(shape))))

for i in range(len(permutations)):
    node = onnx.helper.make_node(
        "Transpose",
        inputs=["data"],
        outputs=["transposed"],
        perm=permutations[i],
    )
    transposed = np.transpose(data, permutations[i])
    expect(
        node,
        inputs=[data],
        outputs=[transposed],
        name="test_transpose_all_permutations_" + str(i),
    )

Transpose - 1 vs 13

Transpose - 1 #