Dl4j-fit(DataSetIterator iterator)源码阅读（七）损失函数得分计算

最新推荐文章于 2021-06-17 23:27:36 发布

寒沧

最新推荐文章于 2021-06-17 23:27:36 发布

阅读量674

点赞数

分类专栏： deeplearning4j DeepLearning4j

本文链接：https://blog.csdn.net/u011669700/article/details/78749397

版权

本文深入探讨了DL4J库中MultiLayerNetwork的computeGradientAndScore()方法，重点讲解了损失函数得分计算过程，包括L1和L2正则化的详细步骤。首先，计算网络的L1，通过遍历每层并应用权重与偏置的1范式。接着，计算L2，采用类似方法但考虑2范式的特性。最后，综合损失函数和正则化项得出最终得分。

摘要由CSDN通过智能技术生成

在反向传播计算完梯度和误差之后，返回到MultiLayerNetwork.computeGradientAndScore()方法中继续计算输出函数的偏差

MultiLayerNetwork.computeGradientAndScore()

@Override
public void computeGradientAndScore() {
    //Calculate activations (which are stored in each layer, and used in backprop)
    if (layerWiseConfigurations.getBackpropType() == BackpropType.TruncatedBPTT) {
        List<INDArray> activations = rnnActivateUsingStoredState(getInput(), true, true);
        if (trainingListeners.size() > 0) {
            for (TrainingListener tl : trainingListeners) {
                tl.onForwardPass(this, activations);
            }
        }
        truncatedBPTTGradient();
    } else {
        //First: do a feed-forward through the network
        //Note that we don't actually need to do the full forward pass through the output layer right now; but we do
        // need the input to the output layer to be set (such that backprop can be done)
        List<INDArray> activations = feedForwardToLayer(layers.length - 2, true);
        if (trainingListeners.size() > 0) {
            //TODO: We possibly do want output layer activations in some cases here...
            for (TrainingListener tl : trainingListeners) {
                tl.onForwardPass(this, activations);
            }
        }
        INDArray actSecondLastLayer = activations.get(activations.size() - 1);
        if (layerWiseConfigurations.getInputPreProcess(layers.length - 1) != null)
            actSecondLastLayer = layerWiseConfigurations.ge