Transpose

Description

Transposes the input tensor.

Input

data: tensor of type float16, float, int8, int16, int32, int64, uint8, uint16, uint32, uint64 or bool.

Attribute

perm: int list, indicating the position of each dimension after the input tensor is transposed.

Output

transposed: tensor of the identical data type as data.

Constraints

None.

ONNX Opset Support

Opset v8/v9/v10/v11/v12/v13/v14/v15/v16/v17/v18