Split#

Split - 13
Split - 11
Split - 2
Split - 1

Split - 13 #

Version

name: Split (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

Split a tensor into a list of tensors, along the specified ‘axis’. Lengths of the parts can be specified using input ‘split’. Otherwise, the tensor is split to equal sized parts.

Attributes

axis: Which axis to split on. A negative value means counting dimensions from the back. Accepted range is [-rank, rank-1] where r = rank(input). Default value is 0.

Inputs

Between 1 and 2 inputs.

input (heterogeneous) - T: The tensor to split
split (optional, heterogeneous) - tensor(int64): Optional length of each output. Values should be >= 0.Sum of the values must be equal to the dim value at ‘axis’ specified.

Outputs

Between 1 and 2147483647 outputs.

outputs (variadic, heterogeneous) - T: One or more outputs forming list of tensors after splitting

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

input = np.array([1., 2., 3., 4., 5., 6.]).astype(np.float32)

node = onnx.helper.make_node(
    'Split',
    inputs=['input'],
    outputs=['output_1', 'output_2', 'output_3'],
    axis=0
)

expected_outputs = [np.array([1., 2.]).astype(np.float32), np.array([3., 4.]).astype(np.float32), np.array([5., 6.]).astype(np.float32)]
expect(node, inputs=[input], outputs=[y for y in expected_outputs], name='test_split_equal_parts_1d')

split = np.array([2, 4]).astype(np.int64)
node = onnx.helper.make_node(
    'Split',
    inputs=['input', 'split'],
    outputs=['output_1', 'output_2'],
    axis=0,
)

expected_outputs = [np.array([1., 2.]).astype(np.float32), np.array([3., 4., 5., 6.]).astype(np.float32)]
expect(node, inputs=[input, split], outputs=[y for y in expected_outputs], name='test_split_variable_parts_1d')

input = np.array([[1., 2., 3., 4., 5., 6.],
                  [7., 8., 9., 10., 11., 12.]]).astype(np.float32)

node = onnx.helper.make_node(
    'Split',
    inputs=['input'],
    outputs=['output_1', 'output_2'],
    axis=1
)

expected_outputs = [np.array([[1., 2., 3.], [7., 8., 9.]]).astype(np.float32),
                    np.array([[4., 5., 6.], [10., 11., 12.]]).astype(np.float32)]

expect(node, inputs=[input], outputs=[y for y in expected_outputs], name='test_split_equal_parts_2d')

split = np.array([2, 4]).astype(np.int64)
node = onnx.helper.make_node(
    'Split',
    inputs=['input', 'split'],
    outputs=['output_1', 'output_2'],
    axis=1,
)

expected_outputs = [np.array([[1., 2.], [7., 8.]]).astype(np.float32),
                    np.array([[3., 4., 5., 6.], [9., 10., 11., 12.]]).astype(np.float32)]

expect(node, inputs=[input, split], outputs=[y for y in expected_outputs], name='test_split_variable_parts_2d')

default_values

input = np.array([1., 2., 3., 4., 5., 6.]).astype(np.float32)

# If axis is not specified, split is applied on default axis 0
node = onnx.helper.make_node(
    'Split',
    inputs=['input'],
    outputs=['output_1', 'output_2', 'output_3']
)

expected_outputs = [np.array([1., 2.]).astype(np.float32), np.array([3., 4.]).astype(np.float32), np.array([5., 6.]).astype(np.float32)]
expect(node, inputs=[input], outputs=[y for y in expected_outputs], name='test_split_equal_parts_default_axis')

split = np.array([2, 4]).astype(np.int64)
node = onnx.helper.make_node(
    'Split',
    inputs=['input', 'split'],
    outputs=['output_1', 'output_2']
)

expected_outputs = [np.array([1., 2.]).astype(np.float32), np.array([3., 4., 5., 6.]).astype(np.float32)]
expect(node, inputs=[input, split], outputs=[y for y in expected_outputs], name='test_split_variable_parts_default_axis')

zero_size_splits

input = np.array([]).astype(np.float32)

# Split emtpy tensor to tensors of size zero
split = np.array([0, 0, 0]).astype(np.int64)
node = onnx.helper.make_node(
    'Split',
    inputs=['input', 'split'],
    outputs=['output_1', 'output_2', 'output_3']
)

expected_outputs = [np.array([]).astype(np.float32), np.array([]).astype(np.float32), np.array([]).astype(np.float32)]
expect(node, inputs=[input, split], outputs=[y for y in expected_outputs], name='test_split_zero_size_splits')

Differences

`0`	`0`	`Split a tensor into a list of tensors, along the specified`	`Split a tensor into a list of tensors, along the specified`
`1`	`1`	`'axis'. Lengths of the parts can be specified using argument 'split'.`	`'axis'. Lengths of the parts can be specified using input 'split'.`
`2`	`2`	`Otherwise, the tensor is split to equal sized parts.`	`Otherwise, the tensor is split to equal sized parts.`
`3`	`3`
`4`	`4`	`Attributes`	`Attributes`
`5`	`5`
`6`	`6`	`* axis:`	`* axis:`
`7`	`7`	`Which axis to split on. A negative value means counting dimensions`	`Which axis to split on. A negative value means counting dimensions`
`8`	`8`	`from the back. Accepted range is [-rank, rank-1] where r =`	`from the back. Accepted range is [-rank, rank-1] where r =`
`9`	`9`	`rank(input). Default value is 0.`	`rank(input). Default value is 0.`
`10`		`* split:`
	`10`
`11`	`11`	`length of each output. Values should be >= 0.`	`Inputs`
`12`	`12`
`13`	`13`	`Inputs`	`Between 1 and 2 inputs.`
`14`	`14`
`15`	`15`	`* input (heterogeneous) - T:`	`* input (heterogeneous) - T:`
	`16`		`The tensor to split`
`16`	`17`	`The tensor to split`	`* split (optional, heterogeneous) - tensor(int64):`
	`18`		`Optional length of each output. Values should be >= 0.Sum of the`
	`19`		`values must be equal to the dim value at 'axis' specified.`
`17`	`20`
`18`	`21`	`Outputs`	`Outputs`
`19`	`22`
`20`	`23`	`Between 1 and 2147483647 outputs.`	`Between 1 and 2147483647 outputs.`
`21`	`24`
`22`	`25`	`* outputs (variadic, heterogeneous) - T:`	`* outputs (variadic, heterogeneous) - T:`
`23`	`26`	`One or more outputs forming list of tensors after splitting`	`One or more outputs forming list of tensors after splitting`
`24`	`27`
`25`	`28`	`Type Constraints`	`Type Constraints`
`26`	`29`
`27`	`30`	`* T in (`	`* T in (`
	`31`		`tensor(bfloat16),`
`28`	`32`	`tensor(bool),`	`tensor(bool),`
`29`	`33`	`tensor(complex128),`	`tensor(complex128),`
`30`	`34`	`tensor(complex64),`	`tensor(complex64),`
`31`	`35`	`tensor(double),`	`tensor(double),`
`32`	`36`	`tensor(float),`	`tensor(float),`
`33`	`37`	`tensor(float16),`	`tensor(float16),`
`34`	`38`	`tensor(int16),`	`tensor(int16),`
`35`	`39`	`tensor(int32),`	`tensor(int32),`
`36`	`40`	`tensor(int64),`	`tensor(int64),`
`37`	`41`	`tensor(int8),`	`tensor(int8),`
`38`	`42`	`tensor(string),`	`tensor(string),`
`39`	`43`	`tensor(uint16),`	`tensor(uint16),`
`40`	`44`	`tensor(uint32),`	`tensor(uint32),`
`41`	`45`	`tensor(uint64),`	`tensor(uint64),`
`42`	`46`	`tensor(uint8)`	`tensor(uint8)`
`43`	`47`	`):`	`):`
`44`	`48`	`Constrain input and output types to all tensor types.`	`Constrain input and output types to all tensor types.`

Split - 11 #

Version

name: Split (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

Split a tensor into a list of tensors, along the specified ‘axis’. Lengths of the parts can be specified using argument ‘split’. Otherwise, the tensor is split to equal sized parts.

Attributes

axis: Which axis to split on. A negative value means counting dimensions from the back. Accepted range is [-rank, rank-1] where r = rank(input). Default value is 0.
split: length of each output. Values should be >= 0.

Inputs

input (heterogeneous) - T: The tensor to split

Outputs

Between 1 and 2147483647 outputs.

outputs (variadic, heterogeneous) - T: One or more outputs forming list of tensors after splitting

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.

Differences

`0`	`0`	`Split a tensor into a list of tensors, along the specified`	`Split a tensor into a list of tensors, along the specified`
`1`	`1`	`'axis'. Lengths of the parts can be specified using argument 'split'.`	`'axis'. Lengths of the parts can be specified using argument 'split'.`
`2`	`2`	`Otherwise, the tensor is split to equal sized parts.`	`Otherwise, the tensor is split to equal sized parts.`
`3`	`3`
`4`	`4`	`Attributes`	`Attributes`
`5`	`5`
`6`	`6`	`* axis:`	`* axis:`
`7`	`7`	`Which axis to split on. Default value is 0.`	`Which axis to split on. A negative value means counting dimensions`
	`8`		`from the back. Accepted range is [-rank, rank-1] where r =`
	`9`		`rank(input). Default value is 0.`
`8`	`10`	`* split:`	`* split:`
`9`	`11`	`length of each output`	`length of each output. Values should be >= 0.`
`10`	`12`
`11`	`13`	`Inputs`	`Inputs`
`12`	`14`
`13`	`15`	`* input (heterogeneous) - T:`	`* input (heterogeneous) - T:`
`14`	`16`	`The tensor to split`	`The tensor to split`
`15`	`17`
`16`	`18`	`Outputs`	`Outputs`
`17`	`19`
`18`	`20`	`Between 1 and 2147483647 outputs.`	`Between 1 and 2147483647 outputs.`
`19`	`21`
`20`	`22`	`* outputs (variadic, heterogeneous) - T:`	`* outputs (variadic, heterogeneous) - T:`
`21`	`23`	`One or more outputs forming list of tensors after splitting`	`One or more outputs forming list of tensors after splitting`
`22`	`24`
`23`	`25`	`Type Constraints`	`Type Constraints`
`24`	`26`
`25`	`27`	`* T in (`	`* T in (`
`26`	`28`	`tensor(bool),`	`tensor(bool),`
`27`	`29`	`tensor(complex128),`	`tensor(complex128),`
`28`	`30`	`tensor(complex64),`	`tensor(complex64),`
`29`	`31`	`tensor(double),`	`tensor(double),`
`30`	`32`	`tensor(float),`	`tensor(float),`
`31`	`33`	`tensor(float16),`	`tensor(float16),`
`32`	`34`	`tensor(int16),`	`tensor(int16),`
`33`	`35`	`tensor(int32),`	`tensor(int32),`
`34`	`36`	`tensor(int64),`	`tensor(int64),`
`35`	`37`	`tensor(int8),`	`tensor(int8),`
`36`	`38`	`tensor(string),`	`tensor(string),`
`37`	`39`	`tensor(uint16),`	`tensor(uint16),`
`38`	`40`	`tensor(uint32),`	`tensor(uint32),`
`39`	`41`	`tensor(uint64),`	`tensor(uint64),`
`40`	`42`	`tensor(uint8)`	`tensor(uint8)`
`41`	`43`	`):`	`):`
`42`	`44`	`Constrain input and output types to all tensor types.`	`Constrain input and output types to all tensor types.`

Split - 2 #

Version

name: Split (GitHub)
domain: main
since_version: 2
function: False
support_level: SupportType.COMMON
shape inference: True

This version of the operator has been available since version 2.

Summary

Split a tensor into a list of tensors, along the specified ‘axis’. Lengths of the parts can be specified using argument ‘split’. Otherwise, the tensor is split to equal sized parts.

Attributes

axis: Which axis to split on. Default value is 0.
split: length of each output

Inputs

input (heterogeneous) - T: The tensor to split

Outputs

Between 1 and 2147483647 outputs.

outputs (variadic, heterogeneous) - T: One or more outputs forming list of tensors after splitting

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.

Differences

`0`	`0`	`Split a tensor into a list of tensors, along the specified`	`Split a tensor into a list of tensors, along the specified`
`1`	`1`	`'axis'. The lengths of the split can be specified using argument 'axis' or`	`'axis'. Lengths of the parts can be specified using argument 'split'.`
`2`		`optional second input blob to the operator. Otherwise, the tensor is split`
`3`	`2`	`to equal sized parts.`	`Otherwise, the tensor is split to equal sized parts.`
`4`	`3`
`5`	`4`	`Attributes`	`Attributes`
`6`	`5`
`7`	`6`	`* axis:`	`* axis:`
`8`	`7`	`Which axis to split on`	`Which axis to split on. Default value is 0.`
`9`	`8`	`* split:`	`* split:`
`10`	`9`	`length of each output`	`length of each output`
`11`	`10`
`12`	`11`	`Inputs`	`Inputs`
`13`	`12`
`14`		`Between 1 and 2 inputs.`
`15`
`16`	`13`	`* input (heterogeneous) - T:`	`* input (heterogeneous) - T:`
`17`		`The tensor to split`
`18`	`14`	`* split (optional, heterogeneous) - T:`	`The tensor to split`
`19`		`Optional list of output lengths (see also arg 'split')`
`20`	`15`
`21`	`16`	`Outputs`	`Outputs`
`22`	`17`
`23`	`18`	`Between 1 and 2147483647 outputs.`	`Between 1 and 2147483647 outputs.`
`24`	`19`
`25`	`20`	`* outputs... (variadic, heterogeneous) - T:`	`* outputs (variadic, heterogeneous) - T:`
`26`	`21`	`One or more outputs forming list of tensors after splitting`	`One or more outputs forming list of tensors after splitting`
`27`	`22`
`28`	`23`	`Type Constraints`	`Type Constraints`
`29`	`24`
`30`	`25`	`* T in (`	`* T in (`
	`26`		`tensor(bool),`
	`27`		`tensor(complex128),`
	`28`		`tensor(complex64),`
`31`	`29`	`tensor(double),`	`tensor(double),`
`32`	`30`	`tensor(float),`	`tensor(float),`
`33`	`31`	`tensor(float16)`	`tensor(float16),`
	`32`		`tensor(int16),`
	`33`		`tensor(int32),`
	`34`		`tensor(int64),`
	`35`		`tensor(int8),`
	`36`		`tensor(string),`
	`37`		`tensor(uint16),`
	`38`		`tensor(uint32),`
	`39`		`tensor(uint64),`
	`40`		`tensor(uint8)`
`34`	`41`	`):`	`):`
`35`	`42`	`Constrain input types to float tensors.`	`Constrain input and output types to all tensor types.`

Split - 1 #

Version

name: Split (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

Split a tensor into a list of tensors, along the specified ‘axis’. The lengths of the split can be specified using argument ‘axis’ or optional second input blob to the operator. Otherwise, the tensor is split to equal sized parts.

Attributes

axis: Which axis to split on
split: length of each output

Inputs

Between 1 and 2 inputs.

input (heterogeneous) - T: The tensor to split
split (optional, heterogeneous) - T: Optional list of output lengths (see also arg ‘split’)

Outputs

Between 1 and 2147483647 outputs.

outputs… (variadic, heterogeneous) - T: One or more outputs forming list of tensors after splitting

Type Constraints

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

SpaceToDepth

SplitToSequence

Split#

Split - 13#

Split - 11#

Split - 2#

Split - 1#

Split - 13 #

Split - 11 #

Split - 2 #

Split - 1 #