caffe.proto文件位于 ..\caffe-fast-rcnn\src\caffe\proto文件目录下 ,根目录为 py_faster_rcnn文件夹
syntax = "proto2";
package caffe;
//
repeated required
optional
// 类似数组 必要的 可选的
// Specifies the shape (dimensions) of a Blob.
message BlobShape {
repeated int64 dim = 1 [packed = true];
}
message BlobProto {
optional BlobShape shape = 7; //下文中替代4D描述符的结构
repeated float data = 5 [packed = true];
repeated float diff = 6 [packed = true];
repeated double double_data = 8 [packed = true];
repeated double double_diff = 9 [packed = true];
// 4D dimensions -- deprecated. Use "shape" instead.
// 4维的描述方式舍弃掉,改用"BlobShape"结构替代
optional int32 num = 1 [default = 0];
optional int32 channels = 2 [default = 0];
optional int32 height = 3 [default = 0];
optional int32 width = 4 [default = 0];
}
// The BlobProtoVector is simply a way to pass multiple blobproto instances
// around.
message BlobProtoVector {
repeated BlobProto blobs = 1;
}
//图像数据结构
message Datum {
optional int32 channels = 1;
optional int32 height = 2;
optional int32 width = 3;
// the actual image data, in bytes
//实际上以字节存储图像内容
optional bytes data = 4;
optional int32 label = 5;
// Optionally, the datum could also hold float data.
repeated float float_data = 6;
// If true data contains an encoded image that need to be decoded
optional bool encoded = 7 [default = false];
}
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 output weights for a given input in
// Gaussian filler -- the default -1 means don't perform sparsification.
//非零的输出值以高斯滤波系数值的方式填充
//默认值为-1,不进行稀疏化
optional int32 sparse = 7 [default = -1];
// Normalize the filler variance by fan_in, fan_out, or their average.
// Applies to 'xavier' and 'msra' fillers.
//Protocol Buffer中的枚举和C++中类似
enum VarianceNorm {
FAN_IN = 0;
FAN_OUT = 1;
AVERAGE = 2;
}
optional VarianceNorm variance_norm = 8 [default = FAN_IN];
}
//网络参数
message NetParameter {
optional string name = 1; // consider giving the network a name
// The input blobs to the network.
repeated string input = 3;
// The shape of the input blobs.
repeated BlobShape input_shape = 8;
// 4D input dimensions -- deprecated. Use "shape" instead.
// If specified, for each input blob there should be four
// values specifying thenum, 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.
//网络是否会迫使每一层都进行反向操作。
//如果设置为False,则根据网络结构和学习速率自动确定是否执行向后。
optional bool force_backward = 5 [default = false];
// The current "state" of the network, including thephase, level, and stage.
//当前的网络状态有phase,level,stage三种状态。
// Some layers may be included/excluded depending on this state and the states
// specified in the layers' include and exclude fields.
//根据此状态和图层的包含和非包含字段中指定的状态,可以包括/排除某些网络层。
optional NetState state = 6;
// Print debugging information about results while running Net::Forward,
// Net::Backward, and Net::Update.
//当运行前向网络,后向网络,更新网络的时候打印
调试信息,默认不打印
optional bool debug_info = 7 [default = false];
// The layers that make up the net. Each of their configurations, including
// connectivity and behavior, is specified as a LayerParameter.
//很多层就构成了网.
连接性和行为等配置参数构成了
层参数.最后打印出来
repeated LayerParameter layer = 100; // ID 100 so layers are printed last.
// DEPRECATED: use 'layer' instead.
//此后改用'layer'结构
repeated V1LayerParameter layers = 2;
}
// NOTE
// Update the next available ID when you add a new SolverParameter field.
//注意
//
当你添加新的求解器参数对象时,
更新了新的可用ID ,为 ID 41 type
//
// SolverParameter next available ID: 41 (last added: type)
//求解器参数
message SolverParameter {
//
// Specifying the train and test networks
//
// Exactly onetrain net must be specified using one of the following fields:
// train_net_param, train_net, net_param, net
// One or moretest nets may be specified using any of the following fields:
// test_net_param, test_net, net_param, net
// If more than one test net field is specified (e.g., both net and
// test_net are specified), they will be evaluated in the field order given
// above: (1) test_net_param, (2) test_net, (3) net_param/net.
//如果指定了多个测试网络字段(例如,指定了net和test_net),则将以上面给出的字段顺序对它们求值:
//(1)test_net_param,(2)test_net,(3)net_param / net。
// A test_iter must be specified for each test_net.
// 必须为每个test_net 指定 test_iter
// A test_level and/or a test_stage may also be specified for each test_net.
// 还可以为每个test_net指定test_level和/或test_stage
//
// Proto filename for the train net, possibly combined with one or more
// test nets.
//对于训练网络的原型文件名可能由一个或者多个训练网络组成。
optional string net = 24;
// Inline train net param, possibly combined with one or more test nets.
// 内联训练网络参数可能含有一个或者多个测试网络
optional NetParameter net_param = 25;
optional string train_net = 1; // Proto filename for the train net.
repeated string test_net = 2; // Proto filenames for the test nets.
optional NetParameter train_net_param = 21; // Inline train net params.
repeated NetParameter test_net_param = 22; // Inline test net params.
// The states for the train/test nets. Must be unspecified or
// specified once per net.
//要么确定,要么不确定,一旦确定,要么全是测试网络要么
全是
训练网络
//
// By default, all states will have solver = true;
// train_state will have phase = TRAIN,
// and all test_state's will have phase = TEST.
// Other defaults are set according to the NetState defaults.
//默认的,所有求解器的状态为真.训练网络
phase =
TRAIN,测试网络
phase = TEST,
//其他情况有网络状态的默认值决定
optional NetState train_state = 26;
repeated NetState test_state = 27;
// The number of iterations for each test net.
repeated int32 test_iter = 3;
// The number of iterations between two testing phases.
// 两个测试阶段之间的迭代次数。
optional int32 test_interval = 4 [default = 0];
optional bool test_compute_loss = 19 [default = false];
// If true, run an initial test pass before the first iteration,
// ensuring memory availability and printing the starting value of the loss.
// 若为真,在执行第一次迭代之前,先得运行初始化测试通过来确保有足够存储资源和打印初始值的loss信息
optional bool test_initialization = 32 [default = true];
optional float base_lr = 5; // The base learning rate //基准学习率
// the number of iterations between displaying info. If display = 0, no info
// will be displayed.
// 显示迭代之间
展示
信息,如果display = 0,则没有信息显示
optional int32 display = 6;
// Display the loss averaged over the last average_loss iterations
// 显示上次average_loss迭代的平均损失
optional int32 average_loss = 33 [default = 1];
optional int32 max_iter = 7; // the maximum number of iterations
// accumulate gradients over `iter_size` x `batch_size` instances
optional int32 iter_size = 36 [default = 1];
// The learning rate decay policy. The currently implemented learning rate
// policies are as follows:
// - fixed: always returnbase_lr.
// - step: returnbase_lr *gamma ^ (floor(iter / step))
// - exp: returnbase_lr *gamma ^ iter
// - inv: returnbase_lr * (1 +gamma * iter) ^ (- power)
// - multistep: similar to step but it allows non uniform steps defined by
// stepvalue
// - poly: the effective learning rate follows a polynomial decay, to be
// zero by the max_iter. returnbase_lr (1 -iter/max_iter) ^ (power)
// - sigmoid: the effective learning rate follows a sigmod decay
// returnbase_lr ( 1/(1 + exp(-gamma * (iter - stepsize))))
//
// where base_lr, max_iter, gamma, step, stepvalue and power are defined
// in the solver parameter protocol buffer, and iter is the current iteration.
optional string lr_policy = 8;
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. //动量值?
optional float weight_decay = 12; // The weight decay. //权重衰减
// regularization types supported: L1 and L2
// controlled by weight_decay
//正则化方式支持:L1 和 L2
//由权值衰减变量控制
optional string regularization_type = 29 [default = "L2"]; //默认正则化方式为L2
// the stepsize for learning rate policy "step"
optional int32 stepsize = 13;
// the stepsize for learning rate policy "multistep"
repeated int32 stepvalue = 34;
// Set clip_gradients to >= 0 to clip parameter gradients to that L2 norm,
// whenever their actual L2 norm is larger.
// 设置
clip_gradients
大于零,只要它比实际的L2范数大,那么它就等于L2范数
optional float clip_gradients = 35 [default = -1];
optional int32 snapshot = 14 [default = 0]; // The snapshot interval //snapshot:快照
optional string snapshot_prefix = 15; // The prefix for the snapshot. //prefix:字首
// whether to snapshot diff in the results or not. Snapshotting diff will help
// debugging but the final protocol buffer size will be much larger.
// 无论快照在结果中有无差值,快照的差值将会有助于调试,但是最终的protocol buffer的尺寸会大很多
//
optional bool snapshot_diff = 16 [default = false];
enum SnapshotFormat {
HDF5 = 0;
BINARYPROTO = 1;
}
optional SnapshotFormat snapshot_format = 37 [default = BINARYPROTO];
// 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];
// type of the solver
//求解器的类型 默认类型为SGD
optional string type = 40 [default = "SGD"]; //string 类型
// numerical stability for RMSProp, AdaGrad and AdaDelta and Adam
// 对于
RMSProp, AdaGrad and AdaDelta and Adam的数值稳定性默认阈值为 1e-8
optional float delta = 31 [default = 1e-8];
// parameters for the Adam solver
// 自适应动量求解器的衰减的默认取值为0.999
optional float momentum2 = 39 [default = 0.999];
// RMSProp decay value
// RMSProp的衰减值
// MeanSquare(t) = rms_decay*MeanSquare(t-1) + (1-rms_decay)*SquareGradient(t)
// 均方差的迭代求解关系
// MeanSquare(t) = rms_decay*MeanSquare(t-1) + (1-rms_decay)*SquareGradient(t)
optional float rms_decay = 38;
// If true, print information about the state of the net that may help with
// debugging learning problems.
// 是否打印调试信息,默认设置为否
optional bool debug_info = 23 [default = false];
// If false, don't save a snapshot after training finishes.
//如何设置为否,则不保存每次训练结束后的快照
optional bool snapshot_after_train = 28 [default = true];
// DEPRECATED: old solver enum types, use string instead
//舍弃旧的求解器枚举类型,使用string代替
enum SolverType {
SGD = 0;
NESTEROV = 1;
ADAGRAD = 2;
RMSPROP = 3;
ADADELTA = 4;
ADAM = 5;
}
// DEPRECATED: use type instead of solver_type
// 舍弃solver_type, 改用 type
optional SolverType solver_type = 30 [default = SGD];
}
// A message that stores the solver snapshots
message SolverState {
optional int32 iter = 1; // The current iteration //当前迭代
optional string learned_net = 2; // The file that stores the learned net. //保存学习网络的文件
repeated BlobProto history = 3; // The history for sgd solvers //sgd求解器的历史记录
optional int32 current_step = 4 [default = 0]; // The current step for learning rate //当前学习率的步进
}
//状态枚举:训练或者测试
enum Phase {
TRAIN = 0;
TEST = 1;
}
//网络状态
message NetState {
optional Phase phase = 1 [default = TEST];
optional int32 level = 2 [default = 0];
repeated string stage = 3;
}
//Rule网络状态
message NetStateRule {
// Set phase to require the NetState have a particular phase (TRAIN or TEST)
// to meet this rule.
optional Phase phase = 1;
// Set the minimum and/or maximum levels in which the layer should be used.
// Leave undefined to meet the rule regardless of level.
//设置Rule层需使用的最大与/或最小层,其他未定义的层需满足rule规则。
optional int32 min_level = 2;
optional int32 max_level = 3;
// Customizable sets of stages to include or exclude.
//包含或排除用户自定义集的状态
// The net must have ALL of the specified stages and NONE of the specified
// "not_stage"s to meet the rule.
//网络必须含有所有具体的状态,使用多层网络Rlue用于连接特定状态
// (Use multiple NetStateRules to specify conjunctions of stages.)
repeated string stage = 4;
repeated string not_stage = 5;
}
// Specifies training parameters (multipliers on global learning constants,
// and the name and other settings used for weight sharing).
// 指定训练参数(多层网络的全局学习常数,以及用于权重分配的名称和其他设置)。
message ParamSpec {
// The names of the parameter blobs -- useful for sharing parameters among
// layers, but never required otherwise. To share a parameter between two
// layers, give it a (non-empty) name.
//
blobs参数的名称-用于在图层之间共享参数,但从不需要。为了共享一个参数给两层网络,给它一个名字
optional string name = 1;
// Whether to require shared weights to have the same shape, or just the same
// count -- defaults to STRICT if unspecified.
// 无论是为了相同的shape而共享权值,或者仅仅只是计数。默认情况下如果未指定则为STRICT(限制)
//
optional DimCheckMode share_mode = 2;
enum DimCheckMode {
// STRICT (default) requires thatnum, channels, height, width each match.
//
STRICT 限制 (默认)
num, channels, height, width
为shape的四个参数,对应一一匹配
STRICT = 0;
// PERMISSIVE requires only the count (num*channels*height*width) to match.
//
PERMISSIVE 允许 仅需要
num*channels*height*width的数相同即可
PERMISSIVE = 1;
}
// The multiplier on the global learning rate for this parameter.
//该参数在全局上的学习率的乘数
optional float lr_mult = 3 [default = 1.0];
// The multiplier on the global weight decay for this parameter.
// 该参数在全局上的权值衰减的乘数
optional float decay_mult = 4 [default = 1.0];
}
// NOTE
// Update the next available ID when you add a new LayerParameter field.
//注意
//当你增加新的网络参数字段时,更新新的可用ID
// LayerParameter next available layer-specific ID: 143 (last added: scale_param)
// 新的可用字段号为143
message LayerParameter {
optional string name = 1; // the layer name
optional string type = 2; // the layer type
repeated string bottom = 3; // the name of each bottom blob
repeated string top = 4; // the name of each top blob
// The train / test phase for computation.
optional Phase phase = 10;
// The amount of weight to assign each top blob in the objective.
// Each layer assigns a default value, usually of either 0 or 1,
// to each top blob.
// 在目标中分配每个顶部blob的权重量。每个图层为每个顶部blob分配一个默认值,通常为0或1。
repeated float loss_weight = 5;
// Specifies training parameters (multipliers on global learning constants,
// and the name and other settings used for weight sharing).
// 指定训练参数(全局学习常数的乘数,以及用于权值共享的名称和其他设置)。
repeated ParamSpec param = 6;
// The blobs containing the numeric parameters of the layer.
// blob包含层的数值参数。
repeated BlobProto blobs = 7;
// Specifies on which bottoms the backpropagation should be skipped.
//反向传播中
指定应该跳过哪些
bottoms
// The size must be either 0 or equal to the number of bottoms.
//
大小为0或者等于
bottoms的个数
repeated bool propagate_down = 11;
// Rules controlling whether and when a layer is included in the network,
// based on the current NetState. You may specify a non-zero number of rules
// to include OR exclude, but not both. If no include or exclude rules are
// specified, the layer is always included. If the current NetState meets
// ANY (i.e., one or more) of the specified rules, the layer is
// included/excluded.
// Rules 基于当前的网络状态控制该层是否包含在网络中,您可以指定非零数量的规则以包括或排除,但不能同时包含两者。
// 如果未指定包含或排除规则,则始终包括该层。如果当前网络状态满足指定规则中的任意(即一个或多个),则包括/排除该层。
repeated NetStateRule include = 8;
repeated NetStateRule exclude = 9;
// Parameters for data pre-processing.
// 数据预处理的参数
optional TransformationParameter transform_param = 100;
// Parameters shared by loss layers.
// 损耗层共享的参数。
optional LossParameter loss_param = 101;
// Layer type-specific parameters.
// 层的各种具体类型的参数
// Note: certain layers may have more than one computational engine
// for their implementation. These layers include an Engine type and
// engine parameter for selecting the implementation.
// The default for the engine is set by the ENGINE switch at compile-time.
// 注意:某些图层可能有多个计算引擎用于实现。
// 这些层包括用于选择实现的引擎类型和引擎参数。
// 引擎的默认值由编译时的ENGINE开关设置。
optional AccuracyParameter accuracy_param = 102;//准确率
optional ArgMaxParameter argmax_param = 103;//极大值
optional BatchNormParameter batch_norm_param = 139;//块归一化
optional BiasParameter bias_param = 141;//偏置
optional ConcatParameter concat_param = 104;//连续
optional ContrastiveLossParameter contrastive_loss_param = 105;//对比损失
optional ConvolutionParameter convolution_param = 106;//卷积
optional DataParameter data_param = 107;//数据
optional DropoutParameter dropout_param = 108;//退出
optional DummyDataParameter dummy_data_param = 109;// 填充数据
optional EltwiseParameter eltwise_param = 110;//
eltwise
optional ELUParameter elu_param = 140;//elu
optional EmbedParameter embed_param = 137;//嵌入
optional ExpParameter exp_param = 111;
optional FlattenParameter flatten_param = 135;
optional HDF5DataParameter hdf5_data_param = 112;
//hdf5 数据参数
optional HDF5OutputParameter hdf5_output_param = 113;
//hdf5 数据输出参数
optional HingeLossParameter hinge_loss_param = 114;//合并损失
optional ImageDataParameter image_data_param = 115;//图像数据
optional InfogainLossParameter infogain_loss_param = 116;//信息获取?infogain
optional InnerProductParameter inner_product_param = 117;//内部参数
optional LogParameter log_param = 134;//对数参数
optional LRNParameter lrn_param = 118;//逻辑回归参数?
optional MemoryDataParameter memory_data_param = 119;//内存数据?
optional MVNParameter mvn_param = 120;//mvn?
optional PoolingParameter pooling_param = 121;池化参数
optional PowerParameter power_param = 122;//能量参数
optional PReLUParameter prelu_param = 131;//预Relu参数
optional PythonParameter python_param = 130;//python参数
optional ReductionParameter reduction_param = 136;//减少参数
optional ReLUParameter relu_param = 123;//relu
optional ReshapeParameter reshape_param = 133;//更改形状
optional ROIPoolingParameter roi_pooling_param = 8266711;//感兴趣区域池化参数
optional ScaleParameter scale_param = 142;//尺度化参数
optional SigmoidParameter sigmoid_param = 124;//simgmoid参数
optional SmoothL1LossParameter smooth_l1_loss_param = 8266712;//平滑l1损失参数
optional SoftmaxParameter softmax_param = 125;//softmax参数
optional SPPParameter spp_param = 132;//SPP参数
optional SliceParameter slice_param = 126;//切片参数
optional TanHParameter tanh_param = 127;//反正切参数
optional ThresholdParameter threshold_param = 128;//阈值参数
optional TileParameter tile_param = 138;tile参数
optional WindowDataParameter window_data_param = 129;//数据窗参数
}
// Message that stores parameters used to apply transformation
// to the data layer's data
// 存储将数据转换应用到数据层的消息结构
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.
// 如果使用数据预处理,我们可以做一些简单的尺度化和
对数据均值的
减法。
// 注意,减法操作在尺度化操作之前
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
// 不能同时制定
mean_file 和
mean_value
optional string mean_file = 4;
// if specified can be repeated once (would substract it from all the channels)
// or can be repeated the same number of times as channels
// (would subtract them from the corresponding channel)
//
强如果制定可以重复一次(从所有信道中减去它)
//
或者每个信道单独减去它们
repeated float mean_value = 5;
// Force the decoded image to have 3 color channels.
// 强制解码成三通道
颜色
optional bool force_color = 6 [default = false];
// Force the decoded image to have 1 color channels.
// 强制解码成单通道颜色
optional bool force_gray = 7 [default = false];
}
// Message that stores parameters shared by loss layers
// 存储有损耗层共享的消息结构
message LossParameter {
// If specified, ignore instances with the given label.
// 如果指定,忽略给定标签的实例
optional int32 ignore_label = 1;
// How to normalize the loss for loss layers that aggregate across batches,
// spatial dimensions, or other dimensions. Currently only implemented in
// SoftmaxWithLoss layer.
// 如何归一化在不同批次之间聚合的损失层的损失,空间尺寸或其他尺寸。
// 目前仅实现了SoftmaxWithLoss层
enum NormalizationMode {
// Divide by the number of examples in the batch times spatial dimensions.
// Outputs that receive the ignore label will NOT be ignored in computing
// the normalization factor.
// 除以例子中批次时域尺寸的数目
// 接受的输出中忽略的标签将会考虑在计算归一化因子的过程中
FULL = 0;
// Divide by the total number of output locations that do not take the
// ignore_label. If ignore_label is not set, this behaves like FULL.
// 除以未采用ignore_label的输出位置的总数。 如果未设置ignore_label,则其行为类似于FULL。
VALID = 1;
// Divide by the batch size.
// 除以批尺寸
BATCH_SIZE = 2;
// Do not normalize the loss.
// 不归一化
NONE = 3;
}
optional NormalizationMode normalization = 3 [default = VALID];
// Deprecated. Ignored if normalization is specified. If normalization
// is not specified, then setting this to false will be equivalent to
// normalization = BATCH_SIZE to be consistent with previous behavior.
// 已弃用。 如果指定了归一化,则忽略。 如果未指定规范化,则将其设置为false,
// 将等同于规范化= BATCH_SIZE,以与以前的行为一致。
optional bool normalize = 2;
}
// Messages that store parameters used by individual layer types follow, in
// alphabetical order.
message AccuracyParameter {
// When computing accuracy, count as correct by comparing the true label to
// the top k scoring classes. By default, only compare to the top scoring
// class (i.e. argmax).
// 当计算准确性时,通过将真实标签与前k个评分类进行比较来计算为正确。
// 默认情况下,只比较顶级评分类(即argmax)。
optional uint32 top_k = 1 [default = 1];
// The "label" axis of the prediction blob, whose argmax corresponds to the
// predicted label -- may be negative to index from the end (e.g., -1 for the
// last axis). For example, if axis == 1 and the predictions are
// (N x C x H x W), the label blob is expected to contain N*H*W ground truth
// labels with integer values in {0, 1, ..., C-1}.
// 预测斑点的“标签”轴(其argmax对应于预测标签)可以从末端开始索引(例如,对于最后一个轴为-1)。
// 例如,如果axis == 1并且预测是(N×C×H×W),则期望标签blob包含具有{0,1,...,N}中的整数值的N * C-1}。
optional int32 axis = 2 [default = 1];
// If specified, ignore instances with the given label.
// 如果指定,忽略给定标签的实例
optional int32 ignore_label = 3;
}
message ArgMaxParameter {
// If true produce pairs (argmax, maxval)
// 如果为真,产生
(argmax, maxval)数据对,默认为假
optional bool out_max_val = 1 [default = false];
optional uint32 top_k = 2 [default = 1];
// The axis along which to maximise -- may be negative to index from the
// end (e.g., -1 for the last axis).
// 沿其最大化的轴可以对从末端开始的索引为负(例如,对于最后一个轴为-1)。
// By default ArgMaxLayer maximizes over the flattened trailing dimensions
// for each index of the first / num dimension.
// 默认情况下,ArgMaxLayer最大化第一个/num维度的每个索引的展平拖尾尺寸。
optional int32 axis = 3;
}
message ConcatParameter {
// The axis along which to concatenate -- may be negative to index from the
// end (e.g., -1 for the last axis). Other axes must have the
// same dimension for all the bottom blobs.
// By default, ConcatLayer concatenates blobs along the "channels" axis (1).
// 沿着其连接的轴 - 可以从末尾开始索引(例如,对于最后一个轴为-1)。 其他轴必须有
// 相同尺寸的所有底部斑点。
// 默认情况下,ConcatLayer沿着“通道”轴
(1)
连接blob。
optional int32 axis = 2 [default = 1];
// DEPRECATED: alias for "axis" -- does not support negative indexing.
// DEPRECATED:“axis”的别名 - 不支持负索引。
optional uint32 concat_dim = 1 [default = 1];
}
message BatchNormParameter {
// If false, accumulate global mean/variance values via a moving average. If
// true, use those accumulated values instead of computing mean/variance
// across the batch.
// 如果为假,则通过移动平均值累积全局均值/方差值。
// 如果为真,请使用这些累计值,而不是计算整个批次的均值/方差。
optional bool use_global_stats = 1;
// How much does the moving average decay each iteration?
//
每次迭代
移动平均值衰减有多少?
optional float moving_average_fraction = 2 [default = .999];
// Small value to add to the variance estimate so that we don't divide by
// zero.
// 防止除0
optional float eps = 3 [default = 1e-5];
}
message BiasParameter {
// The first axis of bottom[0] (the first input Blob) along which to apply
// bottom[1] (the second input Blob). May be negative to index from the end
// (e.g., -1 for the last axis).
//
// 底部[0]的第一个轴(第一个输入Blob),沿着它应用底部[1](第二个输入Blob)。
// 可以从末尾开始索引(例如,对于最后一个轴为-1)。
// For example, if bottom[0] is 4D with shape 100x3x40x60, the output
// top[0] will have the same shape, and bottom[1] may have any of the
// following shapes (for the given value of axis):
// 例如,如果底部[0]是具有形状100x3x40x60的4D,则为输出
// 顶部[0]将具有相同的形状,底部[1]可具有任何的
// 以下形状(对于给定的轴值):
// (axis == 0 == -4) 100; 100x3; 100x3x40; 100x3x40x60
// (axis == 1 == -3) 3; 3x40; 3x40x60
// (axis == 2 == -2) 40; 40x60
// (axis == 3 == -1) 60
// Furthermore, bottom[1] may have the empty shape (regardless of the value of
// "axis") -- a scalar bias.
// 此外,底部[1]可以具有空形状(不管“轴”的值) - 标量偏差。
optional int32 axis = 1 [default = 1];
// (num_axes is ignored unless just one bottom is given and the bias is
// a learned parameter of the layer. Otherwise, num_axes is determined by the
// number of axes by the second bottom.)
// (忽略num_axes,除非给定一个底部,偏差是层的学习参数,否则num_axes由第二个底部的轴数确定)。
// The number of axes of the input (bottom[0]) covered by the bias
// parameter, or -1 to cover all axes of bottom[0] starting from `axis`.
// Set num_axes := 0, to add a zero-axis Blob: a scalar.
// 由偏置参数覆盖的输入(底部[0])的轴数,或从“轴”开始覆盖底部[0]的所有轴的-1。
// 设置num_axes:= 0,以添加零轴Blob:标量。
optional int32 num_axes = 2 [default = 1];
// (filler is ignored unless just one bottom is given and the bias is
// a learned parameter of the layer.)
// The initialization for the learned bias parameter.
// Default is the zero (0) initialization, resulting in the BiasLayer
// initially performing the identity operation.
// (填充被忽略,除非只给出一个底部,并且偏置是层的学习参数)。
// 学习的偏置参数的初始化。
// 默认是零(0)初始化,导致偏置层初始化执行识别操作。
optional FillerParameter filler = 3;
}
限于能力有限,代码注释中定有错误和纰漏,望大家指正,后续持续修改ing......