Concatenation

Concatenates input tensors into an output tensor.

Attributes

axis the axis on which the concatenation is applied. For inputs with rank n, the default value is \(max(0, n-3)\).

Inputs

inputs: tensors of type T. Limited up to 10000 tensors.

Outputs

output: tensor of type T.

Data Types

T: bool, int8, int32, int64, float16, float32, bfloat16

Shape Information

inputs tensors of rank n. The tensors’ shapes must match, excluding the axis dimension.

output tensor of rank n. The shape is matching the inputs’ shape, excluding the axis dimension, which is the sum of the axis dimension of all input tensors.

DLA Support

DLA FP16 and DLA INT8 are supported for concatenation across C dimensions only.

Examples

Concatenation

in1 = network.add_input("input1", dtype=trt.float32, shape=(1, 1, 2, 5))
in2 = network.add_input("input2", dtype=trt.float32, shape=(1, 2, 2, 5))
in3 = network.add_input("input3", dtype=trt.float32, shape=(1, 1, 2, 5))
layer = network.add_concatenation([in1, in2, in3])
network.mark_output(layer.get_output(0))

inputs[in1.name] = np.array([[[[-3.0, -2.0, -1.0, 10.0, -25.0], [0.0, 1.0, 2.0, -2.0, -1.0]]]])
inputs[in2.name] = np.array(
    [
        [[[-3.0, -2.0, -1.0, 10.0, -25.0], [0.0, 1.0, 2.0, -2.0, -1.0]]],
        [[[-4.0, -4.0, -4.0, -4.0, -4.0], [-4.0, -4.0, -4.0, -4.0, -4.0]]],
    ]
)
inputs[in3.name] = np.array([[[[-3.0, -2.0, -1.0, 10.0, -25.0], [0.0, 1.0, 2.0, -2.0, -1.0]]]])

outputs[layer.get_output(0).name] = layer.get_output(0).shape
expected[layer.get_output(0).name] = np.array(
    [
        [
            [[-3.0, -2.0, -1.0, 10.0, -25.0], [0.0, 1.0, 2.0, -2.0, -1.0]],
            [[-3.0, -2.0, -1.0, 10.0, -25.0], [0.0, 1.0, 2.0, -2.0, -1.0]],
            [[-4.0, -4.0, -4.0, -4.0, -4.0], [-4.0, -4.0, -4.0, -4.0, -4.0]],
            [[-3.0, -2.0, -1.0, 10.0, -25.0], [0.0, 1.0, 2.0, -2.0, -1.0]],
        ]
    ]
)

C++ API

For more information about the C++ IConcatenationLayer operator, refer to the C++ IConcatenationLayer documentation.

Python API

For more information about the Python IConcatenationLayer operator, refer to the Python IConcatenationLayer documentation.