Concat

Description

Concatenates a list of tensors into a single tensor. All input tensors must have the same shape, except for the size of the dimensions of the axes to be concatenated.

Input

inputs: list of tensors to be concatenated. The input data types must be the same. The data type can be float16, float, int8, int16, int32, int64, uint8, uint16, uint32, or uint64.

Attribute

axis: (optional) axis on which the concatenation operation is performed. A negative number indicates that the dimension is counted from back to front. The value range is [-r, r - 1], where r indicates the number of dimensions of the input.

Output

concat_result: output concatenated tensor. The data type is the same as the input data.

Constraints

None.

ONNX Opset Support

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

Parent topic: Supported ONNX Operators