当前位置: 首页>>代码示例>>Python>>正文


Python utils._ntuple方法代码示例

本文整理汇总了Python中torch.nn.modules.utils._ntuple方法的典型用法代码示例。如果您正苦于以下问题:Python utils._ntuple方法的具体用法?Python utils._ntuple怎么用?Python utils._ntuple使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在torch.nn.modules.utils的用法示例。


在下文中一共展示了utils._ntuple方法的5个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。

示例1: interpolate

# 需要导入模块: from torch.nn.modules import utils [as 别名]
# 或者: from torch.nn.modules.utils import _ntuple [as 别名]
def interpolate(
    input, size=None, scale_factor=None, mode="nearest", align_corners=None
):
    if input.numel() > 0:
        return torch.nn.functional.interpolate(
            input, size, scale_factor, mode, align_corners
        )

    def _check_size_scale_factor(dim):
        if size is None and scale_factor is None:
            raise ValueError("either size or scale_factor should be defined")
        if size is not None and scale_factor is not None:
            raise ValueError("only one of size or scale_factor should be defined")
        if (
            scale_factor is not None
            and isinstance(scale_factor, tuple)
            and len(scale_factor) != dim
        ):
            raise ValueError(
                "scale_factor shape must match input shape. "
                "Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
            )

    def _output_size(dim):
        _check_size_scale_factor(dim)
        if size is not None:
            return size
        scale_factors = _ntuple(dim)(scale_factor)
        # math.floor might return float in py2.7
        return [
            int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)
        ]

    output_shape = tuple(_output_size(2))
    output_shape = input.shape[:-2] + output_shape
    return _NewEmptyTensorOp.apply(input, output_shape) 
开发者ID:Res2Net,项目名称:Res2Net-maskrcnn,代码行数:38,代码来源:misc.py

示例2: interpolate

# 需要导入模块: from torch.nn.modules import utils [as 别名]
# 或者: from torch.nn.modules.utils import _ntuple [as 别名]
def interpolate(x, size=None, scale_factor=None, mode="nearest", align_corners=None):
    if x.numel() > 0:
        return torch.nn.functional.interpolate(
            x, size, scale_factor, mode, align_corners
        )

    def _check_size_scale_factor(dim):
        if size is None and scale_factor is None:
            raise ValueError("either size or scale_factor should be defined")
        if size is not None and scale_factor is not None:
            raise ValueError("only one of size or scale_factor should be defined")
        if (
            scale_factor is not None
            and isinstance(scale_factor, tuple)
            and len(scale_factor) != dim
        ):
            raise ValueError(
                "scale_factor shape must match input shape. "
                "Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
            )

    def _output_size(dim):
        _check_size_scale_factor(dim)
        if size is not None:
            return size
        scale_factors = _ntuple(dim)(scale_factor)
        # math.floor might return float in py2.7
        return [
            int(math.floor(x.size(i + 2) * scale_factors[i])) for i in range(dim)
        ]

    output_shape = tuple(_output_size(2))
    output_shape = x.shape[:-2] + output_shape
    return _NewEmptyTensorOp.apply(x, output_shape) 
开发者ID:soeaver,项目名称:Parsing-R-CNN,代码行数:36,代码来源:misc.py

示例3: interpolate

# 需要导入模块: from torch.nn.modules import utils [as 别名]
# 或者: from torch.nn.modules.utils import _ntuple [as 别名]
def interpolate(input, size=None, scale_factor=None, mode='nearest', align_corners=None):
    if input.numel() > 0:
        return torch.nn.functional.interpolate(input, size, scale_factor, mode, align_corners)

    from torch.nn.modules.utils import _ntuple
    import math

    def _check_size_scale_factor(dim):
        if size is None and scale_factor is None:
            raise ValueError('either size or scale_factor should be defined')
        if size is not None and scale_factor is not None:
            raise ValueError('only one of size or scale_factor should be defined')
        if scale_factor is not None and isinstance(scale_factor, tuple)\
                and len(scale_factor) != dim:
            raise ValueError('scale_factor shape must match input shape. '
                             'Input is {}D, scale_factor size is {}'.format(dim, len(scale_factor)))

    def _output_size(dim):
        _check_size_scale_factor(dim)
        if size is not None:
            return size
        scale_factors = _ntuple(dim)(scale_factor)
        # math.floor might return float in py2.7
        return [int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)]

    output_shape = tuple(_output_size(2))
    output_shape = input.shape[:-2] + output_shape
    return _NewEmptyTensorOp.apply(input, output_shape) 
开发者ID:mlperf,项目名称:training_results_v0.5,代码行数:30,代码来源:utils.py

示例4: interpolate

# 需要导入模块: from torch.nn.modules import utils [as 别名]
# 或者: from torch.nn.modules.utils import _ntuple [as 别名]
def interpolate(input, size=None, scale_factor=None, mode="nearest", align_corners=None):
    """
    A wrapper around :func:`torch.nn.functional.interpolate` to support zero-size tensor.
    """
    if TORCH_VERSION > (1, 4) or input.numel() > 0:
        return torch.nn.functional.interpolate(
            input, size, scale_factor, mode, align_corners=align_corners
        )

    def _check_size_scale_factor(dim):
        if size is None and scale_factor is None:
            raise ValueError("either size or scale_factor should be defined")
        if size is not None and scale_factor is not None:
            raise ValueError("only one of size or scale_factor should be defined")
        if (
            scale_factor is not None
            and isinstance(scale_factor, tuple)
            and len(scale_factor) != dim
        ):
            raise ValueError(
                "scale_factor shape must match input shape. "
                "Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
            )

    def _output_size(dim):
        _check_size_scale_factor(dim)
        if size is not None:
            return size
        scale_factors = _ntuple(dim)(scale_factor)
        # math.floor might return float in py2.7
        return [int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)]

    output_shape = tuple(_output_size(2))
    output_shape = input.shape[:-2] + output_shape
    return _NewEmptyTensorOp.apply(input, output_shape) 
开发者ID:facebookresearch,项目名称:detectron2,代码行数:37,代码来源:wrappers.py

示例5: interpolate

# 需要导入模块: from torch.nn.modules import utils [as 别名]
# 或者: from torch.nn.modules.utils import _ntuple [as 别名]
def interpolate(input, size=None, scale_factor=None, mode="nearest", align_corners=None):
    """
    A wrapper around :func:`torch.nn.functional.interpolate` to support zero-size tensor.
    """
    if input.numel() > 0:
        return torch.nn.functional.interpolate(
            input, size, scale_factor, mode, align_corners=align_corners
        )

    def _check_size_scale_factor(dim):
        if size is None and scale_factor is None:
            raise ValueError("either size or scale_factor should be defined")
        if size is not None and scale_factor is not None:
            raise ValueError("only one of size or scale_factor should be defined")
        if (
            scale_factor is not None
            and isinstance(scale_factor, tuple)
            and len(scale_factor) != dim
        ):
            raise ValueError(
                "scale_factor shape must match input shape. "
                "Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
            )

    def _output_size(dim):
        _check_size_scale_factor(dim)
        if size is not None:
            return size
        scale_factors = _ntuple(dim)(scale_factor)
        # math.floor might return float in py2.7
        return [int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)]

    output_shape = tuple(_output_size(2))
    output_shape = input.shape[:-2] + output_shape
    return _NewEmptyTensorOp.apply(input, output_shape) 
开发者ID:conansherry,项目名称:detectron2,代码行数:37,代码来源:wrappers.py


注:本文中的torch.nn.modules.utils._ntuple方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。