Identity¶

Outputs the given input tensor to the output tensor. When a tensor precision is explicitly specified, the input is transformed from one precision to another.

Other than conversions between the same type (float32 -> float32 for example), the only valid conversions are:

(float32 | float16) -> uint8

uint8 -> (float32 | float16)

Inputs¶

input: tensor of type T1.

Outputs¶

output: tensor of type T2.

Data Types¶

T1: bool, int8, uint8, int32, float16, float32

T2: bool, int8, uint8, int32, float16, float32

Shape Information¶

input and output are tensors with a shape of \([a_0,...,a_n]\)

Examples¶

Identity

in1 = network.add_input("input1", dtype=trt.float32, shape=(1, 1, 3, 3))
layer = network.add_identity(in1)
network.mark_output(layer.get_output(0))

inputs[in1.name] = np.array(
    [
        [
            [
                [1.0, 2.0, 3.0],
                [4.0, 5.0, 6.0],
                [7.0, 8.0, 9.0],
            ]
        ]
    ]
)

outputs[layer.get_output(0).name] = layer.get_output(0).shape

expected[layer.get_output(0).name] = inputs[in1.name]

Identity with a Different Precision

in1 = network.add_input("input1", dtype=trt.float32, shape=(1, 1, 3, 3))
layer = network.add_identity(in1)
layer.set_output_type(0, dtype=trt.int32)
layer2 = network.add_identity(layer.get_output(0))
network.mark_output(layer2.get_output(0))

inputs[in1.name] = np.array(
    [
        [
            [
                [1.1, 2.4, 3.7],
                [4.2, 5.5, 6.8],
                [7.3, 8.6, 9.9],
            ]
        ]
    ]
)

outputs[layer2.get_output(0).name] = layer2.get_output(0).shape

expected[layer2.get_output(0).name] = np.array(
    [
        [
            [
                [1.0, 2.0, 3.0],
                [4.0, 5.0, 6.0],
                [7.0, 8.0, 9.0],
            ]
        ]
    ]
)

C++ API¶

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

Python API¶

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