Python _C.deform_conv_forward方法代碼示例

本文整理匯總了Python中maskrcnn_benchmark._C.deform_conv_forward方法的典型用法代碼示例。如果您正苦於以下問題：Python _C.deform_conv_forward方法的具體用法？Python _C.deform_conv_forward怎麽用？Python _C.deform_conv_forward使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類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個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。

示例1: forward

# 需要導入模塊: from maskrcnn_benchmark import _C [as 別名]
# 或者: from maskrcnn_benchmark._C import deform_conv_forward [as 別名]
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

開發者ID:simaiden，項目名稱:Clothing-Detection，代碼行數:59，代碼來源:deform_conv_func.py

示例2: forward

# 需要導入模塊: from maskrcnn_benchmark import _C [as 別名]
# 或者: from maskrcnn_benchmark._C import deform_conv_forward [as 別名]
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

開發者ID:HuangQinJian，項目名稱:DF-Traffic-Sign-Identification，代碼行數:59，代碼來源:deform_conv_func.py

注：本文中的maskrcnn_benchmark._C.deform_conv_forward方法示例由純淨天空整理自Github/MSDocs等開源代碼及文檔管理平台，相關代碼片段篩選自各路編程大神貢獻的開源項目，源碼版權歸原作者所有，傳播和使用請參考對應項目的License；未經允許，請勿轉載。