在caffe中layer分为以下几类:
- Data Layers
- Vision Layers
- Recurrent Layers
- Common Layers
- Normalization Layers
- Activation / Neuron Layers
- Utility Layers
Loss Layers
首先介绍数据层,数据层是每个模型的最底层,是模型的入口,不仅提供数据的输入,也提供数据从Blobs转换成别的格式进行保存输出。通常数据的预处理(如减去均值, 放大缩小, 裁剪和镜像等),也在这一层设置参数实现。数据来源可以来自高效的数据库(如LevelDB和LMDB),也可以直接来自于内存。如果不是很注重效率的话,数据也可来自磁盘的hdf5文件和图片格式文件。所有的数据层的都具有的公用参数:先看示例:
layer {
name: "cifar"
type: "Data"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
mean_file: "examples/cifar10/mean.binaryproto"
}
data_param {
source: "examples/cifar10/cifar10_train_lmdb"
batch_size: 100
backend: LMDB
}
}
下面分别介绍这些参数的含义:
1)name:表示该层的名字,一般选取有意义的名称;
2) type: 表示层类型,如果是Data,表示数据来源于LevelDB或LMDB。根据数据的来源不同,数据层的类型也不同(后面会详细阐述)。通常都是采 用的LevelDB或LMDB数据,因此层类型设置为Data。
3)top或bottom: 每一层用bottom来输入数据,用top来输出数据。如果只有top没有bottom,则此层只有输出,没有输入。反之亦然。如果有多个 top或多个bottom,表示有多个blobs数据的输入和输出。
4)data 与 label: 在数据层中,至少有一个命名为data的top。如果有第二个top,若是分类问题则一般是label。根据任务的不同top的有所不同,例如:siftflow-fcn16s 的datalayer如下:
layer {
name: "data"
type: "Python"
top: "data"
top: "sem"
top: "geo"
python_param {
module: "siftflow_layers"
layer: "SIFTFlowSegDataLayer"
param_str: "{\'siftflow_dir\': \'../data/sift-flow\', \'seed\': 1337, \'split\': \'trainval\'}"
}
}
5)include: 一般训练的时候和测试的时候,模型的层是不一样的。该层(layer)是属于训练阶段的层,还是属于测试阶段的层,需要用include来指定。如果没有include参数,则表示该层既在训练模型中,又在测试模型中
6)Transform_param: 数据的预处理,可以将数据变换到定义的范围内。如设置scale、mirror、crop_size、mean_file等。例如:
transform_param {
scale: 0.00390625
mean_file_size: "examples/cifar10/mean.binaryproto"
# 用一个配置文件来进行均值操作
mirror: 1 # 1表示开启镜像,0表示关闭,也可用ture和false来表示
# 剪裁一个 227*227的图块,在训练阶段随机剪裁,在测试阶段从中间裁剪
crop_size: 227
}
参考caffe.proto 文件,有关transform_param 的code如下:
// Message that stores parameters used to apply transformation
// to the data layer's data
message TransformationParameter {
// For data pre-processing, we can do simple scaling and subtracting the
// data mean, if provided. Note that the mean subtraction is always carried
// out before scaling.
optional float scale = 1 [default = 1];
// Specify if we want to randomly mirror data.
optional bool mirror = 2 [default = false];
// Specify if we would like to randomly crop an image.
optional uint32 crop_size = 3 [default = 0];
// mean_file and mean_value cannot be specified at the same time
optional string mean_file = 4;
// if specified can be repeated once (would subtract it from all the channels)
// or can be repeated the same number of times as channels
// (would subtract them from the corresponding channel)
repeated float mean_value = 5;
// Force the decoded image to have 3 color channels.
optional bool force_color = 6 [default = false];
// Force the decoded image to have 1 color channels.
optional bool force_gray = 7 [default = false];
}
type:参数输入类型很多,所以单独拿出来做解释,下面详细介绍:
1) tpye:Data,这种最常用 ,例如:
layer {
name: "mnist"
type: "Data"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
scale: 0.00390625
}
data_param {
source: "examples/mnist/mnist_train_lmdb"
batch_size: 64
backend: LMDB
}
}
必须设置的参数:
source: 包含数据库的目录名称,如examples/mnist/mnist_train_lmdb
batch_size: 每次处理的数据个数,如64
可选的参数:
rand_skip: 在开始的时候,路过某个数据的输入。通常对异步的SGD很有用。
backend: 选择是采用LevelDB还是LMDB, 默认是LevelDB.
参考源码:
**message DataParameter {
enum DB {
LEVELDB = 0;
LMDB = 1;
}
// Specify the data source.
optional string source = 1;
// Specify the batch size.
optional uint32 batch_size = 4;
// The rand_skip variable is for the data layer to skip a few data points
// to avoid all asynchronous sgd clients to start at the same point. The skip
// point would be set as rand_skip * rand(0,1). Note that rand_skip should not
// be larger than the number of keys in the database.
// DEPRECATED. Each solver accesses a different subset of the database.
optional uint32 rand_skip = 7 [default = 0];
optional DB backend = 8 [default = LEVELDB];
// DEPRECATED. See TransformationParameter. For data pre-processing, we can do
// simple scaling and subtracting the data mean, if provided. Note that the
// mean subtraction is always carried out before scaling.
optional float scale = 2 [default = 1];
optional string mean_file = 3;
// DEPRECATED. See TransformationParameter. Specify if we would like to randomly
// crop an image.
optional uint32 crop_size = 5 [default = 0];
// DEPRECATED. See TransformationParameter. Specify if we want to randomly mirror
// data.
optional bool mirror = 6 [default = false];
// Force the encoded image to have 3 color channels
optional bool force_encoded_color = 9 [default = false];
// Prefetch queue (Increase if data feeding bandwidth varies, within the
// limit of device memory for GPU training)
optional uint32 prefetch = 10 [default = 4];
}**
2)type:memory_data
layer {
top: "data"
top: "label"
name: "memory_data"
type: "MemoryData"
memory_data_param{
batch_size: 2
height: 100
width: 100
channels: 1
}
transform_param {
scale: 0.0078125
mean_file: "mean.proto"
mirror: false
}
}
必须设置的参数: batch_size:每一次处理的数据个数,比如2; channels:通道数; height:高度; width: 宽度;
参考源码:
message MemoryDataParameter {
optional uint32 batch_size = 1;
optional uint32 channels = 2;
optional uint32 height = 3;
optional uint32 width = 4;
}
3) type:HDF5data
layer {
name: "data"
type: "HDF5Data"
top: "data"
top: "label"
hdf5_data_param {
source: "examples/hdf5_classification/data/train.txt"
batch_size: 10
}
}
必须设置的参数:source: 读取的文件名称;batch_size: 每一次处理的数据个数
// Message that stores parameters used by HDF5DataLayer
message HDF5DataParameter {
// Specify the data source.
optional string source = 1;
// Specify the batch size.
optional uint32 batch_size = 2;
// Specify whether to shuffle the data.
// If shuffle == true, the ordering of the HDF5 files is shuffled,
// and the ordering of data within any given HDF5 file is shuffled,
// but data between different files are not interleaved; all of a file's
// data are output (in a random order) before moving onto another file.
optional bool shuffle = 3 [default = false];
}
4) type:ImageData
layer {
name: "data"
type: "ImageData"
top: "data"
top: "label"
transform_param {
mirror: false
crop_size: 227
mean_file: "data/ilsvrc12/imagenet_mean.binaryproto"
}
image_data_param {
source: "examples/_temp/file_list.txt"
batch_size: 50
new_height: 256
new_width: 256
}
}
必须设置的参数:
source: 一个文本文件的名字,每一行给定一个图片文件的名称和标签(label)
batch_size: 每一次处理的数据个数,即图片数
可选参数:
rand_skip: 在开始的时候,路过某个数据的输入。通常对异步的SGD很有用。
shuffle: 随机打乱顺序,默认值为false
new_height,new_width: 如果设置,则将图片进行resize
参考源码:
message ImageDataParameter {
// Specify the data source.
optional string source = 1;
// Specify the batch size.
optional uint32 batch_size = 4 [default = 1];
// The rand_skip variable is for the data layer to skip a few data points
// to avoid all asynchronous sgd clients to start at the same point. The skip
// point would be set as rand_skip * rand(0,1). Note that rand_skip should not
// be larger than the number of keys in the database.
optional uint32 rand_skip = 7 [default = 0];
// Whether or not ImageLayer should shuffle the list of files at every epoch.
optional bool shuffle = 8 [default = false];
// It will also resize images if new_height or new_width are not zero.
optional uint32 new_height = 9 [default = 0];
optional uint32 new_width = 10 [default = 0];
// Specify if the images are color or gray
optional bool is_color = 11 [default = true];
// DEPRECATED. See TransformationParameter. For data pre-processing, we can do
// simple scaling and subtracting the data mean, if provided. Note that the
// mean subtraction is always carried out before scaling.
optional float scale = 2 [default = 1];
optional string mean_file = 3;
// DEPRECATED. See TransformationParameter. Specify if we would like to randomly
// crop an image.
optional uint32 crop_size = 5 [default = 0];
// DEPRECATED. See TransformationParameter. Specify if we want to randomly mirror
// data.
optional bool mirror = 6 [default = false];
optional string root_folder = 12 [default = ""];
}
5)type:Python 这个有点牛,可以自己定义
例如:鼎鼎大名的fcn 就采用了这个:
layer {
name: "data"
type: "Python"
top: "data"
top: "sem"
top: "geo"
python_param {
module: "siftflow_layers"
layer: "SIFTFlowSegDataLayer"
param_str: "{\'siftflow_dir\': \'../data/sift-flow\', \'seed\': 1337, \'split\': \'trainval\'}"
}
}
具体可去caffe官网查看内容,先写这么多吧!!!