当前位置: 首页>>代码示例>>Python>>正文


Python _C.deform_conv_forward方法代码示例

本文整理汇总了Python中maskrcnn_benchmark._C.deform_conv_forward方法的典型用法代码示例。如果您正苦于以下问题:Python _C.deform_conv_forward方法的具体用法?Python _C.deform_conv_forward怎么用?Python _C.deform_conv_forward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maskrcnn_benchmark._C的用法示例。


在下文中一共展示了_C.deform_conv_forward方法的2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: forward

# 需要导入模块: from maskrcnn_benchmark import _C [as 别名]
# 或者: from maskrcnn_benchmark._C import deform_conv_forward [as 别名]
def forward(
        ctx,
        input,
        offset,
        weight,
        stride=1,
        padding=0,
        dilation=1,
        groups=1,
        deformable_groups=1,
        im2col_step=64
    ):
        if input is not None and input.dim() != 4:
            raise ValueError(
                "Expected 4D tensor as input, got {}D tensor instead.".format(
                    input.dim()))
        ctx.stride = _pair(stride)
        ctx.padding = _pair(padding)
        ctx.dilation = _pair(dilation)
        ctx.groups = groups
        ctx.deformable_groups = deformable_groups
        ctx.im2col_step = im2col_step

        ctx.save_for_backward(input, offset, weight)

        output = input.new_empty(
            DeformConvFunction._output_size(input, weight, ctx.padding,
                                            ctx.dilation, ctx.stride))

        ctx.bufs_ = [input.new_empty(0), input.new_empty(0)]  # columns, ones

        if not input.is_cuda:
            raise NotImplementedError
        else:
            cur_im2col_step = min(ctx.im2col_step, input.shape[0])
            assert (input.shape[0] %
                    cur_im2col_step) == 0, 'im2col step must divide batchsize'
            _C.deform_conv_forward(
                input,
                weight,
                offset,
                output,
                ctx.bufs_[0],
                ctx.bufs_[1],
                weight.size(3),
                weight.size(2),
                ctx.stride[1],
                ctx.stride[0],
                ctx.padding[1],
                ctx.padding[0],
                ctx.dilation[1],
                ctx.dilation[0],
                ctx.groups,
                ctx.deformable_groups,
                cur_im2col_step
            )
        return output 
开发者ID:simaiden,项目名称:Clothing-Detection,代码行数:59,代码来源:deform_conv_func.py

示例2: forward

# 需要导入模块: from maskrcnn_benchmark import _C [as 别名]
# 或者: from maskrcnn_benchmark._C import deform_conv_forward [as 别名]
def forward(
        ctx, 
        input, 
        offset, 
        weight,
        stride=1, 
        padding=0, 
        dilation=1, 
        groups=1, 
        deformable_groups=1, 
        im2col_step=64
    ):
        if input is not None and input.dim() != 4:
            raise ValueError(
                "Expected 4D tensor as input, got {}D tensor instead.".format(
                    input.dim()))
        ctx.stride = _pair(stride)
        ctx.padding = _pair(padding)
        ctx.dilation = _pair(dilation)
        ctx.groups = groups
        ctx.deformable_groups = deformable_groups
        ctx.im2col_step = im2col_step

        ctx.save_for_backward(input, offset, weight)

        output = input.new_empty(
            DeformConvFunction._output_size(input, weight, ctx.padding,
                                            ctx.dilation, ctx.stride))

        ctx.bufs_ = [input.new_empty(0), input.new_empty(0)]  # columns, ones

        if not input.is_cuda:
            raise NotImplementedError
        else:
            cur_im2col_step = min(ctx.im2col_step, input.shape[0])
            assert (input.shape[0] %
                    cur_im2col_step) == 0, 'im2col step must divide batchsize'
            _C.deform_conv_forward(
                input, 
                weight, 
                offset, 
                output, 
                ctx.bufs_[0], 
                ctx.bufs_[1],
                weight.size(3), 
                weight.size(2), 
                ctx.stride[1], 
                ctx.stride[0],
                ctx.padding[1], 
                ctx.padding[0], 
                ctx.dilation[1],
                ctx.dilation[0], 
                ctx.groups, 
                ctx.deformable_groups,
                cur_im2col_step
            )
        return output 
开发者ID:HuangQinJian,项目名称:DF-Traffic-Sign-Identification,代码行数:59,代码来源:deform_conv_func.py


注:本文中的maskrcnn_benchmark._C.deform_conv_forward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。