[转]caffe源码解析 — caffe.proto
原文地址
引言
要看caffe源码，我认为首先应该看的就是caffe.proto。
它位于…\src\caffe\proto目录下，在这个文件夹下还有一个.pb.cc和一个.pb.h文件，这两个文件都是由caffe.proto编译而来的。
在caffe.proto中定义了很多结构化数据，包括：
- BlobProto
- Datum
- FillerParameter
- NetParameter
- SolverParameter
- SolverState
- LayerParameter
- ConcatParameter
- ConvolutionParameter
- DataParameter
- DropoutParameter
- HDF5DataParameter
- HDF5OutputParameter
- ImageDataParameter
- InfogainLossParameter
- InnerProductParameter
- LRNParameter
- MemoryDataParameter
- PoolingParameter
- PowerParameter
- WindowDataParameter
- V0LayerParameter
正文
一、什么是protocol buffer
以下内容摘自：Google Protocol Buffer 的使用和原理
强烈推荐另外一篇极好的博文是：Protocol Buffer技术详解(C++实例)
简介
什么是 Google Protocol Buffer？ 假如您在网上搜索，应该会得到类似这样的文字介绍：
Google Protocol Buffer( 简称 Protobuf) 是 Google 公司内部的混合语言数据标准，目前已经正在使用的有超过 48,162 种报文格式定义和超过 12,183 个 .proto 文件。他们用于 RPC 系统和持续数据存储系统。
Protocol Buffers 是一种轻便高效的结构化数据存储格式，可以用于结构化数据串行化，或者说序列化。它很适合做数据存储或 RPC 数据交换格式。可用于通讯协议、数据存储等领域的语言无关、平台无关、可扩展的序列化结构数据格式。目前提供了 C++、Java、Python 三种语言的 API。
或许您和我一样，在第一次看完这些介绍后还是不明白 Protobuf 究竟是什么，那么我想一个简单的例子应该比较有助于理解它。
一个简单的例子
安装 Google Protocol Buffer
在网站 http://code.google.com/p/protobuf/downloads/list上可以下载 Protobuf 的源代码。然后解压编译安装便可以使用它了。
安装步骤如下所示：
tar -xzf protobuf-2.1.0.tar.gz
cd protobuf-2.1.0
./configure --prefix=$INSTALL_DIR
make
make check
make install
- 1
- 2
- 3
- 4
- 5
- 6
关于简单例子的描述
我打算使用 Protobuf 和 C++ 开发一个十分简单的例子程序。
该程序由两部分组成。第一部分被称为 Writer，第二部分叫做 Reader。
Writer 负责将一些结构化的数据写入一个磁盘文件，Reader 则负责从该磁盘文件中读取结构化数据并打印到屏幕上。
准备用于演示的结构化数据是 HelloWorld，它包含两个基本数据：
- ID，为一个整数类型的数据
- Str，这是一个字符串
书写 .proto 文件
首先我们需要编写一个 proto 文件，定义我们程序中需要处理的结构化数据，在 protobuf 的术语中，结构化数据被称为 Message。proto 文件非常类似 java 或者 C 语言的数据定义。代码清单 1 显示了例子应用中的 proto 文件内容。
清单 1. proto 文件
package lm;
message helloworld
{
required int32 id = 1; // ID
required string str = 2; // str
optional int32 opt = 3; //optional field
}
- 1
- 2
- 3
- 4
- 5
- 6
- 7
一个比较好的习惯是认真对待 proto 文件的文件名。比如将命名规则定于
packageName.MessageName.proto
在上例中，package 名字叫做 lm，定义了一个消息 helloworld，该消息有三个成员，类型为 int32 的 id，另一个为类型为 string 的成员 str。opt 是一个可选的成员，即消息中可以不包含该成员。
编译 .proto 文件
写好 proto 文件之后就可以用 Protobuf 编译器将该文件编译成目标语言了。本例中我们将使用 C++。
假设您的 proto 文件存放在 $SRC_DIR 下面，您也想把生成的文件放在同一个目录下，则可以使用如下命令：
protoc -I=$SRC_DIR --cpp_out=$DST_DIR $SRC_DIR/addressbook.proto
- 1
命令将生成两个文件：
lm.helloworld.pb.h ， 定义了 C++ 类的头文件
lm.helloworld.pb.cc ， C++ 类的实现文件
在生成的头文件中，定义了一个 C++ 类 helloworld，后面的 Writer 和 Reader 将使用这个类来对消息进行操作。诸如对消息的成员进行赋值，将消息序列化等等都有相应的方法。
编写 writer 和 Reader
如前所述，Writer将把一个结构化数据写入磁盘，以便其他人来读取。假如我们不使用 Protobuf，其实也有许多的选择。一个可能的方法是将数据转换为字符串，然后将字符串写入磁盘。转换为字符串的方法可以使用sprintf()，这非常简单。数字123可以变成字符串“123”。
这样做似乎没有什么不妥，但是仔细考虑一下就会发现，这样的做法对写 Reader 的那个人的要求比较高，Reader 的作者必须了 Writer 的细节。比如”123”可以是单个数字 123，但也可以是三个数字 1,2 和 3，等等。这么说来，我们还必须让 Writer 定义一种分隔符一样的字符，以便 Reader 可以正确读取。但分隔符也许还会引起其他的什么问题。最后我们发现一个简单的 Helloworld 也需要写许多处理消息格式的代码。
如果使用 Protobuf，那么这些细节就可以不需要应用程序来考虑了。
使用 Protobuf，Writer 的工作很简单，需要处理的结构化数据由 .proto 文件描述，经过上一节中的编译过程后，该数据化结构对应了一个 C++ 的类，并定义在 lm.helloworld.pb.h 中。对于本例，类名为 lm::helloworld。
Writer 需要 include 该头文件，然后便可以使用这个类了。
现在，在 Writer 代码中，将要存入磁盘的结构化数据由一个 lm::helloworld 类的对象表示，它提供了一系列的 get/set 函数用来修改和读取结构化数据中的数据成员，或者叫 field。
当我们需要将该结构化数据保存到磁盘上时，类 lm::helloworld 已经提供相应的方法来把一个复杂的数据变成一个字节序列，我们可以将这个字节序列写入磁盘。
对于想要读取这个数据的程序来说，也只需要使用类 lm::helloworld 的相应反序列化方法来将这个字节序列重新转换会结构化数据。这同我们开始时那个“123”的想法类似，不过 Protobuf 想的远远比我们那个粗糙的字符串转换要全面，因此，我们不如放心将这类事情交给 Protobuf 吧。
程序清单 2 演示了 Writer 的主要代码，您一定会觉得很简单吧？
清单 2. Writer 的主要代码
#include "lm.helloworld.pb.h"
…
int main(void)
{
lm::helloworld msg1;
msg1.set_id(101);
msg1.set_str(“hello”);
// Write the new address book back to disk.
fstream output("./log", ios::out | ios::trunc | ios::binary);
if (!msg1.SerializeToOstream(&output)) {
cerr << "Failed to write msg." << endl;
return -1;
}
return 0;
}
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
Msg1 是一个 helloworld 类的对象，set_id() 用来设置 id 的值。SerializeToOstream 将对象序列化后写入一个 fstream 流。
代码清单 3 列出了 reader 的主要代码。
清单 3. Reader
#include "lm.helloworld.pb.h"
…
void ListMsg(const lm::helloworld & msg) {
cout << msg.id() << endl;
cout << msg.str() << endl;
}
int main(int argc, char* argv[]) {
lm::helloworld msg1;
{
fstream input("./log", ios::in | ios::binary);
if (!msg1.ParseFromIstream(&input)) {
cerr << "Failed to parse address book." << endl;
return -1;
}
}
ListMsg(msg1);
…
}
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
同样，Reader 声明类 helloworld 的对象 msg1，然后利用 ParseFromIstream 从一个 fstream 流中读取信息并反序列化。此后，ListMsg 中采用 get 方法读取消息的内部信息，并进行打印输出操作。
运行结果
运行 Writer 和 Reader 的结果如下：
\>writer
\>reader
101
Hello
- 1
- 2
- 3
- 4
Reader 读取文件 log 中的序列化信息并打印到屏幕上。本文中所有的例子代码都可以在附件中下载。您可以亲身体验一下。
这个例子本身并无意义，但只要您稍加修改就可以将它变成更加有用的程序。比如将磁盘替换为网络 socket，那么就可以实现基于网络的数据交换任务。而存储和交换正是 Protobuf 最有效的应用领域。
二、caffe.proto中的几个重要数据类型
看完了上面关于protocol buffer的介绍，大家应该可以知道其实caffe.pb.cc里面的东西都是从caffe.proto编译而来的，无非就是一些关于这些数据结构（类）的标准化操作，比如
void CopyFrom();
void MergeFrom();
void CopyFrom();
void MergeFrom;
void Clear();
bool IsInitialized() const;
int ByteSize() const;
bool MergePartialFromCodedStream();
void SerializeWithCachedSizes() const;
SerializeWithCachedSizesToArray() const;
int GetCachedSize()
void SharedCtor();
void SharedDtor();
void SetCachedSize() const;
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
<0> BlobProto
message BlobProto {//blob的属性以及blob中的数据(data\diff)
optional int32 num = 1 [default = 0];
optional int32 channels = 2 [default = 0];
optional int32 height = 3 [default = 0];
optional int32 width = 4 [default = 0];
repeated float data = 5 [packed = true];
repeated float diff = 6 [packed = true];
}
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
<1> Datum
message Datum {
optional int32 channels = 1;
optional int32 height = 2;
optional int32 width = 3;
optional bytes data = 4;//真实的图像数据，以字节存储(bytes)
optional int32 label = 5;
repeated float float_data = 6;//datum也能存float类型的数据(float)
}
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
<2> LayerParameter
message LayerParameter {
repeated string bottom = 2; //输入的blob的名字(string)
repeated string top = 3; //输出的blob的名字(string)
optional string name = 4; //层的名字
enum LayerType { //层的枚举（enum，和c++中的enum一样）
NONE = 0;
ACCURACY = 1;
BNLL = 2;
CONCAT = 3;
CONVOLUTION = 4;
DATA = 5;
DROPOUT = 6;
EUCLIDEAN_LOSS = 7;
ELTWISE_PRODUCT = 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;
POOLING = 17;
POWER = 26;
RELU = 18;
SIGMOID = 19;
SIGMOID_CROSS_ENTROPY_LOSS = 27;
SOFTMAX = 20;
SOFTMAX_LOSS = 21;
SPLIT = 22;
TANH = 23;
WINDOW_DATA = 24;
}
optional LayerType type = 5; // 层的类型
repeated BlobProto blobs = 6; //blobs的数值参数
repeated float blobs_lr = 7; //学习速率(repeated)，如果你想那个设置一个blob的学习速率，你需要设置所有blob的学习速率。
repeated float weight_decay = 8; //权值衰减(repeated)
// 相对于某一特定层的参数(optional)
optional ConcatParameter concat_param = 9;
optional ConvolutionParameter convolution_param = 10;
optional DataParameter data_param = 11;
optional DropoutParameter dropout_param = 12;
optional HDF5DataParameter hdf5_data_param = 13;
optional HDF5OutputParameter hdf5_output_param = 14;
optional ImageDataParameter image_data_param = 15;
optional InfogainLossParameter infogain_loss_param = 16;
optional InnerProductParameter inner_product_param = 17;
optional LRNParameter lrn_param = 18;
optional MemoryDataParameter memory_data_param = 22;
optional PoolingParameter pooling_param = 19;
optional PowerParameter power_param = 21;
optional WindowDataParameter window_data_param = 20;
optional V0LayerParameter layer = 1;
}
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
- 27
- 28
- 29
- 30
- 31
- 32
- 33
- 34
- 35
- 36
- 37
- 38
- 39
- 40
- 41
- 42
- 43
- 44
- 45
- 46
- 47
- 48
- 49
- 50
- 51
- 52
- 53
- 54
- 55
- 56
- 57
- 58
<3> NetParameter
message NetParameter {
optional string name = 1;//网络的名字
repeated LayerParameter layers = 2; //repeated类似于数组
repeated string input = 3;//输入层blob的名字
repeated int32 input_dim = 4;//输入层blob的维度，应该等于(4*#input)
optional bool force_backward = 5 [default = false];//网络是否进行反向传播。如果设置为否，则由网络的结构和学习速率来决定是否进行反向传播。
}
- 1
- 2
- 3
- 4
- 5
- 6
- 7
<4> SolverParameter
message SolverParameter {
optional string train_net = 1; // 训练网络的proto file
optional string test_net = 2; // 测试网络的proto file
optional int32 test_iter = 3 [default = 0]; // 每次测试时的迭代次数
optional int32 test_interval = 4 [default = 0]; // 两次测试的间隔迭代次数
optional bool test_compute_loss = 19 [default = false];
optional float base_lr = 5; // 基本学习率
optional int32 display = 6; // 两次显示的间隔迭代次数
optional int32 max_iter = 7; // 最大迭代次数
optional string lr_policy = 8; // 学习速率衰减方式
optional float gamma = 9; // 关于梯度下降的一个参数
optional float power = 10; // 计算学习率的一个参数
optional float momentum = 11; // 动量
optional float weight_decay = 12; // 权值衰减
optional int32 stepsize = 13; // 学习速率的衰减步长
optional int32 snapshot = 14 [default = 0]; // snapshot的间隔
optional string snapshot_prefix = 15; // snapshot的前缀
optional bool snapshot_diff = 16 [default = false]; // 是否对于 diff 进行 snapshot
enum SolverMode {
CPU = 0;
GPU = 1;
}
optional SolverMode solver_mode = 17 [default = GPU]; // solver的模式，默认为GPU
optional int32 device_id = 18 [default = 0]; // GPU的ID
optional int64 random_seed = 20 [default = -1]; // 随机数种子
}
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
三、caffe.proto源码
// Copyright 2014 BVLC and contributors.
package caffe;
message BlobProto {
optional int32 num = 1 [default = 0];
optional int32 channels = 2 [default = 0];
optional int32 height = 3 [default = 0];
optional int32 width = 4 [default = 0];
repeated float data = 5 [packed = true];
repeated float diff = 6 [packed = true];
}
// The BlobProtoVector is simply a way to pass multiple blobproto instances
// around.
message BlobProtoVector {
repeated BlobProto blobs = 1;
}
message Datum {
optional int32 channels = 1;
optional int32 height = 2;
optional int32 width = 3;
// the actual image data, in bytes
optional bytes data = 4;
optional int32 label = 5;
// Optionally, the datum could also hold float data.
repeated float float_data = 6;
}
message FillerParameter {
// The filler type.
optional string type = 1 [default = 'constant'];
optional float value = 2 [default = 0]; // the value in constant filler
optional float min = 3 [default = 0]; // the min value in uniform filler
optional float max = 4 [default = 1]; // the max value in uniform filler
optional float mean = 5 [default = 0]; // the mean value in Gaussian filler
optional float std = 6 [default = 1]; // the std value in Gaussian filler
// The expected number of non-zero input weights for a given output in
// Gaussian filler -- the default -1 means don't perform sparsification.
optional int32 sparse = 7 [default = -1];
}
message NetParameter {
optional string name = 1; // consider giving the network a name
repeated LayerParameter layers = 2; // a bunch of layers.
// The input blobs to the network.
repeated string input = 3;
// The dim of the input blobs. For each input blob there should be four
// values specifying the num, channels, height and width of the input blob.
// Thus, there should be a total of (4 * #input) numbers.
repeated int32 input_dim = 4;
// Whether the network will force every layer to carry out backward operation.
// If set False, then whether to carry out backward is determined
// automatically according to the net structure and learning rates.
optional bool force_backward = 5 [default = false];
}
message SolverParameter {
optional string train_net = 1; // The proto file for the training net.
optional string test_net = 2; // The proto file for the testing net.
// The number of iterations for each testing phase.
optional int32 test_iter = 3 [default = 0];
// The number of iterations between two testing phases.
optional int32 test_interval = 4 [default = 0];
optional bool test_compute_loss = 19 [default = false];
optional float base_lr = 5; // The base learning rate
// the number of iterations between displaying info. If display = 0, no info
// will be displayed.
optional int32 display = 6;
optional int32 max_iter = 7; // the maximum number of iterations
optional string lr_policy = 8; // The learning rate decay policy.
optional float gamma = 9; // The parameter to compute the learning rate.
optional float power = 10; // The parameter to compute the learning rate.
optional float momentum = 11; // The momentum value.
optional float weight_decay = 12; // The weight decay.
optional int32 stepsize = 13; // the stepsize for learning rate policy "step"
optional int32 snapshot = 14 [default = 0]; // The snapshot interval
optional string snapshot_prefix = 15; // The prefix for the snapshot.
// whether to snapshot diff in the results or not. Snapshotting diff will help
// debugging but the final protocol buffer size will be much larger.
optional bool snapshot_diff = 16 [default = false];
// the mode solver will use: 0 for CPU and 1 for GPU. Use GPU in default.
enum SolverMode {
CPU = 0;
GPU = 1;
}
optional SolverMode solver_mode = 17 [default = GPU];
// the device_id will that be used in GPU mode. Use device_id = 0 in default.
optional int32 device_id = 18 [default = 0];
// If non-negative, the seed with which the Solver will initialize the Caffe
// random number generator -- useful for reproducible results. Otherwise,
// (and by default) initialize using a seed derived from the system clock.
optional int64 random_seed = 20 [default = -1];
}
// A message that stores the solver snapshots
message SolverState {
optional int32 iter = 1; // The current iteration
optional string learned_net = 2; // The file that stores the learned net.
repeated BlobProto history = 3; // The history for sgd solvers
}
// Update the next available ID when you add a new LayerParameter field.
//
// LayerParameter next available ID: 23 (last added: memory_data_param)
message LayerParameter {
repeated string bottom = 2; // the name of the bottom blobs
repeated string top = 3; // the name of the top blobs
optional string name = 4; // the layer name
// Add new LayerTypes to the enum below in lexicographical order (other than
// starting with NONE), starting with the next available ID in the comment
// line above the enum. Update the next available ID when you add a new
// LayerType.
//
// LayerType next available ID: 30 (last added: MEMORY_DATA)
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;
ACCURACY = 1;
BNLL = 2;
CONCAT = 3;
CONVOLUTION = 4;
DATA = 5;
DROPOUT = 6;
EUCLIDEAN_LOSS = 7;
ELTWISE_PRODUCT = 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;
POOLING = 17;
POWER = 26;
RELU = 18;
SIGMOID = 19;
SIGMOID_CROSS_ENTROPY_LOSS = 27;
SOFTMAX = 20;
SOFTMAX_LOSS = 21;
SPLIT = 22;
TANH = 23;
WINDOW_DATA = 24;
}
optional LayerType type = 5; // the layer type from the enum above
// The blobs containing the numeric parameters of the layer
repeated BlobProto blobs = 6;
// The ratio that is multiplied on the global learning rate. If you want to
// set the learning ratio for one blob, you need to set it for all blobs.
repeated float blobs_lr = 7;
// The weight decay that is multiplied on the global weight decay.
repeated float weight_decay = 8;
// Parameters for particular layer types.
optional ConcatParameter concat_param = 9;
optional ConvolutionParameter convolution_param = 10;
optional DataParameter data_param = 11;
optional DropoutParameter dropout_param = 12;
optional HDF5DataParameter hdf5_data_param = 13;
optional HDF5OutputParameter hdf5_output_param = 14;
optional ImageDataParameter image_data_param = 15;
optional InfogainLossParameter infogain_loss_param = 16;
optional InnerProductParameter inner_product_param = 17;
optional LRNParameter lrn_param = 18;
optional MemoryDataParameter memory_data_param = 22;
optional PoolingParameter pooling_param = 19;
optional PowerParameter power_param = 21;
optional WindowDataParameter window_data_param = 20;
// DEPRECATED: The layer parameters specified as a V0LayerParameter.
// This should never be used by any code except to upgrade to the new
// LayerParameter specification.
optional V0LayerParameter layer = 1;
}
// Message that stores parameters used by ConcatLayer
message ConcatParameter {
// Concat Layer needs to specify the dimension along the concat will happen,
// the other dimensions must be the same for all the bottom blobs
// By default it will concatenate blobs along channels dimension
optional uint32 concat_dim = 1 [default = 1];
}
// Message that stores parameters used by ConvolutionLayer
message ConvolutionParameter {
optional uint32 num_output = 1; // The number of outputs for the layer
optional bool bias_term = 2 [default = true]; // whether to have bias terms
optional uint32 pad = 3 [default = 0]; // The padding size
optional uint32 kernel_size = 4; // The kernel size
optional uint32 group = 5 [default = 1]; // The group size for group conv
optional uint32 stride = 6 [default = 1]; // The stride
optional FillerParameter weight_filler = 7; // The filler for the weight
optional FillerParameter bias_filler = 8; // The filler for the bias
}
// Message that stores parameters used by DataLayer
message DataParameter {
// Specify the data source.
optional string source = 1;
// 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;
// Specify the batch size.
optional uint32 batch_size = 4;
// Specify if we would like to randomly crop an image.
optional uint32 crop_size = 5 [default = 0];
// Specify if we want to randomly mirror data.
optional bool mirror = 6 [default = false];
// 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 leveldb.
optional uint32 rand_skip = 7 [default = 0];
}
// Message that stores parameters used by DropoutLayer
message DropoutParameter {
optional float dropout_ratio = 1 [default = 0.5]; // dropout ratio
}
// 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;
}
// Message that stores parameters used by HDF5OutputLayer
message HDF5OutputParameter {
optional string file_name = 1;
}
// Message that stores parameters used by ImageDataLayer
message ImageDataParameter {
// Specify the data source.
optional string source = 1;
// 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;
// Specify the batch size.
optional uint32 batch_size = 4;
// Specify if we would like to randomly crop an image.
optional uint32 crop_size = 5 [default = 0];
// Specify if we want to randomly mirror data.
optional bool mirror = 6 [default = false];
// 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 leveldb.
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];
}
// Message that stores parameters InfogainLossLayer
message InfogainLossParameter {
// Specify the infogain matrix source.
optional string source = 1;
}
// Message that stores parameters used by InnerProductLayer
message InnerProductParameter {
optional uint32 num_output = 1; // The number of outputs for the layer
optional bool bias_term = 2 [default = true]; // whether to have bias terms
optional FillerParameter weight_filler = 3; // The filler for the weight
optional FillerParameter bias_filler = 4; // The filler for the bias
}
// Message that stores parameters used by LRNLayer
message LRNParameter {
optional uint32 local_size = 1 [default = 5];
optional float alpha = 2 [default = 1.];
optional float beta = 3 [default = 0.75];
enum NormRegion {
ACROSS_CHANNELS = 0;
WITHIN_CHANNEL = 1;
}
optional NormRegion norm_region = 4 [default = ACROSS_CHANNELS];
}
// Message that stores parameters used by MemoryDataLayer
message MemoryDataParameter {
optional uint32 batch_size = 1;
optional uint32 channels = 2;
optional uint32 height = 3;
optional uint32 width = 4;
}
// Message that stores parameters used by PoolingLayer
message PoolingParameter {
enum PoolMethod {
MAX = 0;
AVE = 1;
STOCHASTIC = 2;
}
optional PoolMethod pool = 1 [default = MAX]; // The pooling method
optional uint32 kernel_size = 2; // The kernel size
optional uint32 stride = 3 [default = 1]; // The stride
// The padding size -- currently implemented only for average pooling.
optional uint32 pad = 4 [default = 0];
}
// Message that stores parameters used by PowerLayer
message PowerParameter {
// PowerLayer computes outputs y = (shift + scale * x) ^ power.
optional float power = 1 [default = 1.0];
optional float scale = 2 [default = 1.0];
optional float shift = 3 [default = 0.0];
}
// Message that stores parameters used by WindowDataLayer
message WindowDataParameter {
// Specify the data source.
optional string source = 1;
// 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;
// Specify the batch size.
optional uint32 batch_size = 4;
// Specify if we would like to randomly crop an image.
optional uint32 crop_size = 5 [default = 0];
// Specify if we want to randomly mirror data.
optional bool mirror = 6 [default = false];
// Foreground (object) overlap threshold
optional float fg_threshold = 7 [default = 0.5];
// Background (non-object) overlap threshold
optional float bg_threshold = 8 [default = 0.5];
// Fraction of batch that should be foreground objects
optional float fg_fraction = 9 [default = 0.25];
// Amount of contextual padding to add around a window
// (used only by the window_data_layer)
optional uint32 context_pad = 10 [default = 0];
// Mode for cropping out a detection window
// warp: cropped window is warped to a fixed size and aspect ratio
// square: the tightest square around the window is cropped
optional string crop_mode = 11 [default = "warp"];
}
// DEPRECATED: V0LayerParameter is the old way of specifying layer parameters
// in Caffe. We keep this message type around for legacy support.
message V0LayerParameter {
optional string name = 1; // the layer name
optional string type = 2; // the string to specify the layer type
// Parameters to specify layers with inner products.
optional uint32 num_output = 3; // The number of outputs for the layer
optional bool biasterm = 4 [default = true]; // whether to have bias terms
optional FillerParameter weight_filler = 5; // The filler for the weight
optional FillerParameter bias_filler = 6; // The filler for the bias
optional uint32 pad = 7 [default = 0]; // The padding size
optional uint32 kernelsize = 8; // The kernel size
optional uint32 group = 9 [default = 1]; // The group size for group conv
optional uint32 stride = 10 [default = 1]; // The stride
enum PoolMethod {
MAX = 0;
AVE = 1;
STOCHASTIC = 2;
}
optional PoolMethod pool = 11 [default = MAX]; // The pooling method
optional float dropout_ratio = 12 [default = 0.5]; // dropout ratio
optional uint32 local_size = 13 [default = 5]; // for local response norm
optional float alpha = 14 [default = 1.]; // for local response norm
optional float beta = 15 [default = 0.75]; // for local response norm
// For data layers, specify the data source
optional string source = 16;
// 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 = 17 [default = 1];
optional string meanfile = 18;
// For data layers, specify the batch size.
optional uint32 batchsize = 19;
// For data layers, specify if we would like to randomly crop an image.
optional uint32 cropsize = 20 [default = 0];
// For data layers, specify if we want to randomly mirror data.
optional bool mirror = 21 [default = false];
// The blobs containing the numeric parameters of the layer
repeated BlobProto blobs = 50;
// The ratio that is multiplied on the global learning rate. If you want to
// set the learning ratio for one blob, you need to set it for all blobs.
repeated float blobs_lr = 51;
// The weight decay that is multiplied on the global weight decay.
repeated float weight_decay = 52;
// 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 leveldb.
optional uint32 rand_skip = 53 [default = 0];
// Fields related to detection (det_*)
// foreground (object) overlap threshold
optional float det_fg_threshold = 54 [default = 0.5];
// background (non-object) overlap threshold
optional float det_bg_threshold = 55 [default = 0.5];
// Fraction of batch that should be foreground objects
optional float det_fg_fraction = 56 [default = 0.25];
// optional bool OBSOLETE_can_clobber = 57 [default = true];
// Amount of contextual padding to add around a window
// (used only by the window_data_layer)
optional uint32 det_context_pad = 58 [default = 0];
// Mode for cropping out a detection window
// warp: cropped window is warped to a fixed size and aspect ratio
// square: the tightest square around the window is cropped
optional string det_crop_mode = 59 [default = "warp"];
// For ReshapeLayer, one needs to specify the new dimensions.
optional int32 new_num = 60 [default = 0];
optional int32 new_channels = 61 [default = 0];
optional int32 new_height = 62 [default = 0];
optional int32 new_width = 63 [default = 0];
// Whether or not ImageLayer should shuffle the list of files at every epoch.
// It will also resize images if new_height or new_width are not zero.
optional bool shuffle_images = 64 [default = false];
// For ConcatLayer, one needs to specify the dimension for concatenation, and
// the other dimensions must be the same for all the bottom blobs.
// By default it will concatenate blobs along the channels dimension.
optional uint32 concat_dim = 65 [default = 1];
optional HDF5OutputParameter hdf5_output_param = 1001;
}
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
- 27
- 28
- 29
- 30
- 31
- 32
- 33
- 34
- 35
- 36
- 37
- 38
- 39
- 40
- 41
- 42
- 43
- 44
- 45
- 46
- 47
- 48
- 49
- 50
- 51
- 52
- 53
- 54
- 55
- 56
- 57
- 58
- 59
- 60
- 61
- 62
- 63
- 64
- 65
- 66
- 67
- 68
- 69
- 70
- 71
- 72
- 73
- 74
- 75
- 76
- 77
- 78
- 79
- 80
- 81
- 82
- 83
- 84
- 85
- 86
- 87
- 88
- 89
- 90
- 91
- 92
- 93
- 94
- 95
- 96
- 97
- 98
- 99
- 100
- 101
- 102
- 103
- 104
- 105
- 106
- 107
- 108
- 109
- 110
- 111
- 112
- 113
- 114
- 115
- 116
- 117
- 118
- 119
- 120
- 121
- 122
- 123
- 124
- 125
- 126
- 127
- 128
- 129
- 130
- 131
- 132
- 133
- 134
- 135
- 136
- 137
- 138
- 139
- 140
- 141
- 142
- 143
- 144
- 145
- 146
- 147
- 148
- 149
- 150
- 151
- 152
- 153
- 154
- 155
- 156
- 157
- 158
- 159
- 160
- 161
- 162
- 163
- 164
- 165
- 166
- 167
- 168
- 169
- 170
- 171
- 172
- 173
- 174
- 175
- 176
- 177
- 178
- 179
- 180
- 181
- 182
- 183
- 184
- 185
- 186
- 187
- 188
- 189
- 190
- 191
- 192
- 193
- 194
- 195
- 196
- 197
- 198
- 199
- 200
- 201
- 202
- 203
- 204
- 205
- 206
- 207
- 208
- 209
- 210
- 211
- 212
- 213
- 214
- 215
- 216
- 217
- 218
- 219
- 220
- 221
- 222
- 223
- 224
- 225
- 226
- 227
- 228
- 229
- 230
- 231
- 232
- 233
- 234
- 235
- 236
- 237
- 238
- 239
- 240
- 241
- 242
- 243
- 244
- 245
- 246
- 247
- 248
- 249
- 250
- 251
- 252
- 253
- 254
- 255
- 256
- 257
- 258
- 259
- 260
- 261
- 262
- 263
- 264
- 265
- 266
- 267
- 268
- 269
- 270
- 271
- 272
- 273
- 274
- 275
- 276
- 277
- 278
- 279
- 280
- 281
- 282
- 283
- 284
- 285
- 286
- 287
- 288
- 289
- 290
- 291
- 292
- 293
- 294
- 295
- 296
- 297
- 298
- 299
- 300
- 301
- 302
- 303
- 304
- 305
- 306
- 307
- 308
- 309
- 310
- 311
- 312
- 313
- 314
- 315
- 316
- 317
- 318
- 319
- 320
- 321
- 322
- 323
- 324
- 325
- 326
- 327
- 328
- 329
- 330
- 331
- 332
- 333
- 334
- 335
- 336
- 337
- 338
- 339
- 340
- 341
- 342
- 343
- 344
- 345
- 346
- 347
- 348
- 349
- 350
- 351
- 352
- 353
- 354
- 355
- 356
- 357
- 358
- 359
- 360
- 361
- 362
- 363
- 364
- 365
- 366
- 367
- 368
- 369
- 370
- 371
- 372
- 373
- 374
- 375
- 376
- 377
- 378
- 379
- 380
- 381
- 382
- 383
- 384
- 385
- 386
- 387
- 388
- 389
- 390
- 391
- 392
- 393
- 394
- 395
- 396
- 397
- 398
- 399
- 400
- 401
- 402
- 403
- 404
- 405
- 406
- 407
- 408
- 409
- 410
- 411
- 412
- 413
- 414
- 415
- 416
- 417
- 418
- 419
- 420
- 421
- 422
- 423
- 424
- 425
- 426
- 427
- 428
- 429
- 430
- 431
- 432
- 433
- 434
- 435
- 436
- 437
- 438
- 439
- 440
- 441
- 442
- 443
- 444
- 445
- 446
- 447
- 448