package caffe

Get desktop application:
View/edit binary Protocol Buffers messages

Message that stores parameters used by AccuracyLayer

Used in: LayerParameter

• optional uint32 top_k = 1

  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).

Message that stores parameters used by ArgMaxLayer

Used in: LayerParameter

• optional bool out_max_val = 1

  If true produce pairs (argmax, maxval)

• optional uint32 top_k = 2

Message that stores parameters used by BNLayer

Used in: LayerParameter

• optional FillerParameter scale_filler = 1

  The filler for the scale

• optional FillerParameter shift_filler = 2

  The filler for the shift

• optional float var_eps = 3

  The epsilon added to variance

• optional bool moving_average = 4

  whether or not using moving average for inference

• optional float decay = 5

  The decay factor for moving average

Used in: BlobProtoVector, LayerParameter, SolverState, V0LayerParameter

• optional int32 num = 1

• optional int32 channels = 2

• optional int32 height = 3

• optional int32 width = 4

• repeated float data = 5

• repeated float diff = 6

The BlobProtoVector is simply a way to pass multiple blobproto instances around.

• repeated BlobProto blobs = 1

Message that stores parameters used by ConcatLayer

Used in: LayerParameter

• optional uint32 concat_dim = 1

  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

Message that stores parameters used by ConvolutionLayer

Used in: LayerParameter

• optional uint32 num_output = 1

  The number of outputs for the layer

• optional bool bias_term = 2

  whether to have bias terms

• optional uint32 pad = 3

  Pad, kernel size, and stride are all given as a single value for equal dimensions in height and width or as Y, X pairs.

  The padding size (equal in Y, X)

• optional uint32 pad_h = 9

  The padding height

• optional uint32 pad_w = 10

  The padding width

• optional uint32 kernel_size = 4

  The kernel size (square)

• optional uint32 kernel_h = 11

  The kernel height

• optional uint32 kernel_w = 12

  The kernel width

• optional uint32 group = 5

  The group size for group conv

• optional uint32 stride = 6

  The stride (equal in Y, X)

• optional uint32 stride_h = 13

  The stride height

• optional uint32 stride_w = 14

  The stride width

• optional FillerParameter weight_filler = 7

  The filler for the weight

• optional FillerParameter bias_filler = 8

  The filler for the bias

• optional ConvolutionParameter.Engine engine = 15

Used in: ConvolutionParameter

• DEFAULT = 0

• CAFFE = 1

• CUDNN = 2

Message that stores parameters used by DataLayer

Used in: LayerParameter

• optional string source = 1

  Specify the data source.

• optional uint32 batch_size = 4

  Specify the batch size.

• optional uint32 rand_skip = 7

  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 DataParameter.DB backend = 8

• optional float scale = 2

  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 string mean_file = 3

• optional uint32 crop_size = 5

  DEPRECATED. See TransformationParameter. Specify if we would like to randomly crop an image.

• optional bool mirror = 6

  DEPRECATED. See TransformationParameter. Specify if we want to randomly mirror data.

Used in: DataParameter

• LEVELDB = 0

• LMDB = 1

• optional int32 channels = 1

• optional int32 height = 2

• optional int32 width = 3

• optional bytes data = 4

  the actual image data, in bytes

• optional int32 label = 5

• repeated float float_data = 6

  Optionally, the datum could also hold float data.

Message that stores parameters used by DropoutLayer

Used in: LayerParameter

• optional float dropout_ratio = 1

  dropout ratio

Message that stores parameters used by DummyDataLayer. DummyDataLayer fills any number of arbitrarily shaped blobs with random (or constant) data generated by "Fillers" (see "message FillerParameter").

Used in: LayerParameter

• repeated FillerParameter data_filler = 1

  This layer produces N >= 1 top blobs. DummyDataParameter must specify 1 or N num, N channels, N height, and N width fields, and must specify 0, 1 or N data_fillers. If 0 data_fillers are specified, ConstantFiller with a value of 0 is used. If 1 data_filler is specified, it is applied to all top blobs. If N are specified, the ith is applied to the ith top blob.

• repeated uint32 num = 2

• repeated uint32 channels = 3

• repeated uint32 height = 4

• repeated uint32 width = 5

Message that stores parameters used by EltwiseLayer

Used in: LayerParameter

• optional EltwiseParameter.EltwiseOp operation = 1

  element-wise operation

• repeated float coeff = 2

  blob-wise coefficient for SUM operation

• optional bool stable_prod_grad = 3

  Whether to use an asymptotically slower (for >2 inputs) but stabler method of computing the gradient for the PROD operation. (No effect for SUM op.)

Used in: EltwiseParameter

• PROD = 0

• SUM = 1

• MAX = 2

Used in: BNParameter, ConvolutionParameter, DummyDataParameter, InnerProductParameter, V0LayerParameter

• optional string type = 1

  The filler type.

• optional float value = 2

  the value in constant filler

• optional float min = 3

  the min value in uniform filler

• optional float max = 4

  the max value in uniform filler

• optional float mean = 5

  the mean value in Gaussian filler

• optional float std = 6

  the std value in Gaussian filler

• optional int32 sparse = 7

  The expected number of non-zero input weights for a given output in Gaussian filler -- the default -1 means don't perform sparsification.

• optional float negative_slope = 8

  the negative slope of the leaky relu attached to the previous activation

• optional FillerParameter.VarianceNorm variance_norm = 9

• optional FillerParameter.LayerType layer_type = 10

• optional string source = 11

Applies to xavier and relu fillers.

Used in: FillerParameter

• CONVOLUTION = 0

• INNER_PRODUCT = 1

Normalize the filler variance by fan_in, fan_out, or their average. Applies to xavier and relu fillers.

Used in: FillerParameter

• FAN_IN = 0

• FAN_OUT = 1

• AVERAGE = 2

Message that stores parameters used by HDF5DataLayer

Used in: LayerParameter

• optional string source = 1

  Specify the data source.

• optional uint32 batch_size = 2

  Specify the batch size.

Message that stores parameters used by HDF5OutputLayer

Used in: LayerParameter, V0LayerParameter

• optional string file_name = 1

Used in: LayerParameter

• optional HingeLossParameter.Norm norm = 1

  Specify the Norm to use L1 or L2

Used in: HingeLossParameter

• L1 = 1

• L2 = 2

Message that stores parameters used by ImageDataLayer

Used in: LayerParameter

• optional string source = 1

  Specify the data source.

• optional uint32 batch_size = 4

  Specify the batch size.

• optional uint32 rand_skip = 7

  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 bool shuffle = 8

  Whether or not ImageLayer should shuffle the list of files at every epoch.

• optional uint32 new_height = 9

  It will also resize images if new_height or new_width are not zero.

• optional uint32 new_width = 10

• optional float scale = 2

  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 string mean_file = 3

• optional uint32 crop_size = 5

  DEPRECATED. See TransformationParameter. Specify if we would like to randomly crop an image.

• optional bool mirror = 6

  DEPRECATED. See TransformationParameter. Specify if we want to randomly mirror data.

Message that stores parameters InfogainLossLayer

Used in: LayerParameter

• optional string source = 1

  Specify the infogain matrix source.

Message that stores parameters used by InnerProductLayer

Used in: LayerParameter

• optional uint32 num_output = 1

  The number of outputs for the layer

• optional bool bias_term = 2

  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

Used in: LayerParameter

• optional uint32 local_size = 1

• optional float alpha = 2

• optional float beta = 3

• optional LRNParameter.NormRegion norm_region = 4

Used in: LRNParameter

• ACROSS_CHANNELS = 0

• WITHIN_CHANNEL = 1

NOTE Update the next available ID when you add a new LayerParameter field. LayerParameter next available ID: 40 (last added: softmax_param)

Used in: NetParameter, NetParameterPrettyPrint

• 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

• repeated NetStateRule include = 32

  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.

• repeated NetStateRule exclude = 33

• optional LayerParameter.LayerType type = 5

  the layer type from the enum above

• repeated BlobProto blobs = 6

  The blobs containing the numeric parameters of the layer

• repeated string param = 1001

  The names of the parameter blobs -- useful for sharing parameters among layers (but never required).

• repeated LayerParameter.DimCheckMode blob_share_mode = 1002

  Whether to require shared weights to have the same shape, or just the same count -- defaults to STRICT if unspecified.

• repeated float blobs_lr = 7

  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 weight_decay = 8

  The weight decay that is multiplied on the global weight decay.

• repeated float loss_weight = 35

  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.

• optional AccuracyParameter accuracy_param = 27

• optional ArgMaxParameter argmax_param = 23

• optional BNParameter bn_param = 41

• optional ConcatParameter concat_param = 9

• optional ConvolutionParameter convolution_param = 10

• optional DataParameter data_param = 11

• optional DropoutParameter dropout_param = 12

• optional DummyDataParameter dummy_data_param = 26

• optional EltwiseParameter eltwise_param = 24

• optional HDF5DataParameter hdf5_data_param = 13

• optional HDF5OutputParameter hdf5_output_param = 14

• optional HingeLossParameter hinge_loss_param = 29

• 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 MVNParameter mvn_param = 34

• optional PoolingParameter pooling_param = 19

• optional PowerParameter power_param = 21

• optional PReLUParameter prelu_param = 40

• optional ReLUParameter relu_param = 30

• optional SigmoidParameter sigmoid_param = 38

• optional SoftmaxParameter softmax_param = 39

• optional SliceParameter slice_param = 31

• optional TanHParameter tanh_param = 37

• optional ThresholdParameter threshold_param = 25

• optional WindowDataParameter window_data_param = 20

• optional TransformationParameter transform_param = 36

  Parameters for data pre-processing.

• optional V0LayerParameter layer = 1

  DEPRECATED: The layer parameters specified as a V0LayerParameter. This should never be used by any code except to upgrade to the new LayerParameter specification.

Used in: LayerParameter

• STRICT = 0

  STRICT (default) requires that num, channels, height, width each match.

• PERMISSIVE = 1

  PERMISSIVE requires only the count (num*channels*height*width) to match.

NOTE 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: 40 (last added: BN)

Used in: LayerParameter

• NONE = 0

  "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).

• ABSVAL = 35

• ACCURACY = 1

• ARGMAX = 30

• BN = 39

• BNLL = 2

• CONCAT = 3

• COMPACT_DATA = 37

• CONVOLUTION = 4

• DATA = 5

• DROPOUT = 6

• DUMMY_DATA = 32

• EUCLIDEAN_LOSS = 7

• ELTWISE = 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

• MVN = 34

• POOLING = 17

• POWER = 26

• PRELU = 38

• RELU = 18

• SIGMOID = 19

• SIGMOID_CROSS_ENTROPY_LOSS = 27

• SILENCE = 36

• SOFTMAX = 20

• SOFTMAX_LOSS = 21

• SPLIT = 22

• SLICE = 33

• TANH = 23

• WINDOW_DATA = 24

• THRESHOLD = 31

Message that stores parameters used by MVNLayer

Used in: LayerParameter

• optional bool normalize_variance = 1

  This parameter can be set to false to normalize mean only

• optional bool across_channels = 2

  This parameter can be set to true to perform DNN-like MVN

Message that stores parameters used by MemoryDataLayer

Used in: LayerParameter

• optional uint32 batch_size = 1

• optional uint32 channels = 2

• optional uint32 height = 3

• optional uint32 width = 4

Used in: SolverParameter

• optional string name = 1

  consider giving the network a name

• repeated LayerParameter layers = 2

  a bunch of layers.

• repeated string input = 3

  The input blobs to the network.

• repeated int32 input_dim = 4

  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.

• optional bool force_backward = 5

  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 NetState state = 6

  The current "state" of the network, including the phase, level, and stage. Some layers may be included/excluded depending on this state and the states specified in the layers' include and exclude fields.

A near-duplicate of NetParameter with fields re-numbered to beautify automatic prototext dumps. The main practical purpose is to print inputs before layers, because having inputs at the end looks weird. NetParameterPrettyPrint should never be used in code except for conversion FROM NetParameter and subsequent dumping to proto text file.

• optional string name = 1

• optional bool force_backward = 2

• repeated string input = 3

• repeated int32 input_dim = 4

• repeated LayerParameter layers = 5

Used in: NetParameter, SolverParameter

• optional Phase phase = 1

• optional int32 level = 2

• repeated string stage = 3

Used in: LayerParameter

• optional Phase phase = 1

  Set phase to require the NetState have a particular phase (TRAIN or TEST) to meet this rule.

• optional int32 min_level = 2

  Set the minimum and/or maximum levels in which the layer should be used. Leave undefined to meet the rule regardless of level.

• optional int32 max_level = 3

• repeated string stage = 4

  Customizable sets of stages to include or exclude. The net must have ALL of the specified stages and NONE of the specified "not_stage"s to meet the rule. (Use multiple NetStateRules to specify conjunctions of stages.)

• repeated string not_stage = 5

Message that stores parameters used by PReLULayer

Parametric ReLU described in K. He et al, Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification, 2015.

Used in: LayerParameter

• optional float init_value = 1

  Initial value of a_i. Set as a_i=init_value for all channel i.

• optional bool channel_shared = 2

  Whether or not slope paramters are shared across channels.

Used in: NetState, NetStateRule

• TRAIN = 0

• TEST = 1

Message that stores parameters used by PoolingLayer

Used in: LayerParameter

• optional PoolingParameter.PoolMethod pool = 1

  The pooling method

• optional uint32 pad = 4

  Pad, kernel size, and stride are all given as a single value for equal dimensions in height and width or as Y, X pairs.

  The padding size (equal in Y, X)

• optional uint32 pad_h = 9

  The padding height

• optional uint32 pad_w = 10

  The padding width

• optional uint32 kernel_size = 2

  The kernel size (square)

• optional uint32 kernel_h = 5

  The kernel height

• optional uint32 kernel_w = 6

  The kernel width

• optional uint32 stride = 3

  The stride (equal in Y, X)

• optional uint32 stride_h = 7

  The stride height

• optional uint32 stride_w = 8

  The stride width

• optional PoolingParameter.Engine engine = 11

Used in: PoolingParameter

• DEFAULT = 0

• CAFFE = 1

• CUDNN = 2

Used in: PoolingParameter

• MAX = 0

• AVE = 1

• STOCHASTIC = 2

Message that stores parameters used by PowerLayer

Used in: LayerParameter

• optional float power = 1

  PowerLayer computes outputs y = (shift + scale * x) ^ power.

• optional float scale = 2

• optional float shift = 3

Message that stores parameters used by ReLULayer

Used in: LayerParameter

• optional float negative_slope = 1

  Allow non-zero slope for negative inputs to speed up optimization Described in: Maas, A. L., Hannun, A. Y., & Ng, A. Y. (2013). Rectifier nonlinearities improve neural network acoustic models. In ICML Workshop on Deep Learning for Audio, Speech, and Language Processing.

• optional ReLUParameter.Engine engine = 2

Used in: ReLUParameter

• DEFAULT = 0

• CAFFE = 1

• CUDNN = 2

Message that stores parameters used by SigmoidLayer

Used in: LayerParameter

• optional SigmoidParameter.Engine engine = 1

Used in: SigmoidParameter

• DEFAULT = 0

• CAFFE = 1

• CUDNN = 2

Message that stores parameters used by SliceLayer

Used in: LayerParameter

• optional uint32 slice_dim = 1

  SliceLayer needs to know which dimension to slice across. Currently, SliceLayer only supports slicing across num (dim 0) and channels (dim 1). By default, SliceLayer slices across channels.

• repeated uint32 slice_point = 2

Message that stores parameters used by SoftmaxLayer, SoftMaxWithLossLayer

Used in: LayerParameter

• optional SoftmaxParameter.Engine engine = 1

Used in: SoftmaxParameter

• DEFAULT = 0

• CAFFE = 1

• CUDNN = 2

NOTE Update the next available ID when you add a new SolverParameter field. SolverParameter next available ID: 36 (last added: rms_decay)

//////////////////////////////////////////////////////////////////////////// Specifying the train and test networks Exactly one train net must be specified using one of the following fields: train_net_param, train_net, net_param, net One or more test 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. A test_iter must be specified for each test_net. A test_level and/or a test_stage may also be specified for each test_net. ////////////////////////////////////////////////////////////////////////////

• optional string net = 24

  Proto filename for the train net, possibly combined with one or more test nets.

• optional NetParameter net_param = 25

  Inline train net param, possibly combined with one or more test nets.

• 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.

• optional NetState train_state = 26

  The states for the train/test nets. Must be unspecified or specified once per net. 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.

• repeated NetState test_state = 27

• repeated int32 test_iter = 3

  The number of iterations for each test net.

• optional int32 test_interval = 4

  The number of iterations between two testing phases.

• optional bool test_compute_loss = 19

• optional bool test_initialization = 32

  If true, run an initial test pass before the first iteration, ensuring memory availability and printing the starting value of the loss.

• optional float base_lr = 5

  The base learning rate

• optional int32 display = 6

  the number of iterations between displaying info. If display = 0, no info will be displayed.

• optional int32 average_loss = 34

  Display the cost averaged over the last average_cost iterations

• 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 string regularization_type = 29

  regularization types supported: L1 and L2 controled by weight_decay

• optional int32 stepsize = 13

  the stepsize for learning rate policy "step"

• optional int32 snapshot = 14

  The snapshot interval

• optional string snapshot_prefix = 15

  The prefix for the snapshot.

• optional bool snapshot_diff = 16

  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 SolverParameter.SolverMode solver_mode = 17

• optional int32 device_id = 18

  the device_id will that be used in GPU mode. Use device_id = 0 in default.

• optional int64 random_seed = 20

  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 int32 update_interval = 33

  added to allow big batch_size

• optional SolverParameter.SolverType solver_type = 30

• optional float delta = 31

  numerical stability for AdaGrad

• optional float rms_decay = 35

  RMSprop decay value

• optional bool debug_info = 23

  If true, print information about the state of the net that may help with debugging learning problems.

• optional bool snapshot_after_train = 28

  If false, don't save a snapshot after training finishes.

the mode solver will use: 0 for CPU and 1 for GPU. Use GPU in default.

Used in: SolverParameter

• CPU = 0

• GPU = 1

Solver type

Used in: SolverParameter

• SGD = 0

• NESTEROV = 1

• ADAGRAD = 2

• ADADELTA = 3

• RMSPROP = 4

A message that stores the solver snapshots

• 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

Message that stores parameters used by SigmoidLayer

Used in: LayerParameter

• optional TanHParameter.Engine engine = 1

Used in: TanHParameter

• DEFAULT = 0

• CAFFE = 1

• CUDNN = 2

Message that stores parameters used by ThresholdLayer

Used in: LayerParameter

• optional float threshold = 1

  Strictly Positive values

Message that stores parameters used to apply transformation to the data layer's data

Used in: LayerParameter

• optional float scale = 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 bool mirror = 2

  Specify if we want to randomly mirror data.

• optional uint32 crop_size = 3

  Specify if we would like to randomly crop an image.

• optional string mean_file = 4

• optional bool multiscale = 5

• optional float min_scaling_factor = 6

  Specify the range of scaling factor for doing resizing

• optional float max_scaling_factor = 7

• optional float angle_interval = 8

  Specify the angle interval for doing rotation

• optional float max_shearing_ratio = 9

  Specify the shearing ratio

• optional float max_perspective_ratio = 10

  Specify the perspective ratio

• optional float warp_fillval = 11

  Specify the constant value we would like to fill with when doing affine transformation

• optional bool debug_display = 12

• optional bool contrast_adjustment = 13

• optional bool smooth_filtering = 14

• optional bool jpeg_compression = 15

DEPRECATED: V0LayerParameter is the old way of specifying layer parameters in Caffe. We keep this message type around for legacy support.

Used in: LayerParameter

• optional string name = 1

  the layer name

• optional string type = 2

  the string to specify the layer type

• optional uint32 num_output = 3

  Parameters to specify layers with inner products.

  The number of outputs for the layer

• optional bool biasterm = 4

  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

  The padding size

• optional uint32 kernelsize = 8

  The kernel size

• optional uint32 group = 9

  The group size for group conv

• optional uint32 stride = 10

  The stride

• optional V0LayerParameter.PoolMethod pool = 11

  The pooling method

• optional float dropout_ratio = 12

  dropout ratio

• optional uint32 local_size = 13

  for local response norm

• optional float alpha = 14

  for local response norm

• optional float beta = 15

  for local response norm

• optional string source = 16

  For data layers, specify the data source

• optional float scale = 17

  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 string meanfile = 18

• optional uint32 batchsize = 19

  For data layers, specify the batch size.

• optional uint32 cropsize = 20

  For data layers, specify if we would like to randomly crop an image.

• optional bool mirror = 21

  For data layers, specify if we want to randomly mirror data.

• repeated BlobProto blobs = 50

  The blobs containing the numeric parameters of the layer

• repeated float blobs_lr = 51

  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 weight_decay = 52

  The weight decay that is multiplied on the global weight decay.

• optional uint32 rand_skip = 53

  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 float det_fg_threshold = 54

  Fields related to detection (det_*) foreground (object) overlap threshold

• optional float det_bg_threshold = 55

  background (non-object) overlap threshold

• optional float det_fg_fraction = 56

  Fraction of batch that should be foreground objects

• optional uint32 det_context_pad = 58

  Amount of contextual padding to add around a window (used only by the window_data_layer)

• optional string det_crop_mode = 59

  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 int32 new_num = 60

  For ReshapeLayer, one needs to specify the new dimensions.

• optional int32 new_channels = 61

• optional int32 new_height = 62

• optional int32 new_width = 63

• optional bool shuffle_images = 64

  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 uint32 concat_dim = 65

  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 HDF5OutputParameter hdf5_output_param = 1001

Used in: V0LayerParameter

• MAX = 0

• AVE = 1

• STOCHASTIC = 2

Message that stores parameters used by WindowDataLayer

Used in: LayerParameter

• optional string source = 1

  Specify the data source.

• optional float scale = 2

  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 string mean_file = 3

• optional uint32 batch_size = 4

  Specify the batch size.

• optional uint32 crop_size = 5

  Specify if we would like to randomly crop an image.

• optional bool mirror = 6

  Specify if we want to randomly mirror data.

• optional float fg_threshold = 7

  Foreground (object) overlap threshold

• optional float bg_threshold = 8

  Background (non-object) overlap threshold

• optional float fg_fraction = 9

  Fraction of batch that should be foreground objects

• optional uint32 context_pad = 10

  Amount of contextual padding to add around a window (used only by the window_data_layer)

• optional string crop_mode = 11

  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