Some fixes to momentum

Joseph Redmon

2014-12-08 a99050f0c8cb0315fa31e3d1fa3e38594fe5e40a

 src/connected_layer.c

@@ -24,19 +24,17 @@
    layer->delta = calloc(batch*outputs, sizeof(float*));

    layer->weight_updates = calloc(inputs*outputs, sizeof(float));
    //layer->weight_adapt = calloc(inputs*outputs, sizeof(float));
    layer->weights = calloc(inputs*outputs, sizeof(float));
    float scale = 1./inputs;
    scale = .01;
    for(i = 0; i < inputs*outputs; ++i)
        layer->weights[i] = scale*2*(rand_uniform()-.5);
    for(i = 0; i < inputs*outputs; ++i){
        layer->weights[i] = scale*rand_normal();
    }

    layer->bias_updates = calloc(outputs, sizeof(float));
    //layer->bias_adapt = calloc(outputs, sizeof(float));
    layer->biases = calloc(outputs, sizeof(float));
    for(i = 0; i < outputs; ++i){
        //layer->biases[i] = rand_normal()*scale + scale;
        layer->biases[i] = 1;
        layer->biases[i] = .01;
    }

    #ifdef GPU
@@ -59,7 +57,7 @@
    axpy_cpu(layer.outputs, layer.learning_rate, layer.bias_updates, 1, layer.biases, 1);
    scal_cpu(layer.outputs, layer.momentum, layer.bias_updates, 1);

    scal_cpu(layer.inputs*layer.outputs, 1.-layer.learning_rate*layer.decay, layer.weights, 1);
    axpy_cpu(layer.inputs*layer.outputs, -layer.decay, layer.weights, 1, layer.weight_updates, 1);
    axpy_cpu(layer.inputs*layer.outputs, layer.learning_rate, layer.weight_updates, 1, layer.weights, 1);
    scal_cpu(layer.inputs*layer.outputs, layer.momentum, layer.weight_updates, 1);
}
@@ -129,7 +127,7 @@
    axpy_ongpu(layer.outputs, layer.learning_rate, layer.bias_updates_cl, 1, layer.biases_cl, 1);
    scal_ongpu(layer.outputs, layer.momentum, layer.bias_updates_cl, 1);

    scal_ongpu(layer.inputs*layer.outputs, 1.-layer.learning_rate*layer.decay, layer.weights_cl, 1);
    axpy_ongpu(layer.inputs*layer.outputs, -layer.decay, layer.weights_cl, 1, layer.weight_updates_cl, 1);
    axpy_ongpu(layer.inputs*layer.outputs, layer.learning_rate, layer.weight_updates_cl, 1, layer.weights_cl, 1);
    scal_ongpu(layer.inputs*layer.outputs, layer.momentum, layer.weight_updates_cl, 1);
    pull_connected_layer(layer);