Slice mode attribute is not exposed to Python.

[jxchenus]

Description

slice has 4 attributes, but the add_slice function only takes the first 3, leaving out mode. If the 4th input fill_value is specified, the following error is thrown:

[sliceLayer.cpp::validate::190] Error Code 2: Internal Error (Assertion params.mode == SampleMode::kFILL || inputForms.size() <= 4 failed. Fill input should only be provided when SampleMode is kFILL)

Environment

AWS p3.3xlarge

TensorRT Version: 10.0.1

NVIDIA GPU: Tesla V100-SXM2-16GB

NVIDIA Driver Version: 535.161.07

CUDA Version: 12.2

CUDNN Version:

Operating System:

Python Version (if applicable): Python 3.10.12

Tensorflow Version (if applicable):

PyTorch Version (if applicable):

Baremetal or Container (if so, version):

Relevant Files

Model link:

Steps To Reproduce

Commands or scripts:

...
ndim = input.rank()
layer = default_trtnet().add_slice(
input.trt_tensor,
start=[0 for _ in range(ndim)],
shape=[1 for _ in range(ndim)], # unused dummy value
stride=[1 for _ in range(ndim)] # unused dummy value
)

# The stride is either:
#   0 for dimensions of size 1 (i.e. shape(input, i) - 1 == 1 - 1 == 0) or,
#   1 for dimensions of size > 1 since minimum(value >= 1, 1) == 1.
stride_tensor = concat(
    [minimum((shape(input, i) - 1), 1) for i in range(ndim)])

layer.set_input(2, expand_shape.trt_tensor)
layer.set_input(3, stride_tensor.trt_tensor)
if fill_value is not None:
    layer.set_input(4, fill_value.trt_tensor)
return _create_tensor(layer.get_output(0), layer)

...

Have you tried the latest release?: no

Can this model run on other frameworks? For example run ONNX model with ONNXRuntime (polygraphy run <model.onnx> --onnxrt):

[lix19937]

For you ref, Slice Fill mode

in1 = network.add_input("input1", dtype=trt.float32, shape=(2, 2))
layer = network.add_slice(in1, start=(0, 0), shape=(3, 3), stride=(1, 1))
fill_constant = network.add_input("fill_constant", dtype=trt.float32, shape=())
layer.mode = trt.SampleMode.FILL  ## !!!   
layer.set_input(4, fill_constant)
network.mark_output(layer.get_output(0))

inputs[in1.name] = np.zeros(shape=(2, 2))
inputs[fill_constant.name] = np.array([1.0])

outputs[layer.get_output(0).name] = layer.get_output(0).shape
expected[layer.get_output(0).name] = np.array([[0, 0, 1], [0, 0, 1], [1, 1, 1]])

[jxchenus]

That worked! Thank you @lix19937 !

When you get a chance, can you take a look at this one too?