如何在Caffe中配置每一个层的结构.docxVIP

/danieljianfeng/article/details何在Caffe中配置每一个层的结构1. Vision Layers1.1 卷积层(Convolution)类型：CONVOLUTION例子layers { name: conv1 type: CONVOLUTION bottom: data top: conv1 blobs_lr: 1 # learning rate multiplier for the filters blobs_lr: 2 # learning rate multiplier for the biases weight_decay: 1 # weight decay multiplier for the filters weight_decay: 0 # weight decay multiplier for the biases convolution_param {num_output: 96 # learn 96 filterskernel_size: 11 # each filter is 11x11stride: 4 # step 4 pixels between each filter applicationweight_filler {type: gaussian # initialize the filters from a Gaussianstd: 0.01 # distribution with stdev 0.01 (default mean: 0)}bias_filler {type: constant # initialize the biases to zero (0)value: 0} }}blobs_lr:?学习率调整的参数，在上面的例子中,设置权重学习率和运行中求解器给出的学习率一样(blobs_lr: 1)，偏置学习率为权重的两倍(blobs_lr: 2)。?weight_decay：?卷积层的重要参数必须参数：num_output (c_o)：过滤器的个数kernel_size (or kernel_h and kernel_w)：过滤器的大小?可选参数：weight_filler [default type: constant value: 0]：参数的初始化方法bias_filler：偏置的初始化方法bias_term [default true]：指定是否开启偏置项pad (or pad_h and pad_w) [default 0]：指定在输入的每一边加上多少个像素stride (or stride_h and stride_w) [default 1]：指定过滤器的步长group (g) [default 1]:?If g 1, we restrict the connectivity of each filter to a subset of the input. Specifically, the input and output channels are separated into g groups, and the ith output group channels will be only connected to the ith input group channels.?通过卷积后的大小变化：输入：n * c_i * h_i * w_i输出：n * c_o * h_o * w_o，其中h_o = (h_i + 2 * pad_h - kernel_h) / stride_h + 1，w_o= (w_i + 2 * pad_w - kernel_w) / stride_w + 1。1.2 池化层（Pooling）类型：POOLING例子layers { name: pool1 type: POOLING bottom: conv1 top: pool1 pooling_param {pool: MAXkernel_size: 3 # pool over a 3x3 regionstride: 2 # step two pixels (in the bottom blob) between pooling regions }}池化层的重要参数必需参数：kernel_size (or kernel_h and kernel_w)：过滤器的大小?可选参数：pool [default MAX]：pooling的方法，目前有MAX, AVE, 和STOCHASTIC三种方法pad