Det#

  • Domain: ai.onnx

  • Since version: 22

Det calculates determinant of a square matrix or batches of square matrices. Det takes one input tensor of shape [*, M, M], where * is zero or more batch dimensions, and the inner-most 2 dimensions form square matrices. The output is a tensor of shape [*], containing the determinants of all input submatrices. e.g., When the input is 2-D, the output is a scalar(shape is empty: []).

Inputs

  • X (T): Input tensor

Outputs

  • Y (T): Output tensor

Type Constraints

  • T: Constrain input and output types to floating-point tensors. Allowed types: tensor(bfloat16), tensor(double), tensor(float), tensor(float16).

Examples#

test_cc_det_bfloat16

Node:
  Det(X) -> (Y)

Inputs:
  X: shape=(3, 2, 2), dtype=bfloat16
    [[[0, 1],
      [2, 3]],

     [[1, 2],
      [2, 4]],

     [[1, 2],
      [3, 4]]]

Outputs:
  Y: shape=(3,), dtype=bfloat16
    [-2, 0, -2]

test_cc_det_bfloat16_empty_batch

Node:
  Det(X) -> (Y)

Inputs:
  X: shape=(0, 2, 2), dtype=bfloat16
    []

Outputs:
  Y: shape=(0,), dtype=bfloat16
    []

test_cc_det_bfloat16_scalar

Node:
  Det(X) -> (Y)

Inputs:
  X: shape=(2, 2), dtype=bfloat16
    [[1, 2],
     [3, 4]]

Outputs:
  Y: shape=(), dtype=bfloat16
    -2

Differences with previous version (11)#

SchemaDiff: Det (domain 'ai.onnx')

  • old version: 11

  • new version: 22

  • breaking: no

Type constraints:

  • changed ‘T’: added types: [‘tensor(bfloat16)’]

Version History#