Question

以下是神经网络前向传播的代码。我想加快速度。至于循环需要时间，任何身体都可以帮助纠正代码加速它，就像matlab说矢量化等。在这段代码中，我每次从大小为19x19的输入获取4x4的接收场，而不是将每个像素乘以4x4的权重（net.w {layer_no}（u，v），大小为19x19）。你也可以说它是两者的点积。我没有直接做两个小矩阵的点积，因为有一个边界检查。它最终在输出中提供了6x6输出。我不是一个经验丰富的编码员，所以我尽我所能。任何人都可以指导我如何加快速度，因为与Opencv相比需要很多时间。会感恩的。此致

    receptiveSize = 4;
    overlap= 1;
    inhibatory = 0;
    gap = receptiveSize-overlap;

    UpperLayerSize = size(net.b{layer_no}); % 6x6
    Curr_layerSize = size(net.w{layer_no}); % 19x19

    for u=1:UpperLayerSize(1)-1
        for v=1:UpperLayerSize(2)-1

            summed_value=0;
            min_u = (u - 1) * gap + 1;
            max_u = (u - 1) * gap + receptiveSize;
            min_v = (v - 1) * gap + 1;
            max_v = (v - 1) * gap + receptiveSize;
            for i = min_u : max_u
                for j = min_v : max_v
                    if(i>Curr_layerSize(1) || j>Curr_layerSize(2))
                        continue;
                    end
                    if(i<1 || j<1)
                        continue;
                    end
                    summed_value = summed_value + input{layer_no}.images(i,j,sample_ind) * net.w{layer_no}(i,j);
                 end
            end
            summed_value = summed_value + net.b{layer_no}(u,v);
            input{layer_no+1}.images(u,v,sample_ind) = summed_value;
        end
    end
    temp = activate_Mat(input{layer_no+1}.images(:,:,sample_ind),net.AF{layer_no});
    output{layer_no}.images(:,:,sample_ind) = temp(:,:);

Answer 1

如何将内部循环（循环遍历i并循环遍历j）更改为：

ii = max( 1, min_u ) : min( max_u, Curr_layerSize(1) );
jj = max( 1, min_v ) : min( max_v, Curr_layerSize(2) );
input{layer_no+1}.images(u,v,sample_ind) = ...
    reshape( input{layer_no}.images(ii,jj,sample_ind), 1, [] ) * ...
    reshape( net.w{layer_no}(ii,jj), [], 1 ) + ...
    net.b{layer_no}(u,v); %// should this term be added rather than multiplied?

如何在matlab中加速代码？

1 个答案: