Skip to content

ncnn

Classes:

  • NCNN –

    NCNN Vulkan backend.

NCNN dataclass 

NCNN(
    *,
    device_id: int = 0,
    num_streams: int = 1,
    fp16: bool | None = True,
    fp16_blacklist_ops: Collection[str] | None = None,
)

Bases: BackendAutoConvertFloat

NCNN Vulkan backend.

Methods:

  • autoselect –

    Try to select the best backend for the current system.

  • get_args –

    Return backend plugin arguments derived from this configuration.

  • inference –

    Run inference with this backend.

Attributes:

device_id class-attribute instance-attribute 

device_id: int = 0

Vulkan device index used by NCNN.

flexible_output_prop class-attribute 

flexible_output_prop: str = 'MlrtFlexible'

fp16 class-attribute instance-attribute 

fp16: bool | None = True

Enable NCNN FP16 storage/arithmetic where supported.

fp16_blacklist_ops class-attribute instance-attribute 

fp16_blacklist_ops: Collection[str] | None = None

ONNX node or op names to keep in FP32 during FP16 conversion.

num_streams class-attribute instance-attribute 

num_streams: int = 1

Number of parallel NCNN inference streams.

plugin class-attribute instance-attribute 

plugin = core.lazy.ncnn

autoselect staticmethod 

autoselect(device_id: int = 0, **kwargs: Any) -> Backend

Try to select the best backend for the current system.

Parameters:

  • device_id

    (int, default: 0 ) –

    The GPU device id.

  • **kwargs

    (Any, default: {} ) –

    Additional arguments to pass to the backend.

Returns:

  • Backend –

    The selected backend.

Source code in vsscale/mlrt/backend/base.py 
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
@staticmethod
def autoselect(device_id: int = 0, **kwargs: Any) -> Backend:
    """
    Try to select the best backend for the current system.

    Args:
        device_id: The GPU device id.
        **kwargs: Additional arguments to pass to the backend.

    Returns:
        The selected backend.
    """

    gpu = get_gpu(device_id)
    vendor = None if not gpu else str(gpu.vendor).strip()

    match vendor:
        # Windows & Linux
        case "NVIDIA Corporation":
            if hasattr(core, "trt"):
                backend = UserBackend.TRT
            elif hasattr(core, "trt_rtx"):
                backend = UserBackend.TRT_RTX
            elif platform.system().lower() == "windows" and hasattr(core, "ort"):
                backend = UserBackend.ORT_DML
            elif hasattr(core, "ort"):
                backend = UserBackend.ORT_CUDA
            elif hasattr(core, "ncnn"):
                backend = UserBackend.NCNN
            else:
                backend = UserBackend.OV_CPU
        # Windows & Linux
        case "Advanced Micro Devices, Inc.":
            if platform.system().lower() == "windows" and hasattr(core, "ort"):
                backend = UserBackend.ORT_DML
            elif hasattr(core, "migx"):
                backend = UserBackend.MIGX
            elif hasattr(core, "ncnn"):
                backend = UserBackend.NCNN_VK
            else:
                backend = UserBackend.OV_CPU
        # Windows & Linux
        case "Intel(R) Corporation":
            if hasattr(core, "ov"):
                backend = UserBackend.OV_GPU
            elif platform.system().lower() == "windows" and hasattr(core, "ort"):
                backend = UserBackend.ORT_DML
            elif hasattr(core, "ncnn"):
                backend = UserBackend.NCNN_VK
            else:
                backend = UserBackend.OV_CPU
        # macOS ARM64 & x86_64
        case "Apple":
            if hasattr(core, "ncnn"):
                backend = UserBackend.NCNN_VK
            elif hasattr(core, "ort"):
                backend = UserBackend.ORT_COREML
            else:
                backend = UserBackend.OV_CPU
        case _:
            backend = UserBackend.OV_CPU

    del gpu

    if hasattr(backend, "device_id"):
        kwargs["device_id"] = device_id

    return backend(**kwargs)

get_args 

get_args(clips: VideoNode | Sequence[VideoNode]) -> dict[str, Any]

Return backend plugin arguments derived from this configuration.

Source code in vsscale/mlrt/backend/ncnn.py 
28
29
30
31
32
33
def get_args(self, clips: vs.VideoNode | Sequence[vs.VideoNode]) -> dict[str, Any]:
    return super().get_args(clips) | {
        "fp16": self.fp16,
        "device_id": self.device_id,
        "num_streams": self.num_streams,
    }

inference 

inference(
    clips: VideoNode | Sequence[VideoNode],
    network_path: str | PathLike[str],
    /,
    overlap: tuple[int, int],
    tilesize: tuple[int, int],
    *,
    flexible: Literal[False] = ...,
    **kwargs: Any,
) -> VideoNode

inference(
    clips: VideoNode | Sequence[VideoNode],
    network_path: str | PathLike[str],
    /,
    overlap: tuple[int, int],
    tilesize: tuple[int, int],
    *,
    flexible: Literal[True],
    **kwargs: Any,
) -> list[VideoNode]

inference(
    clips: VideoNode | Sequence[VideoNode],
    network_path: str | PathLike[str],
    /,
    overlap: tuple[int, int],
    tilesize: tuple[int, int],
    *,
    flexible: bool = ...,
    **kwargs: Any,
) -> VideoNode | list[VideoNode]

inference(
    clips: VideoNode | Sequence[VideoNode],
    network_path: str | PathLike[str],
    /,
    overlap: tuple[int, int],
    tilesize: tuple[int, int],
    *,
    flexible: bool = False,
    **kwargs: Any,
) -> VideoNode | list[VideoNode]

Run inference with this backend.

Parameters:

  • clips

    (VideoNode | Sequence[VideoNode]) –

    Input clip or clips passed to the backend model.

  • network_path

    (str | PathLike[str]) –

    Path to the model file or backend artifact.

  • overlap

    (tuple[int, int]) –

    Horizontal and vertical tile overlap in pixels.

  • tilesize

    (tuple[int, int]) –

    Horizontal and vertical tile size in pixels.

  • flexible

    (bool, default: False ) –

    Return each flexible output plane as a separate clip.

  • **kwargs

    (Any, default: {} ) –

    Additional backend plugin arguments forwarded unchanged.

Returns:

  • VideoNode | list[VideoNode] –

    A single output clip, or a list of output clips when flexible is enabled.

Source code in vsscale/mlrt/backend/base.py 
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
def inference(
    self,
    clips: vs.VideoNode | Sequence[vs.VideoNode],
    network_path: str | os.PathLike[str],
    /,
    overlap: tuple[int, int],
    tilesize: tuple[int, int],
    *,
    flexible: bool = False,
    **kwargs: Any,
) -> vs.VideoNode | list[vs.VideoNode]:
    """
    Run inference with this backend.

    Args:
        clips: Input clip or clips passed to the backend model.
        network_path: Path to the model file or backend artifact.
        overlap: Horizontal and vertical tile overlap in pixels.
        tilesize: Horizontal and vertical tile size in pixels.
        flexible: Return each flexible output plane as a separate clip.
        **kwargs: Additional backend plugin arguments forwarded unchanged.

    Returns:
        A single output clip, or a list of output clips when `flexible` is enabled.
    """
    UnsupportedSampleTypeError.check(clips, vs.FLOAT, self.__class__)

    args = self.get_args(clips)

    if flexible:
        args = args.copy()
        args["flexible_output_prop"] = self.flexible_output_prop

    logger.info("Calling %s.Model", self.plugin.namespace)
    logger.info("Clips: %r", clips)
    logger.info("Network Path: %s", network_path)
    logger.info("overlap=%s, tilesize=%s, %s", overlap, tilesize, args | kwargs)
    output = self.plugin.Model(clips, network_path, overlap, tilesize, **args | kwargs)

    if flexible:
        clip = output["clip"]
        num_planes = output["num_planes"]

        output = [clip.std.PropToClip(prop=f"{self.flexible_output_prop}{i}") for i in range(num_planes)]

    return output