Project MhLiao/TextBoxes_plusplus

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).
optional int32 axis = 2
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}.
optional int32 ignore_label = 3
If specified, ignore instances with the given label.

Used in: LayerParameter

repeated BatchSampler batch_sampler = 1
Define the sampler.
optional string label_map_file = 2
Store label name and label id in LabelMap format.
optional AnnotatedDatum.AnnotationType anno_type = 3
If provided, it will replace the AnnotationType stored in each AnnotatedDatum.

An extension of Datum which contains "rich" annotations.

optional Datum datum = 1
optional AnnotatedDatum.AnnotationType type = 2
If there are "rich" annotations, specify the type of annotation. Currently it only supports bounding box. If there are no "rich" annotations, use label in datum instead.
repeated AnnotationGroup annotation_group = 3
Each group contains annotation for a particular class.

Used in: AnnotatedDataParameter, AnnotatedDatum

BBOX = 0

Annotation for each object instance.

Used in: AnnotationGroup

optional int32 instance_id = 1
optional NormalizedBBox bbox = 2
optional NormalizedRBox rbox = 3
optional NormalizedPolygon polygon = 4

Group of annotations for a particular label.

Used in: AnnotatedDatum

optional int32 group_label = 1
repeated Annotation annotation = 2

optional bool out_max_val = 1
If true produce pairs (argmax, maxval)
optional uint32 top_k = 2
optional int32 axis = 3
The axis along which to maximise -- may be negative to index from the end (e.g., -1 for the last axis). By default ArgMaxLayer maximizes over the flattened trailing dimensions for each index of the first / num dimension.

Used in: LayerParameter

optional bool use_global_stats = 1
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.
optional float moving_average_fraction = 2
How much does the moving average decay each iteration?
optional float eps = 3
Small value to add to the variance estimate so that we don't divide by zero.

Sample a batch of bboxes with provided constraints.

Used in: AnnotatedDataParameter

optional bool use_original_image = 1
Use original image as the source for sampling.
optional Sampler sampler = 2
Constraints for sampling bbox.
optional SampleConstraint sample_constraint = 3
Constraints for determining if a sampled bbox is positive or negative.
optional uint32 max_sample = 4
If provided, break when found certain number of samples satisfing the sample_constraint.
optional uint32 max_trials = 5
Maximum number of trials for sampling to avoid infinite loop.

Used in: LayerParameter

optional int32 axis = 1
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). 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): (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.
optional int32 num_axes = 2
(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.) 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.
optional FillerParameter filler = 3
(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.

Used in: BlobProtoVector, LayerParameter, SolverState, V0LayerParameter, V1LayerParameter

optional BlobShape shape = 7
repeated float data = 5
repeated float diff = 6
repeated double double_data = 8
repeated double double_diff = 9
optional int32 num = 1
4D dimensions -- deprecated. Use "shape" instead.
optional int32 channels = 2
optional int32 height = 3
optional int32 width = 4

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

repeated BlobProto blobs = 1

Specifies the shape (dimensions) of a Blob.

Used in: BlobProto, DummyDataParameter, InputParameter, NetParameter, ParameterParameter, ReshapeParameter

repeated int64 dim = 1

Used in: LayerParameter

optional int32 blank_index = 1
The index of the blank index in the labels. A negative (default) value will use the last index
optional bool ctc_merge_repeated = 2
Collapse the repeated labels during the ctc calculation e.g. collapse [0bbb11bb11bb0b2] to [01102] instead of [0111102], where b means blank label. The default behaviour is to merge repeated labels. Note: blank labels will be removed in any case.

Used in: LayerParameter

optional int32 output_delay = 1
Adds delayed output to the CTC loss calculation (untested!)
optional int32 blank_index = 2
The index of the blank index in the labels. A negative (default) value will use the last index
optional bool preprocess_collapse_repeated = 3
Collapse repeating labels of the target sequence before calculating the loss and the gradients (e.g. collapse [01102] to [0102]) The default behaviour is to keep repeated labels. Elsewise the network will not learn to predict repetitions.
optional bool ctc_merge_repeated = 4
Collapse the repeated labels during the ctc calculation e.g collapse [0bbb11bb11bb0b2] to [01102] instead of [0111102], where b means blank label. The default behaviour is to merge repeated labels. Note: blank labels will be removed in any case.
optional int32 loss_calculation_t = 5
/ This parameter is for test cases only! / The time for which to calculate the loss (see Graves Eq. (7.27) ) / Note that the result must be the same for each 0 <= t < T / Therefore you can chose an arbitrary value, default 0

optional int32 axis = 2
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).
optional uint32 concat_dim = 1
DEPRECATED: alias for "axis" -- does not support negative indexing.

optional float margin = 1
margin for dissimilar pair
optional bool legacy_version = 2
The first implementation of this cost did not exactly match the cost of Hadsell et al 2006 -- using (margin - d^2) instead of (margin - d)^2. legacy_version = false (the default) uses (margin - d)^2 as proposed in the Hadsell paper. New models should probably use this version. legacy_version = true uses (margin - d^2). This is kept to support / reproduce existing models and results

optional uint32 num_output = 1
The number of outputs for the layer
optional bool bias_term = 2
whether to have bias terms
repeated uint32 pad = 3
Pad, kernel size, and stride are all given as a single value for equal dimensions in all spatial dimensions, or once per spatial dimension.
The padding size; defaults to 0
repeated uint32 kernel_size = 4
The kernel size
repeated uint32 stride = 6
The stride; defaults to 1
repeated uint32 dilation = 18
Factor used to dilate the kernel, (implicitly) zero-filling the resulting holes. (Kernel dilation is sometimes referred to by its use in the algorithme à trous from Holschneider et al. 1987.)
The dilation; defaults to 1
optional uint32 pad_h = 9
For 2D convolution only, the *_h and *_w versions may also be used to specify both spatial dimensions.
The padding height (2D only)
optional uint32 pad_w = 10
The padding width (2D only)
optional uint32 kernel_h = 11
The kernel height (2D only)
optional uint32 kernel_w = 12
The kernel width (2D only)
optional uint32 stride_h = 13
The stride height (2D only)
optional uint32 stride_w = 14
The stride width (2D only)
optional uint32 group = 5
The group size for group conv
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
optional int32 axis = 16
The axis to interpret as "channels" when performing convolution. Preceding dimensions are treated as independent inputs; succeeding dimensions are treated as "spatial". With (N, C, H, W) inputs, and axis == 1 (the default), we perform N independent 2D convolutions, sliding C-channel (or (C/g)-channels, for groups g>1) filters across the spatial axes (H, W) of the input. With (N, C, D, H, W) inputs, and axis == 1, we perform N independent 3D convolutions, sliding (C/g)-channels filters across the spatial axes (D, H, W) of the input.
optional bool force_nd_im2col = 17
Whether to force use of the general ND convolution, even if a specific implementation for blobs of the appropriate number of spatial dimensions is available. (Currently, there is only a 2D-specific convolution implementation; for input blobs with num_axes != 2, this option is ignored and the ND implementation will be used.)

Used in: ConvolutionParameter

DEFAULT = 0
CAFFE = 1
CUDNN = 2

Used in: LayerParameter

optional int32 axis = 1
To crop, elements of the first bottom are selected to fit the dimensions of the second, reference bottom. The crop is configured by - the crop `axis` to pick the dimensions for cropping - the crop `offset` to set the shift for all/each dimension to align the cropped bottom with the reference bottom. All dimensions up to but excluding `axis` are preserved, while the dimensions including and trailing `axis` are cropped. If only one `offset` is set, then all dimensions are offset by this amount. Otherwise, the number of offsets must equal the number of cropped axes to shift the crop in each dimension accordingly. Note: standard dimensions are N,C,H,W so the default is a spatial crop, and `axis` may be negative to index from the end (e.g., -1 for the last axis).
repeated uint32 offset = 2

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 database. DEPRECATED. Each solver accesses a different subset of the database.
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.
optional bool force_encoded_color = 9
Force the encoded image to have 3 color channels
optional uint32 prefetch = 10
Prefetch queue (Number of batches to prefetch to host memory, increase if data access bandwidth varies).

Used in: DataParameter

LEVELDB = 0
LMDB = 1

Used in: AnnotatedDatum

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.
optional bool encoded = 7
If true data contains an encoded image that need to be decoded

Message that store parameters used by DetectionEvaluateLayer

Used in: LayerParameter

optional uint32 num_classes = 1
Number of classes that are actually predicted. Required!
optional uint32 background_label_id = 2
Label id for background class. Needed for sanity check so that background class is neither in the ground truth nor the detections.
optional float overlap_threshold = 3
Threshold for deciding true/false positive.
optional bool evaluate_difficult_gt = 4
If true, also consider difficult ground truth for evaluation.
optional string name_size_file = 5
A file which contains a list of names and sizes with same order of the input DB. The file is in the following format: name height width ... If provided, we will scale the prediction and ground truth NormalizedBBox for evaluation.
optional ResizeParameter resize_param = 6
The resize parameter used in converting NormalizedBBox to original image.
optional bool use_polygon = 7

Message that store parameters used by DetectionOutputLayer

Used in: LayerParameter

optional uint32 num_classes = 1
Number of classes to be predicted. Required!
optional bool share_location = 2
If true, bounding box are shared among different classes.
optional int32 background_label_id = 3
Background label id. If there is no background class, set it as -1.
optional NonMaximumSuppressionParameter nms_param = 4
Parameters used for non maximum suppression.
optional SaveOutputParameter save_output_param = 5
Parameters used for saving detection results.
optional PriorBoxParameter.CodeType code_type = 6
Type of coding method for bbox.
optional bool variance_encoded_in_target = 8
If true, variance is encoded in target; otherwise we need to adjust the predicted offset accordingly.
optional int32 keep_top_k = 7
Number of total bboxes to be kept per image after nms step. -1 means keeping all bboxes after nms step.
optional float confidence_threshold = 9
Only consider detections whose confidences are larger than a threshold. If not provided, consider all boxes.
optional bool visualize = 10
If true, visualize the detection results.
optional float visualize_threshold = 11
The threshold used to visualize the detection results.
optional string save_file = 12
If provided, save outputs to video file.
optional bool use_polygon = 13

Message that stores parameters used by data transformer for distortion policy

optional float brightness_prob = 1
The probability of adjusting brightness.
optional float brightness_delta = 2
Amount to add to the pixel values within [-delta, delta]. The possible value is within [0, 255]. Recommend 32.
optional float contrast_prob = 3
The probability of adjusting contrast.
optional float contrast_lower = 4
Lower bound for random contrast factor. Recommend 0.5.
optional float contrast_upper = 5
Upper bound for random contrast factor. Recommend 1.5.
optional float hue_prob = 6
The probability of adjusting hue.
optional float hue_delta = 7
Amount to add to the hue channel within [-delta, delta]. The possible value is within [0, 180]. Recommend 36.
optional float saturation_prob = 8
The probability of adjusting saturation.
optional float saturation_lower = 9
Lower bound for the random saturation factor. Recommend 0.5.
optional float saturation_upper = 10
Upper bound for the random saturation factor. Recommend 1.5.
optional float random_order_prob = 11
The probability of randomly order the image channels.

optional float dropout_ratio = 1
dropout ratio
optional bool scale_train = 2
scale train or test phase

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

repeated FillerParameter data_filler = 1
This layer produces N >= 1 top blobs. DummyDataParameter must specify 1 or N shape fields, and 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 BlobShape shape = 6
repeated uint32 num = 2
4D dimensions -- deprecated. Use "shape" instead.
repeated uint32 channels = 3
repeated uint32 height = 4
repeated uint32 width = 5

Message that stores parameters used by ELULayer

Used in: LayerParameter

optional float alpha = 1
Described in: Clevert, D.-A., Unterthiner, T., & Hochreiter, S. (2015). Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs). arXiv

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

Message that stores parameters used by EmbedLayer

Used in: LayerParameter

optional uint32 num_output = 1
The number of outputs for the layer
optional uint32 input_dim = 2
The input is given as integers to be interpreted as one-hot vector indices with dimension num_input. Hence num_input should be 1 greater than the maximum possible input value.
optional bool bias_term = 3
Whether to use a bias term
optional FillerParameter weight_filler = 4
The filler for the weight
optional FillerParameter bias_filler = 5
The filler for the bias

Condition for emitting annotations.

optional EmitConstraint.EmitType emit_type = 1
optional float emit_overlap = 2
If emit_type is MIN_OVERLAP, provide the emit_overlap.

Used in: EmitConstraint

CENTER = 0
MIN_OVERLAP = 1

Message that stores parameters used by ExpLayer

optional float base = 1
ExpLayer computes outputs y = base ^ (shift + scale * x), for base > 0. Or if base is set to the default (-1), base is set to e, so y = exp(shift + scale * x).
optional float scale = 2
optional float shift = 3

Message that stores parameters used by data transformer for expansion policy

optional float prob = 1
Probability of using this expansion policy
optional float max_expand_ratio = 2
The ratio to expand the image.

Used in: BiasParameter, ConvolutionParameter, DummyDataParameter, EmbedParameter, InnerProductParameter, NormalizeParameter, PReLUParameter, RecurrentParameter, ScaleParameter, 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 output weights for a given input in Gaussian filler -- the default -1 means don't perform sparsification.
optional FillerParameter.VarianceNorm variance_norm = 8

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

Used in: FillerParameter

FAN_IN = 0
FAN_OUT = 1
AVERAGE = 2

/ Message that stores parameters used by FlattenLayer

Used in: LayerParameter

optional int32 axis = 1
The first axis to flatten: all preceding axes are retained in the output. May be negative to index from the end (e.g., -1 for the last axis).
optional int32 end_axis = 2
The last axis to flatten: all following axes are retained in the output. May be negative to index from the end (e.g., the default -1 for the last axis).

Message that stores parameters used by HDF5DataLayer

optional string source = 1
Specify the data source.
optional uint32 batch_size = 2
Specify the batch size.
optional bool shuffle = 3
Specify whether to shuffle the data. If shuffle == true, the ordering of the HDF5 files is shuffled, and the ordering of data within any given HDF5 file is shuffled, but data between different files are not interleaved; all of a file's data are output (in a random order) before moving onto another file.

Used in: LayerParameter, V0LayerParameter, V1LayerParameter

optional string file_name = 1

optional HingeLossParameter.Norm norm = 1
Specify the Norm to use L1 or L2

Used in: HingeLossParameter

L1 = 1
L2 = 2

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 database.
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 bool is_color = 11
Specify if the images are color or gray
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.
optional string root_folder = 12

optional string source = 1
Specify the infogain matrix source.

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
optional int32 axis = 5
The first axis to be lumped into a single inner product computation; all preceding axes are retained in the output. May be negative to index from the end (e.g., -1 for the last axis).
optional bool transpose = 6
Specify whether to transpose the weight matrix or not. If transpose == true, any operations will be performed on the transpose of the weight matrix. The weight matrix itself is not going to be transposed but rather the transfer flag of operations will be toggled accordingly.

Used in: LayerParameter

repeated BlobShape shape = 1
This layer produces N >= 1 top blob(s) to be assigned manually. Define N shapes to set a shape for each top. Define 1 shape to set the same shape for every top. Define no shape to defer to reshaping manually.

Message that stores parameters used by LRNLayer

optional uint32 local_size = 1
optional float alpha = 2
optional float beta = 3
optional LRNParameter.NormRegion norm_region = 4
optional float k = 5
optional LRNParameter.Engine engine = 6

Used in: LRNParameter

DEFAULT = 0
CAFFE = 1
CUDNN = 2

Used in: LRNParameter

ACROSS_CHANNELS = 0
WITHIN_CHANNEL = 1

repeated LabelMapItem item = 1

The label (display) name and label id.

Used in: LabelMap

optional string name = 1
Both name and label are required.
optional int32 label = 2
optional string display_name = 3
display_name is optional.

NOTE Update the next available ID when you add a new LayerParameter field. LayerParameter next available layer-specific ID: 151 (last added: roi_pooling_param)

Used in: NetParameter

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
optional Phase phase = 10
The train / test phase for computation.
repeated float loss_weight = 5
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.
repeated ParamSpec param = 6
Specifies training parameters (multipliers on global learning constants, and the name and other settings used for weight sharing).
repeated BlobProto blobs = 7
The blobs containing the numeric parameters of the layer.
repeated bool propagate_down = 11
Specifies whether to backpropagate to each bottom. If unspecified, Caffe will automatically infer whether each input needs backpropagation to compute parameter gradients. If set to true for some inputs, backpropagation to those inputs is forced; if set false for some inputs, backpropagation to those inputs is skipped. The size must be either 0 or equal to the number of bottoms.
repeated NetStateRule include = 8
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 = 9
optional TransformationParameter transform_param = 100
Parameters for data pre-processing.
optional LossParameter loss_param = 101
Parameters shared by loss layers.
optional AccuracyParameter accuracy_param = 102
Layer type-specific parameters. 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.
optional AnnotatedDataParameter annotated_data_param = 200
optional ArgMaxParameter argmax_param = 103
optional BatchNormParameter batch_norm_param = 139
optional BiasParameter bias_param = 141
optional ConcatParameter concat_param = 104
optional ContrastiveLossParameter contrastive_loss_param = 105
optional ConvolutionParameter convolution_param = 106
optional CropParameter crop_param = 144
optional CTCDecoderParameter ctc_decoder_param = 149
optional CTCLossParameter ctc_loss_param = 148
optional DataParameter data_param = 107
optional DetectionEvaluateParameter detection_evaluate_param = 205
optional DetectionOutputParameter detection_output_param = 204
optional DropoutParameter dropout_param = 108
optional DummyDataParameter dummy_data_param = 109
optional EltwiseParameter eltwise_param = 110
optional ELUParameter elu_param = 140
optional EmbedParameter embed_param = 137
optional ExpParameter exp_param = 111
optional FlattenParameter flatten_param = 135
optional HDF5DataParameter hdf5_data_param = 112
optional HDF5OutputParameter hdf5_output_param = 113
optional HingeLossParameter hinge_loss_param = 114
optional ImageDataParameter image_data_param = 115
optional InfogainLossParameter infogain_loss_param = 116
optional InnerProductParameter inner_product_param = 117
optional InputParameter input_param = 143
optional LogParameter log_param = 134
optional LRNParameter lrn_param = 118
optional MemoryDataParameter memory_data_param = 119
optional MultiBoxLossParameter multibox_loss_param = 201
optional MVNParameter mvn_param = 120
optional NormalizeParameter norm_param = 206
optional ParameterParameter parameter_param = 145
optional PermuteParameter permute_param = 202
optional PoolingParameter pooling_param = 121
optional PowerParameter power_param = 122
optional PReLUParameter prelu_param = 131
optional PriorBoxParameter prior_box_param = 203
optional PythonParameter python_param = 130
optional RecurrentParameter recurrent_param = 146
optional ReductionParameter reduction_param = 136
optional ReLUParameter relu_param = 123
optional ReshapeParameter reshape_param = 133
optional ROIPoolingParameter roi_pooling_param = 150
optional ReverseParameter reverse_param = 147
optional ScaleParameter scale_param = 142
optional SigmoidParameter sigmoid_param = 124
optional SoftmaxParameter softmax_param = 125
optional SPPParameter spp_param = 132
optional SliceParameter slice_param = 126
optional TanHParameter tanh_param = 127
optional ThresholdParameter threshold_param = 128
optional TileParameter tile_param = 138
optional VideoDataParameter video_data_param = 207
optional WindowDataParameter window_data_param = 129

Message that stores parameters used by LogLayer

Used in: LayerParameter

optional float base = 1
LogLayer computes outputs y = log_base(shift + scale * x), for base > 0. Or if base is set to the default (-1), base is set to e, so y = ln(shift + scale * x) = log_e(shift + scale * x)
optional float scale = 2
optional float shift = 3

Message that stores parameters shared by loss layers

optional int32 ignore_label = 1
If specified, ignore instances with the given label.
optional LossParameter.NormalizationMode normalization = 3
For historical reasons, the default normalization for SigmoidCrossEntropyLoss is BATCH_SIZE and *not* VALID.
optional bool normalize = 2
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.

How to normalize the loss for loss layers that aggregate across batches, spatial dimensions, or other dimensions. Currently only implemented in SoftmaxWithLoss and SigmoidCrossEntropyLoss layers.

Used in: LossParameter

FULL = 0
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.
VALID = 1
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.
BATCH_SIZE = 2
Divide by the batch size.
NONE = 3
Do not normalize the loss.

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
optional float eps = 3
Epsilon for not dividing by zero while normalizing variance

optional uint32 batch_size = 1
optional uint32 channels = 2
optional uint32 height = 3
optional uint32 width = 4

Message that store parameters used by MultiBoxLossLayer

Used in: LayerParameter

optional MultiBoxLossParameter.LocLossType loc_loss_type = 1
optional MultiBoxLossParameter.ConfLossType conf_loss_type = 2
optional float loc_weight = 3
Weight for localization loss.
optional uint32 num_classes = 4
Number of classes to be predicted. Required!
optional bool share_location = 5
If true, bounding box are shared among different classes.
optional MultiBoxLossParameter.MatchType match_type = 6
optional float overlap_threshold = 7
If match_type is PER_PREDICTION, use overlap_threshold to determine the extra matching bboxes.
optional bool use_prior_for_matching = 8
Use prior for matching.
optional uint32 background_label_id = 9
Background label id.
optional bool use_difficult_gt = 10
If true, also consider difficult ground truth.
optional bool do_neg_mining = 11
If true, perform negative mining. DEPRECATED: use mining_type instead.
optional float neg_pos_ratio = 12
The negative/positive ratio.
optional float neg_overlap = 13
The negative overlap upperbound for the unmatched predictions.
optional PriorBoxParameter.CodeType code_type = 14
Type of coding method for bbox.
optional bool encode_variance_in_target = 16
If true, encode the variance of prior box in the loc loss target instead of in bbox.
optional bool map_object_to_agnostic = 17
If true, map all object classes to agnostic class. It is useful for learning objectness detector.
optional bool ignore_cross_boundary_bbox = 18
If true, ignore cross boundary bbox during matching. Cross boundary bbox is a bbox who is outside of the image region.
optional bool bp_inside = 19
If true, only backpropagate on corners which are inside of the image region when encode_type is CORNER or CORNER_SIZE.
optional MultiBoxLossParameter.MiningType mining_type = 20
optional NonMaximumSuppressionParameter nms_param = 21
Parameters used for non maximum suppression durig hard example mining.
optional int32 sample_size = 22
optional bool use_prior_for_nms = 23
optional bool use_polygon = 24
true for using polygon; false for using rbox

Confidence loss type.

SOFTMAX = 0
LOGISTIC = 1

Localization loss type.

L2 = 0
SMOOTH_L1 = 1

Matching method during training.

BIPARTITE = 0
PER_PREDICTION = 1

Mining type during training. NONE : use all negatives. MAX_NEGATIVE : select negatives based on the score. HARD_EXAMPLE : select hard examples based on "Training Region-based Object Detectors with Online Hard Example Mining", Shrivastava et.al.

NONE = 0
MAX_NEGATIVE = 1
HARD_EXAMPLE = 2

Used in: SolverParameter

optional string name = 1
consider giving the network a name
repeated string input = 3
DEPRECATED. See InputParameter. The input blobs to the network.
repeated BlobShape input_shape = 8
DEPRECATED. See InputParameter. The shape of the input blobs.
repeated int32 input_dim = 4
4D input dimensions -- deprecated. Use "input_shape" instead. If specified, 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.
optional bool debug_info = 7
Print debugging information about results while running Net::Forward, Net::Backward, and Net::Update.
repeated LayerParameter layer = 100
The layers that make up the net. Each of their configurations, including connectivity and behavior, is specified as a LayerParameter.
ID 100 so layers are printed last.
repeated V1LayerParameter layers = 2
DEPRECATED: use 'layer' instead.

Used in: NetParameter, SolverParameter

optional Phase phase = 1
optional int32 level = 2
repeated string stage = 3

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 data transformer for transformation policy

optional float prob = 1
Probability of using this resize policy
optional bool hist_eq = 2
Histogram equalized
optional bool inverse = 3
Color inversion
optional bool decolorize = 4
Grayscale
optional bool gauss_blur = 5
Gaussian blur
optional float jpeg = 6
JPEG compression quality (-1 = no compression)
optional bool posterize = 7
Posterization
optional bool erode = 8
Erosion
optional bool saltpepper = 9
Salt-and-pepper noise
optional SaltPepperParameter saltpepper_param = 10
optional bool clahe = 11
Local histogram equalization
optional bool convert_to_hsv = 12
Color space conversion
optional bool convert_to_lab = 13
Color space conversion

Used in: DetectionOutputParameter, MultiBoxLossParameter

optional float nms_threshold = 1
Threshold to be used in nms.
optional int32 top_k = 2
Maximum number of results to be kept.
optional float eta = 3
Parameter for adaptive nms.

Message that stores parameters used by NormalizeLayer

Used in: LayerParameter

optional bool across_spatial = 1
optional FillerParameter scale_filler = 2
Initial value of scale. Default is 1.0 for all
optional bool channel_shared = 3
Whether or not scale parameters are shared across channels.
optional float eps = 4
Epsilon for not dividing by zero while normalizing variance

The normalized bounding box [0, 1] w.r.t. the input image size.

Used in: Annotation

optional float xmin = 1
optional float ymin = 2
optional float xmax = 3
optional float ymax = 4
optional int32 label = 5
optional bool difficult = 6
optional float score = 7
optional float size = 8
optional string content = 9;

Used in: Annotation

optional float x1 = 1
optional float y1 = 2
optional float x2 = 3
optional float y2 = 4
optional float x3 = 5
optional float y3 = 6
optional float x4 = 7
optional float y4 = 8
optional bool difficult = 9
optional float score = 10
optional float size = 11

The normalized rbox [0, 1] w.r.t. the input image size.

Used in: Annotation

optional float x1 = 1
optional float y1 = 2
optional float x2 = 3
optional float y2 = 4
optional float h = 5
optional bool difficult = 6
optional float score = 7
optional float size = 8

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

Used in: LayerParameter

optional FillerParameter filler = 1
Initial value of a_i. Default is a_i=0.25 for all i.
optional bool channel_shared = 2
Whether or not slope paramters are shared across channels.

Specifies training parameters (multipliers on global learning constants, and the name and other settings used for weight sharing).

Used in: LayerParameter

optional string name = 1
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.
optional ParamSpec.DimCheckMode share_mode = 2
Whether to require shared weights to have the same shape, or just the same count -- defaults to STRICT if unspecified.
optional float lr_mult = 3
The multiplier on the global learning rate for this parameter.
optional float decay_mult = 4
The multiplier on the global weight decay for this parameter.

Used in: ParamSpec

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.

Used in: LayerParameter

optional BlobShape shape = 1

Used in: LayerParameter

repeated uint32 order = 1
The new orders of the axes of data. Notice it should be with in the same range as the input data, and it starts from 0. Do not provide repeated order.

Used in: LayerParameter, NetState, NetStateRule

TRAIN = 0
TEST = 1

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
optional bool global_pooling = 12
If global_pooling then it will pool over the size of the bottom by doing kernel_h = bottom->height and kernel_w = bottom->width

Used in: PoolingParameter

DEFAULT = 0
CAFFE = 1
CUDNN = 2

Used in: PoolingParameter

MAX = 0
AVE = 1
STOCHASTIC = 2

optional float power = 1
PowerLayer computes outputs y = (shift + scale * x) ^ power.
optional float scale = 2
optional float shift = 3

Message that store parameters used by PriorBoxLayer

Used in: LayerParameter

repeated float min_size = 1
Minimum box size (in pixels). Required!
repeated float max_size = 2
Maximum box size (in pixels). Required!
repeated float aspect_ratio = 3
Various of aspect ratios. Duplicate ratios will be ignored. If none is provided, we use default ratio 1.
optional bool flip = 4
If true, will flip each aspect ratio. For example, if there is aspect ratio "r", we will generate aspect ratio "1.0/r" as well.
optional bool clip = 5
If true, will clip the prior so that it is within [0, 1]
repeated float variance = 6
Variance for adjusting the prior bboxes.
optional uint32 img_size = 7
By default, we calculate img_height, img_width, step_x, step_y based on bottom[0] (feat) and bottom[1] (img). Unless these values are explicitely provided. Explicitly provide the img_size.
optional uint32 img_h = 8
Either img_size or img_h/img_w should be specified; not both.
optional uint32 img_w = 9
optional float step = 10
Explicitly provide the step size.
optional float step_h = 11
Either step or step_h/step_w should be specified; not both.
optional float step_w = 12
optional float offset = 13
Offset to the top left corner of each cell.
optional bool denser_prior_boxes = 14

Encode/decode type.

Used in: DetectionOutputParameter, MultiBoxLossParameter

CORNER = 1
CENTER_SIZE = 2
CORNER_SIZE = 3

Used in: LayerParameter

optional string module = 1
optional string layer = 2
optional string param_str = 3
This value is set to the attribute `param_str` of the `PythonLayer` object in Python before calling the `setup()` method. This could be a number, string, dictionary in Python dict format, JSON, etc. You may parse this string in `setup` method and use it in `forward` and `backward`.
optional bool share_in_parallel = 4
Whether this PythonLayer is shared among worker solvers during data parallelism. If true, each worker solver sequentially run forward from this layer. This value should be set true if you are using it as a data layer.

Message that stores parameters used by ROIPoolingLayer

Used in: LayerParameter

optional uint32 pooled_h = 1
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 pooled output height
optional uint32 pooled_w = 2
The pooled output width
optional float spatial_scale = 3
Multiplicative spatial scale factor to translate ROI coords from their input scale to the scale used when pooling

Message that stores parameters used by ReLULayer

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 RecurrentLayer

Used in: LayerParameter

optional uint32 num_output = 1
The dimension of the output (and usually hidden state) representation -- must be explicitly set to non-zero.
optional FillerParameter weight_filler = 2
The filler for the weight
optional FillerParameter bias_filler = 3
The filler for the bias
optional bool debug_info = 4
Whether to enable displaying debug_info in the unrolled recurrent net.
optional bool expose_hidden = 5
Whether to add as additional inputs (bottoms) the initial hidden state blobs, and add as additional outputs (tops) the final timestep hidden state blobs. The number of additional bottom/top blobs required depends on the recurrent architecture -- e.g., 1 for RNNs, 2 for LSTMs.

Message that stores parameters used by ReductionLayer

Used in: LayerParameter

optional ReductionParameter.ReductionOp operation = 1
reduction operation
optional int32 axis = 2
The first axis to reduce to a scalar -- may be negative to index from the end (e.g., -1 for the last axis). (Currently, only reduction along ALL "tail" axes is supported; reduction of axis M through N, where N < num_axes - 1, is unsupported.) Suppose we have an n-axis bottom Blob with shape: (d0, d1, d2, ..., d(m-1), dm, d(m+1), ..., d(n-1)). If axis == m, the output Blob will have shape (d0, d1, d2, ..., d(m-1)), and the ReductionOp operation is performed (d0 * d1 * d2 * ... * d(m-1)) times, each including (dm * d(m+1) * ... * d(n-1)) individual data. If axis == 0 (the default), the output Blob always has the empty shape (count 1), performing reduction across the entire input -- often useful for creating new loss functions.
optional float coeff = 3
coefficient for output

Used in: ReductionParameter

SUM = 1
ASUM = 2
SUMSQ = 3
MEAN = 4

Used in: LayerParameter

optional BlobShape shape = 1
Specify the output dimensions. If some of the dimensions are set to 0, the corresponding dimension from the bottom layer is used (unchanged). Exactly one dimension may be set to -1, in which case its value is inferred from the count of the bottom blob and the remaining dimensions. For example, suppose we want to reshape a 2D blob "input" with shape 2 x 8: layer { type: "Reshape" bottom: "input" top: "output" reshape_param { ... } } If "input" is 2D with shape 2 x 8, then the following reshape_param specifications are all equivalent, producing a 3D blob "output" with shape 2 x 2 x 4: reshape_param { shape { dim: 2 dim: 2 dim: 4 } } reshape_param { shape { dim: 0 dim: 2 dim: 4 } } reshape_param { shape { dim: 0 dim: 2 dim: -1 } } reshape_param { shape { dim: 0 dim:-1 dim: 4 } }
optional int32 axis = 2
axis and num_axes control the portion of the bottom blob's shape that are replaced by (included in) the reshape. By default (axis == 0 and num_axes == -1), the entire bottom blob shape is included in the reshape, and hence the shape field must specify the entire output shape. axis may be non-zero to retain some portion of the beginning of the input shape (and may be negative to index from the end; e.g., -1 to begin the reshape after the last axis, including nothing in the reshape, -2 to include only the last axis, etc.). For example, suppose "input" is a 2D blob with shape 2 x 8. Then the following ReshapeLayer specifications are all equivalent, producing a blob "output" with shape 2 x 2 x 4: reshape_param { shape { dim: 2 dim: 2 dim: 4 } } reshape_param { shape { dim: 2 dim: 4 } axis: 1 } reshape_param { shape { dim: 2 dim: 4 } axis: -3 } num_axes specifies the extent of the reshape. If num_axes >= 0 (and axis >= 0), the reshape will be performed only on input axes in the range [axis, axis+num_axes]. num_axes may also be -1, the default, to include all remaining axes (starting from axis). For example, suppose "input" is a 2D blob with shape 2 x 8. Then the following ReshapeLayer specifications are equivalent, producing a blob "output" with shape 1 x 2 x 8. reshape_param { shape { dim: 1 dim: 2 dim: 8 } } reshape_param { shape { dim: 1 dim: 2 } num_axes: 1 } reshape_param { shape { dim: 1 } num_axes: 0 } On the other hand, these would produce output blob shape 2 x 1 x 8: reshape_param { shape { dim: 2 dim: 1 dim: 8 } } reshape_param { shape { dim: 1 } axis: 1 num_axes: 0 }
optional int32 num_axes = 3

Message that stores parameters used by data transformer for resize policy

Used in: DetectionEvaluateParameter, SaveOutputParameter, TransformationParameter

optional float prob = 1
Probability of using this resize policy
optional ResizeParameter.Resize_mode resize_mode = 2
optional uint32 height = 3
optional uint32 width = 4
optional uint32 height_scale = 8
A parameter used to update bbox in FIT_SMALL_SIZE mode.
optional uint32 width_scale = 9
optional ResizeParameter.Pad_mode pad_mode = 5
Padding mode for BE_SMALL_SIZE_AND_PAD mode and object centering
repeated float pad_value = 6
if specified can be repeated once (would fill all the channels) or can be repeated the same number of times as channels (would use it them to the corresponding channel)
repeated ResizeParameter.Interp_mode interp_mode = 7
interpolation for for resizing

Same as in OpenCV

Used in: ResizeParameter

LINEAR = 1
AREA = 2
NEAREST = 3
CUBIC = 4
LANCZOS4 = 5

Used in: ResizeParameter

CONSTANT = 1
MIRRORED = 2
REPEAT_NEAREST = 3

Used in: ResizeParameter

WARP = 1
FIT_SMALL_SIZE = 2
FIT_LARGE_SIZE_AND_PAD = 3

Used in: LayerParameter

optional int32 axis = 1
axis controls the data axis which shall be inverted. The layout of the content will not be inverted The default axis is 0 that means: data_previous[n] == data_afterwards[N - n -1] where N is the shape of axis(n) Usually this layer will be used with recurrent layers to invert the time axis which is axis 0 This layer will therefore swap the order in time but not the order of the actual data.

Used in: LayerParameter

optional uint32 pyramid_height = 1
optional SPPParameter.PoolMethod pool = 2
The pooling method
optional SPPParameter.Engine engine = 6

Used in: SPPParameter

DEFAULT = 0
CAFFE = 1
CUDNN = 2

Used in: SPPParameter

MAX = 0
AVE = 1
STOCHASTIC = 2

Used in: NoiseParameter

optional float fraction = 1
Percentage of pixels
repeated float value = 2

Constraints for selecting sampled bbox.

Used in: BatchSampler

optional float min_jaccard_overlap = 1
Minimum Jaccard overlap between sampled bbox and all bboxes in AnnotationGroup.
optional float max_jaccard_overlap = 2
Maximum Jaccard overlap between sampled bbox and all bboxes in AnnotationGroup.
optional float min_sample_coverage = 3
Minimum coverage of sampled bbox by all bboxes in AnnotationGroup.
optional float max_sample_coverage = 4
Maximum coverage of sampled bbox by all bboxes in AnnotationGroup.
optional float min_object_coverage = 5
Minimum coverage of all bboxes in AnnotationGroup by sampled bbox.
optional float max_object_coverage = 6
Maximum coverage of all bboxes in AnnotationGroup by sampled bbox.

Sample a bbox in the normalized space [0, 1] with provided constraints.

Used in: BatchSampler

optional float min_scale = 1
Minimum scale of the sampled bbox.
optional float max_scale = 2
Maximum scale of the sampled bbox.
optional float min_aspect_ratio = 3
Minimum aspect ratio of the sampled bbox.
optional float max_aspect_ratio = 4
Maximum aspect ratio of the sampled bbox.

Used in: DetectionOutputParameter

optional string output_directory = 1
Output directory. If not empty, we will save the results.
optional string output_name_prefix = 2
Output name prefix.
optional string output_format = 3
Output format. VOC - PASCAL VOC output format. COCO - MS COCO output format.
optional string label_map_file = 4
If you want to output results, must also provide the following two files. Otherwise, we will ignore saving results. label map file.
optional string name_size_file = 5
A file which contains a list of names and sizes with same order of the input DB. The file is in the following format: name height width ...
optional uint32 num_test_image = 6
Number of test images. It can be less than the lines specified in name_size_file. For example, when we only want to evaluate on part of the test images.
optional ResizeParameter resize_param = 7
The resize parameter used in saving the data.

Used in: LayerParameter

optional int32 axis = 1
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). 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): (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 multiplier.
optional int32 num_axes = 2
(num_axes is ignored unless just one bottom is given and the scale is a learned parameter of the layer. Otherwise, num_axes is determined by the number of axes by the second bottom.) The number of axes of the input (bottom[0]) covered by the scale parameter, or -1 to cover all axes of bottom[0] starting from `axis`. Set num_axes := 0, to multiply with a zero-axis Blob: a scalar.
optional FillerParameter filler = 3
(filler is ignored unless just one bottom is given and the scale is a learned parameter of the layer.) The initialization for the learned scale parameter. Default is the unit (1) initialization, resulting in the ScaleLayer initially performing the identity operation.
optional bool bias_term = 4
Whether to also learn a bias (equivalent to a ScaleLayer+BiasLayer, but may be more efficient). Initialized with bias_filler (defaults to 0).
optional FillerParameter bias_filler = 5

optional SigmoidParameter.Engine engine = 1

Used in: SigmoidParameter

DEFAULT = 0
CAFFE = 1
CUDNN = 2

optional int32 axis = 3
The axis along which to slice -- may be negative to index from the end (e.g., -1 for the last axis). By default, SliceLayer concatenates blobs along the "channels" axis (1).
repeated uint32 slice_point = 2
optional uint32 slice_dim = 1
DEPRECATED: alias for "axis" -- does not support negative indexing.

Message that stores parameters used by SoftmaxLayer, SoftmaxWithLossLayer

optional SoftmaxParameter.Engine engine = 1
optional int32 axis = 2
The axis along which to perform the softmax -- may be negative to index from the end (e.g., -1 for the last axis). Any other axes will be evaluated as independent softmaxes.

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: 44 (last added: plateau_winsize)

//////////////////////////////////////////////////////////////////////////// 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
optional string eval_type = 41
Evaluation type.
optional string ap_version = 42
ap_version: different ways of computing Average Precision. Check https://sanchom.wordpress.com/tag/average-precision/ for details. 11point: the 11-point interpolated average precision. Used in VOC2007. MaxIntegral: maximally interpolated AP. Used in VOC2012/ILSVRC. Integral: the natural integral of the precision-recall curve.
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 = 33
Display the loss averaged over the last average_loss iterations
optional int32 max_iter = 7
the maximum number of iterations
optional int32 iter_size = 36
accumulate gradients over `iter_size` x `batch_size` instances
optional string lr_policy = 8
The learning rate decay policy. The currently implemented learning rate policies are as follows: - fixed: always return base_lr. - step: return base_lr * gamma ^ (floor(iter / step)) - exp: return base_lr * gamma ^ iter - inv: return base_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. return base_lr (1 - iter/max_iter) ^ (power) - sigmoid: the effective learning rate follows a sigmod decay return base_lr ( 1/(1 + exp(-gamma * (iter - stepsize)))) - plateau: decreases lr if the minimum loss isn't updated for 'plateau_winsize' iters 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 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 controlled by weight_decay
optional int32 stepsize = 13
the stepsize for learning rate policy "step"
repeated int32 stepvalue = 34
the stepsize for learning rate policy "multistep"
repeated int32 plateau_winsize = 43
the stepsize for learning rate policy "plateau"
optional float clip_gradients = 35
Set clip_gradients to >= 0 to clip parameter gradients to that L2 norm, whenever their actual L2 norm is larger.
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.SnapshotFormat snapshot_format = 37
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 string type = 40
type of the solver
optional float delta = 31
numerical stability for RMSProp, AdaGrad and AdaDelta and Adam
optional float momentum2 = 39
parameters for the Adam solver
optional float rms_decay = 38
RMSProp decay value MeanSquare(t) = rms_decay*MeanSquare(t-1) + (1-rms_decay)*SquareGradient(t)
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.
optional SolverParameter.SolverType solver_type = 30
DEPRECATED: use type instead of solver_type

Used in: SolverParameter

HDF5 = 0
BINARYPROTO = 1

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

Used in: SolverParameter

CPU = 0
GPU = 1

DEPRECATED: old solver enum types, use string instead

Used in: SolverParameter

SGD = 0
NESTEROV = 1
ADAGRAD = 2
RMSPROP = 3
ADADELTA = 4
ADAM = 5

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
optional int32 current_step = 4
The current step for learning rate
optional float minimum_loss = 5
Historical minimum loss
optional int32 iter_last_event = 6
The iteration when last lr-update or min_loss-update happend

optional TanHParameter.Engine engine = 1

Used in: TanHParameter

DEFAULT = 0
CAFFE = 1
CUDNN = 2

Message that stores parameters used by ThresholdLayer

optional float threshold = 1
Strictly positive values

Message that stores parameters used by TileLayer

Used in: LayerParameter

optional int32 axis = 1
The index of the axis to tile.
optional int32 tiles = 2
The number of copies (tiles) of the blob to output.

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

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 uint32 crop_h = 11
optional uint32 crop_w = 12
optional string mean_file = 4
mean_file and mean_value cannot be specified at the same time
repeated float mean_value = 5
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)
optional bool force_color = 6
Force the decoded image to have 3 color channels.
optional bool force_gray = 7
Force the decoded image to have 1 color channels.
optional ResizeParameter resize_param = 8
Resize policy
optional NoiseParameter noise_param = 9
Noise policy
optional DistortionParameter distort_param = 13
Distortion policy
optional ExpansionParameter expand_param = 14
Expand policy
optional EmitConstraint emit_constraint = 10
Constraint for emitting the annotation after transformation.

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

Used in: V1LayerParameter

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 float k = 22
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 database.
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

DEPRECATED: use LayerParameter.

Used in: NetParameter

repeated string bottom = 2
repeated string top = 3
optional string name = 4
repeated NetStateRule include = 32
repeated NetStateRule exclude = 33
optional V1LayerParameter.LayerType type = 5
repeated BlobProto blobs = 6
repeated string param = 1001
repeated V1LayerParameter.DimCheckMode blob_share_mode = 1002
repeated float blobs_lr = 7
repeated float weight_decay = 8
repeated float loss_weight = 35
optional AccuracyParameter accuracy_param = 27
optional ArgMaxParameter argmax_param = 23
optional ConcatParameter concat_param = 9
optional ContrastiveLossParameter contrastive_loss_param = 40
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 ExpParameter exp_param = 41
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 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
optional LossParameter loss_param = 42
optional V0LayerParameter layer = 1

Used in: V1LayerParameter

STRICT = 0
PERMISSIVE = 1

Used in: V1LayerParameter

NONE = 0
ABSVAL = 35
ACCURACY = 1
ARGMAX = 30
BNLL = 2
CONCAT = 3
CONTRASTIVE_LOSS = 37
CONVOLUTION = 4
DATA = 5
DECONVOLUTION = 39
DROPOUT = 6
DUMMY_DATA = 32
EUCLIDEAN_LOSS = 7
ELTWISE = 25
EXP = 38
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
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

Used in: LayerParameter

optional VideoDataParameter.VideoType video_type = 1
optional int32 device_id = 2
optional string video_file = 3
optional uint32 skip_frames = 4
Number of frames to be skipped before processing a frame.

Used in: VideoDataParameter

WEBCAM = 0
VIDEO = 1