Unsqueeze#

Unsqueeze - 13#

Version

  • name: Unsqueeze (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

Insert single-dimensional entries to the shape of an input tensor (data). Takes one required input axes - which contains a list of dimension indices and this operator will insert a dimension of value 1 into the corresponding index of the output tensor (expanded).

For example:

Given an input tensor (data) of shape [3, 4, 5], then Unsqueeze(data, axes=[0, 4]) outputs a tensor (expanded) containing same data as data but with shape [1, 3, 4, 5, 1].

The input axes should not contain any duplicate entries. It is an error if it contains duplicates. The rank of the output tensor (output_rank) is the rank of the input tensor (data) plus the number of values in axes. Each value in axes should be within the (inclusive) range [-output_rank , output_rank - 1]. The order of values in axes does not matter and can come in any order.

Inputs

  • data (heterogeneous) - T: Original tensor

  • axes (heterogeneous) - tensor(int64): List of integers indicating the dimensions to be inserted. Negative value means counting dimensions from the back. Accepted range is [-r, r-1] where r = rank(expanded).

Outputs

  • expanded (heterogeneous) - T: Reshaped tensor with same data as input.

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

_unsqueeze_one_axis

import numpy as np
import onnx

x = np.random.randn(3, 4, 5).astype(np.float32)

for i in range(x.ndim):
    axes = np.array([i]).astype(np.int64)
    node = onnx.helper.make_node(
        "Unsqueeze",
        inputs=["x", "axes"],
        outputs=["y"],
    )
    y = np.expand_dims(x, axis=i)

    expect(
        node,
        inputs=[x, axes],
        outputs=[y],
        name="test_unsqueeze_axis_" + str(i),
    )

_unsqueeze_two_axes

import numpy as np
import onnx

x = np.random.randn(3, 4, 5).astype(np.float32)
axes = np.array([1, 4]).astype(np.int64)

node = onnx.helper.make_node(
    "Unsqueeze",
    inputs=["x", "axes"],
    outputs=["y"],
)
y = np.expand_dims(x, axis=1)
y = np.expand_dims(y, axis=4)

expect(node, inputs=[x, axes], outputs=[y], name="test_unsqueeze_two_axes")

_unsqueeze_three_axes

import numpy as np
import onnx

x = np.random.randn(3, 4, 5).astype(np.float32)
axes = np.array([2, 4, 5]).astype(np.int64)

node = onnx.helper.make_node(
    "Unsqueeze",
    inputs=["x", "axes"],
    outputs=["y"],
)
y = np.expand_dims(x, axis=2)
y = np.expand_dims(y, axis=4)
y = np.expand_dims(y, axis=5)

expect(node, inputs=[x, axes], outputs=[y], name="test_unsqueeze_three_axes")

_unsqueeze_unsorted_axes

import numpy as np
import onnx

x = np.random.randn(3, 4, 5).astype(np.float32)
axes = np.array([5, 4, 2]).astype(np.int64)

node = onnx.helper.make_node(
    "Unsqueeze",
    inputs=["x", "axes"],
    outputs=["y"],
)
y = np.expand_dims(x, axis=2)
y = np.expand_dims(y, axis=4)
y = np.expand_dims(y, axis=5)

expect(node, inputs=[x, axes], outputs=[y], name="test_unsqueeze_unsorted_axes")

_unsqueeze_negative_axes

import numpy as np
import onnx

node = onnx.helper.make_node(
    "Unsqueeze",
    inputs=["x", "axes"],
    outputs=["y"],
)
x = np.random.randn(1, 3, 1, 5).astype(np.float32)
axes = np.array([-2]).astype(np.int64)
y = np.expand_dims(x, axis=-2)
expect(node, inputs=[x, axes], outputs=[y], name="test_unsqueeze_negative_axes")

Unsqueeze - 11#

Version

  • name: Unsqueeze (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

Insert single-dimensional entries to the shape of an input tensor (data). Takes one required argument axes - which contains a list of dimension indices and this operator will insert a dimension of value 1 into the corresponding index of the output tensor (expanded).

For example:

Given an input tensor (data) of shape [3, 4, 5], then Unsqueeze(data, axes=[0, 4]) outputs a tensor (expanded) containing same data as data but with shape [1, 3, 4, 5, 1].

The attribute axes should not contain any duplicate entries. It is an error if it contains duplicates. The rank of the output tensor (output_rank) is the rank of the input tensor (data) plus the number of values in axes. Each value in axes should be within the (inclusive) range [-output_rank , output_rank - 1]. The order of values in axes does not matter and can come in any order.

Attributes

  • axes (required): List of integers indicating the dimensions to be inserted. Negative value means counting dimensions from the back. Accepted range is [-r, r-1] where r = rank(expanded).

Inputs

  • data (heterogeneous) - T: Original tensor

Outputs

  • expanded (heterogeneous) - T: Reshaped tensor with same data as input.

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 input and output types to all tensor types.

Unsqueeze - 1#

Version

  • name: Unsqueeze (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

Insert single-dimensional entries to the shape of a tensor. Takes one required argument axes, a list of dimensions that will be inserted. Dimension indices in axes are as seen in the output tensor. For example:

Given a tensor such that tensor with shape [3, 4, 5], then Unsqueeze(tensor, axes=[0, 4]) has shape [1, 3, 4, 5, 1]

Attributes

  • axes (required): List of non-negative integers, indicate the dimensions to be inserted

Inputs

  • data (heterogeneous) - T: Original tensor

Outputs

  • expanded (heterogeneous) - T: Reshaped tensor with same data as input.

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 input and output types to all tensor types.