caffe源碼解析-caffe.proto

《caffe源碼解析-caffe.proto》由會(huì)員分享，可在線閱讀，更多相關(guān)《caffe源碼解析-caffe.proto（18頁(yè)珍藏版）》請(qǐng)?jiān)谘b配圖網(wǎng)上搜索。

1、文檔供參考，可復(fù)制、編制，期待您的好評(píng)與關(guān)注！ 要看caffe源碼，首先應(yīng)該看的就是caffe.proto。? 它位于…\src\caffe\proto目錄下，在這個(gè)文件夾下還有一個(gè).pb.cc和一個(gè).pb.h文件，這兩個(gè)文件都是由caffe.proto編譯而來(lái)的。? 在caffe.proto中定義了很多結(jié)構(gòu)化數(shù)據(jù)，包括： · BlobProto · Datum · FillerParameter · NetParameter · SolverParameter · SolverState · LayerParameter · ConcatParameter · C

2、onvolutionParameter · DataParameter · DropoutParameter · HDF5DataParameter · HDF5OutputParameter · ImageDataParameter · InfogainLossParameter · InnerProductParameter · LRNParameter · MemoryDataParameter · PoolingParameter · PowerParameter · WindowDataParameter · V0LayerParameter caffe.

3、proto中的幾個(gè)重要數(shù)據(jù)類型 caffe.pb.cc里面的東西都是從caffe.proto編譯而來(lái)的，無(wú)非就是一些關(guān)于這些數(shù)據(jù)結(jié)構(gòu)（類）的標(biāo)準(zhǔn)化操作，比如 void CopyFrom(); void MergeFrom(); void Clear(); bool IsInitialized() const; int ByteSize() const; bool MergePartialFromCodedStream(); void SerializeWithCachedSizes() const; SerializeWithCachedSiz

4、esToArray() const; int GetCachedSize() void SharedCtor(); void SharedDtor(); void SetCachedSize() const; <0> BlobProto message BlobProto {//blob的屬性以及blob中的數(shù)據(jù)(data\diff) optional int32 num = 1 [default = 0]; optional int32 channels = 2 [default = 0]; optional int32 height = 3 [

5、default = 0]; optional int32 width = 4 [default = 0]; repeated float data = 5 [packed = true]; repeated float diff = 6 [packed = true]; } <1> Datum message Datum { optional int32 channels = 1; optional int32 height = 2; optional int32 width = 3; optional bytes data = 4;//真實(shí)

6、的圖像數(shù)據(jù)，以字節(jié)存儲(chǔ)(bytes) optional int32 label = 5; repeated float float_data = 6;//datum也能存float類型的數(shù)據(jù)(float) } <2> LayerParameter message LayerParameter { repeated string bottom = 2; //輸入的blob的名字(string) repeated string top = 3; //輸出的blob的名字(string) optional string name = 4; //層的名字 en

7、um LayerType { //層的枚舉（enum，和c++中的enum一樣） 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;

8、 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; SOFTM

9、AX_LOSS = 21; SPLIT = 22; TANH = 23; WINDOW_DATA = 24; } optional LayerType type = 5; // 層的類型 repeated BlobProto blobs = 6; //blobs的數(shù)值參數(shù) repeated float blobs_lr = 7; //學(xué)習(xí)速率(repeated)，如果你想設(shè)置一個(gè)blob的學(xué)習(xí)速率，你需要設(shè)置所有blob的學(xué)習(xí)速率。 repeated float weight_decay = 8; //權(quán)值衰減(repeated)

10、 // 相對(duì)于某一特定層的參數(shù)(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 HDF5OutputPa

11、rameter 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 = 2

12、2; optional PoolingParameter pooling_param = 19; optional PowerParameter power_param = 21; optional WindowDataParameter window_data_param = 20; optional V0LayerParameter layer = 1; } <3> NetParameter message NetParameter { optional string name = 1;//網(wǎng)絡(luò)的名字 repeated LayerParameter

13、 layers = 2; //repeated類似于數(shù)組 repeated string input = 3;//輸入層blob的名字 repeated int32 input_dim = 4;//輸入層blob的維度，應(yīng)該等于(4*#input) optional bool force_backward = 5 [default = false];//網(wǎng)絡(luò)是否進(jìn)行反向傳播。如果設(shè)置為否，則由網(wǎng)絡(luò)的結(jié)構(gòu)和學(xué)習(xí)速率來(lái)決定是否進(jìn)行反向傳播。 } <4> SolverParameter message SolverParameter { optional string

14、train_net = 1; // 訓(xùn)練網(wǎng)絡(luò)的proto file optional string test_net = 2; // 測(cè)試網(wǎng)絡(luò)的proto file optional int32 test_iter = 3 [default = 0]; // 每次測(cè)試時(shí)的迭代次數(shù) optional int32 test_interval = 4 [default = 0]; // 兩次測(cè)試的間隔迭代次數(shù) optional bool test_compute_loss = 19 [default = false]; optional float base_lr =

15、5; // 基本學(xué)習(xí)率 optional int32 display = 6; // 兩次顯示的間隔迭代次數(shù) optional int32 max_iter = 7; // 最大迭代次數(shù) optional string lr_policy = 8; // 學(xué)習(xí)速率衰減方式 optional float gamma = 9; // 關(guān)于梯度下降的一個(gè)參數(shù) optional float power = 10; // 計(jì)算學(xué)習(xí)率的一個(gè)參數(shù) optional float momentum = 11; // 動(dòng)量 optional float weight_de

16、cay = 12; // 權(quán)值衰減 optional int32 stepsize = 13; // 學(xué)習(xí)速率的衰減步長(zhǎng) optional int32 snapshot = 14 [default = 0]; // snapshot的間隔 optional string snapshot_prefix = 15; // snapshot的前綴 optional bool snapshot_diff = 16 [default = false]; // 是否對(duì)于 diff 進(jìn)行 snapshot enum SolverMode { CPU = 0;

17、 GPU = 1; } optional SolverMode solver_mode = 17 [default = GPU]; // solver的模式，默認(rèn)為GPU optional int32 device_id = 18 [default = 0]; // GPU的ID optional int64 random_seed = 20 [default = -1]; // 隨機(jī)數(shù)種子 } caffe.proto源碼 // Copyright 2014 BVLC and contributors. package caffe; message Bl

18、obProto { 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

19、 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

20、= 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 f

21、iller 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 Ga

22、ussian 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

23、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,

24、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 rat

25、es. 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. optio

26、nal 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 betw

27、een 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 l

28、earning 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 in

29、t32 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 boo

30、l 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

31、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. optio

32、nal 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 fo

33、r 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 o

34、f 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

35、 // 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).

36、 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;

37、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 =

38、 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 learni

39、ng 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

40、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;

41、 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_pa

42、ram = 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; } // Me

43、ssage 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 opti

44、onal 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 optio

45、nal 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 f

46、iller 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 su

47、btracting 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 rando

48、mly 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

49、 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 {

50、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; } // Messag

51、e 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,

52、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; // Sp

53、ecify 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 asynchron

54、ous 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 fi

55、les 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 m

56、essage 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_t

57、erm = 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 uin

58、t32 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 par

59、ameters 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

60、{ 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 av

61、erage 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];

62、 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 pro

63、vided. 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

64、 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_threshol

65、d = 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

66、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