Method has_opt_impl

src/cpu/operators/CpuGemmConv2d.cpp:653–695

}

Status CpuGemmConv2d::has_opt_impl(arm_compute::WeightFormat &expected_weight_format,
                                   const ITensorInfo         *src,
                                   const ITensorInfo         *weights,
                                   const ITensorInfo         *biases,
                                   const ITensorInfo         *dst,
                                   const PadStrideInfo       &conv_info,
                                   const WeightsInfo         &weights_info,
                                   const Size2D              &dilation,
                                   const ActivationLayerInfo &act_info,
                                   const bool                 enable_fast_math)
{
    const DataLayout   data_layout   = src->data_layout();
    const int          idx_width     = get_data_layout_dimension_index(data_layout, DataLayoutDimension::WIDTH);
    const int          idx_height    = get_data_layout_dimension_index(data_layout, DataLayoutDimension::HEIGHT);
    const unsigned int kernel_width  = weights->dimension(idx_width);
    const unsigned int kernel_height = weights->dimension(idx_height);
    unsigned int       conv_w        = 0;
    unsigned int       conv_h        = 0;
    std::tie(conv_w, conv_h) = scaled_dimensions(src->dimension(idx_width), src->dimension(idx_height), kernel_width,
                                                 kernel_height, conv_info, dilation);

    const CpuGemmConv2d::SkipInfo skip_info =
        CpuGemmConv2d::skip_im_col_info(src, weights, conv_info, dilation, act_info);

    const bool         skip_im2col   = skip_info.skip_im2col;
    const bool         skip_col2im   = skip_info.skip_col2im;
    const unsigned int gemm_3d_depth = skip_col2im ? conv_h : 0;
    const bool         fixed_format  = weights_info.weight_format() != arm_compute::WeightFormat::UNSPECIFIED;

    /** @section note_CpuGemmConv2d_weight_use_in_has_opt_impl Which weights tensor should we use for has_opt_impl
     *
     *  For the pretranspose_B flag, this shares a similar problem and thus the same decision as that of
     *  @ref note_CpuGemmConv2d_weight_use_in_configure
     *
     *  But for the weights, we shall always use the original instead of reshaped weights here
     */
    const GEMMInfo gemm_info = GEMMInfo(false, false, true /* Reshape weights only for the first run */, gemm_3d_depth,
                                        skip_im2col /* Reinterpret the input as 3D if im2col is skipped */, false,
                                        GEMMLowpOutputStageInfo(), false, enable_fast_math, false, act_info,
                                        fixed_format, weights_info.weight_format(), true /* pretranspose_B */);

    return CpuGemm::has_opt_impl(expected_weight_format, src, weights, biases, dst, gemm_info);
}

Status CpuGemmConv2d::validate(const ITensorInfo         *src,
                               const ITensorInfo         *weights,