Alexnet.cnna

architecture Alexnet(img_height=224, img_width=224, img_channels=3, classes=10){
    def input Z(0:255)^{img_channels, img_height, img_width} data
    def output Q(0:1)^{classes} predictions


    unroll<t=5> beamSearchStart (width=5, max_length=50){
        FullyConnected(units=4096) ->
        Relu() ->
        Dropout()
    }



    def split1(i){
        [i] ->
        Convolution(kernel=(5,5), channels=128) ->
        Lrn(nsize=5, alpha=0.0001, beta=0.75) ->
        Pooling(pool_type="max", kernel=(3,3), stride=(2,2), padding="no_loss") ->
        Relu()
    }
    def split2(i){
        [i] ->
        Convolution(kernel=(3,3), channels=192) ->
        Relu() ->
        Convolution(kernel=(3,3), channels=128) ->
        Pooling(pool_type="max", kernel=(3,3), stride=(2,2), padding="no_loss") ->
        Relu()
    }
    def fc(){
        FullyConnected(units=4096) ->
        Relu() ->
        Dropout()
    }




    data ->
    Convolution(kernel=(11,11), channels=96, stride=(4,4), padding="no_loss") ->
    Lrn(nsize=5, alpha=0.0001, beta=0.75) ->
    Pooling(pool_type="max", kernel=(3,3), stride=(2,2), padding="no_loss") ->
    unroll<t> BeamSearchStart (width=5, max_length=50){
        FullyConnected(units=4096) ->
        Relu() ->
        Dropout()
    } ->
    Relu() ->
    Split(n=2) ->
    split1(i=[0|1]) ->
    Concatenate() ->
    Convolution(kernel=(3,3), channels=384) ->
    Relu() ->
    Split(n=2) ->
    split2(i=[0|1]) ->
    Concatenate() ->
    FullyConnected(units=10) ->
    Softmax() ->
    predictions;
}