caffe源码解析caffeproto.docx

1、caffe源码解析 caffeproto要看caffe源码，首先应该看的就是caffe.proto。它位于srccaffeproto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 DropoutPar

2、ameter HDF5DataParameter HDF5OutputParameter ImageDataParameter InfogainLossParameter InnerProductParameter LRNParameter MemoryDataParameter PoolingParameter PowerParameter WindowDataParameter V0LayerParametercaffe.proto中的几个重要数据类型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 Co

3、pyFrom(); 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; BlobPr

4、otomessage BlobProto /blob的属性以及blob中的数据(datadiff) 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; Datum message Datu

5、m 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) LayerParametermessage LayerParameter repeated string bottom = 2; /输入的blob的名字(string) re

6、peated 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 =

7、 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; optiona

8、l 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 co

9、nvolution_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

10、_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

11、 = 20; optional V0LayerParameter layer = 1; NetParametermessage 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 = fal

12、se;/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。 SolverParametermessage 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 op

13、tional 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 f

14、loat 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 Solve

15、rMode 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caffe.proto源码/ Copyright 2014 BVLC and contributors.package caffe;message BlobProto optional int32 n

16、um = 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.me

17、ssage 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 f

18、loat_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 unif

19、orm 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 dont perform sparsification. optio

20、nal 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 b

21、e 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

22、 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 numb

23、er 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 num

24、ber 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 th

25、e 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

26、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

27、; / 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,

28、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 snapshotsmessage

29、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

30、: 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)