pt/vmz/models/utils.py [92:156]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
class Conv3DDepthwise(nn.Conv3d):
    def __init__(self, in_planes, out_planes, midplanes=None, stride=1, padding=1):

        assert in_planes == out_planes
        super(Conv3DDepthwise, self).__init__(
            in_channels=in_planes,
            out_channels=out_planes,
            kernel_size=(3, 3, 3),
            stride=stride,
            padding=padding,
            groups=in_planes,
            bias=False,
        )

    @staticmethod
    def get_downsample_stride(stride):
        return (stride, stride, stride)


class IPConv3DDepthwise(nn.Sequential):
    def __init__(self, in_planes, out_planes, midplanes, stride=1, padding=1):

        assert in_planes == out_planes
        super(IPConv3DDepthwise, self).__init__(
            nn.Conv3d(in_planes, out_planes, kernel_size=1, bias=False),
            nn.BatchNorm3d(out_planes),
            # nn.ReLU(inplace=True),
            Conv3DDepthwise(out_planes, out_planes, None, stride),
        )

    @staticmethod
    def get_downsample_stride(stride):
        return (stride, stride, stride)


class Conv2Plus1D(nn.Sequential):
    def __init__(self, in_planes, out_planes, midplanes, stride=1, padding=1):

        midplanes = (in_planes * out_planes * 3 * 3 * 3) // (
            in_planes * 3 * 3 + 3 * out_planes
        )
        super(Conv2Plus1D, self).__init__(
            nn.Conv3d(
                in_planes,
                midplanes,
                kernel_size=(1, 3, 3),
                stride=(1, stride, stride),
                padding=(0, padding, padding),
                bias=False,
            ),
            nn.BatchNorm3d(midplanes),
            nn.ReLU(inplace=True),
            nn.Conv3d(
                midplanes,
                out_planes,
                kernel_size=(3, 1, 1),
                stride=(stride, 1, 1),
                padding=(padding, 0, 0),
                bias=False,
            ),
        )

    @staticmethod
    def get_downsample_stride(stride):
        return (stride, stride, stride)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



utilities/model_conversion/conversion_models.py [32:96]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
class Conv3DDepthwise(nn.Conv3d):
    def __init__(self, in_planes, out_planes, midplanes=None, stride=1, padding=1):

        assert in_planes == out_planes
        super(Conv3DDepthwise, self).__init__(
            in_channels=in_planes,
            out_channels=out_planes,
            kernel_size=(3, 3, 3),
            stride=stride,
            padding=padding,
            groups=in_planes,
            bias=False,
        )

    @staticmethod
    def get_downsample_stride(stride):
        return (stride, stride, stride)


class IPConv3DDepthwise(nn.Sequential):
    def __init__(self, in_planes, out_planes, midplanes, stride=1, padding=1):

        assert in_planes == out_planes
        super(IPConv3DDepthwise, self).__init__(
            nn.Conv3d(in_planes, out_planes, kernel_size=1, bias=False),
            nn.BatchNorm3d(out_planes),
            # nn.ReLU(inplace=True),
            Conv3DDepthwise(out_planes, out_planes, None, stride),
        )

    @staticmethod
    def get_downsample_stride(stride):
        return (stride, stride, stride)


class Conv2Plus1D(nn.Sequential):
    def __init__(self, in_planes, out_planes, midplanes, stride=1, padding=1):

        midplanes = (in_planes * out_planes * 3 * 3 * 3) // (
            in_planes * 3 * 3 + 3 * out_planes
        )
        super(Conv2Plus1D, self).__init__(
            nn.Conv3d(
                in_planes,
                midplanes,
                kernel_size=(1, 3, 3),
                stride=(1, stride, stride),
                padding=(0, padding, padding),
                bias=False,
            ),
            nn.BatchNorm3d(midplanes),
            nn.ReLU(inplace=True),
            nn.Conv3d(
                midplanes,
                out_planes,
                kernel_size=(3, 1, 1),
                stride=(stride, 1, 1),
                padding=(padding, 0, 0),
                bias=False,
            ),
        )

    @staticmethod
    def get_downsample_stride(stride):
        return (stride, stride, stride)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -