caffe源码阅读5-各种layer概述

工厂模式：一个工厂可以生产N种产品，那么就需要N种磨具。

因为从来没有玩过设计模式，而layer是采用工厂模式的，就临时看了一下，大概可以用上面的那一句话来描述吧。

基本可以说caffe中的所有层都是继承了layer类的，那么在caffe中，一共有哪些层呢？可以在caffe.proto中看到：

enum LayerType {
// "NONE" layer type is 0th enum element so that we don't cause confusion
// by defaulting to an existent LayerType (instead, should usually error if
// the type is unspecified).
NONE = 0;
ABSVAL = 35;
ACCURACY = 1;
ARGMAX = 30;
BNLL = 2;
CONCAT = 3;
CONTRASTIVE_LOSS = 37;
CONVOLUTION = 4;
DATA = 5;
DROPOUT = 6;
DUMMY_DATA = 32;
EUCLIDEAN_LOSS = 7;
ELTWISE = 25;
FLATTEN = 8;
HDF5_DATA = 9;
HDF5_OUTPUT = 10;
HINGE_LOSS = 28;
IM2COL = 11;
IMAGE_DATA = 12;
INFOGAIN_LOSS = 13;
INNER_PRODUCT = 14;
LRN = 15;
MEMORY_DATA = 29;
MULTINOMIAL_LOGISTIC_LOSS = 16;
MVN = 34;
POOLING = 17;
POWER = 26;
RELU = 18;
SIGMOID = 19;
SIGMOID_CROSS_ENTROPY_LOSS = 27;
SILENCE = 36;
SOFTMAX = 20;
SOFTMAX_LOSS = 21;
SPLIT = 22;
SLICE = 33;
TANH = 23;
WINDOW_DATA = 24;
THRESHOLD = 31;
}

哇，吓我一跳！这么多！！
一个个的来分析，这么多种层，都分别在什么地方呢？包括：

vision_layers.hpp：ConvolutionLayer类，CuDNNConvolutionLayer类，Im2colLayer类，LRNLayer类，PoolingLayer类，CuDNNPoolingLayer类；

neuron_layers.hpp：NeuronLayer类，AbsValLayer类，BNLLLayer类，DropoutLayer类，PowerLayer类，ReLULayer类，CuDNNReLULayer类，SigmoidLayer类，CuDNNSigmoidLayer类，TanHLayer类，CuDNNTanHLayer类，ThresholdLayer类；

common_layers.hpp：ArgMaxLayer类，ConcatLayer类，EltwiseLayer类，FlattenLayer类，InnerProductLayer类，MVNLayer类，SilenceLayer类，SoftmaxLayer类，CuDNNSoftmaxLayer类，SplitLayer类，SliceLayer类

data_layers.hpp：BaseDataLayer类，BasePrefetchingDataLayer类，DataLayer类，DummyDataLayer类，HDF5DataLayer类，HDF5OutputLayer类，ImageDataLayer类，MemoryDataLayer类，WindowDataLayer类，

loss_layers.hpp：AccuracyLayer类，LossLayer类，ContrastiveLossLayer类，EuclideanLossLayer类，HingeLossLayer类，InfogainLossLayer类，MultinomialLogisticLossLayer类，SigmoidCrossEntropyLossLayer类，SoftmaxWithLossLayer类。

虽然这里有这么多种层，其实我们可能只关心其中的某一些而已。另外还看到，其实只有少部分的层使用GPU，也就是带有CuDNN的那些层。