package caffe

Get desktop application:
View/edit binary Protocol Buffers messages

Message that stores parameters used by AccuracyLayer

Used in: LayerParameter, V1LayerParameter

• 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).

Used in: LayerParameter

• optional uint32 coefficient_len = 1

• optional bool has_offset = 2

• optional int32 depth_d = 3

Used in: LayerParameter

• optional uint32 output_h = 1

• optional uint32 output_w = 2

• optional float border_value = 3

• repeated float affine_mat = 4

• optional float scale = 5

• optional float translate_x = 6

• optional float translate_y = 7

Used in: LayerParameter

• optional bool inverse = 1

• optional float translate_x = 2

• optional float translate_y = 3

• repeated float affine_mat = 4

• optional float scale = 5

Used in: LayerParameter

• optional float mouth_scale = 1

• optional float eye_scale = 2

• optional int32 max_width = 3

• optional int32 max_height = 4

Message that stores parameters used by ArgMaxLayer

Used in: LayerParameter, V1LayerParameter

• optional bool out_max_val = 1

  If true produce pairs (argmax, maxval)

• optional uint32 top_k = 2

• optional int32 axis = 3

Message that stores parameters used by ArgSortLayer

Used in: LayerParameter

• optional bool descending = 1

• optional int32 axis = 2

Added 2015/7/7

Used in: LayerParameter

• optional FillerParameter scale_filler = 1

  The initial filler for the scale

• optional FillerParameter shift_filler = 2

  The initial 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: LayerParameter

• optional int32 min_disparity = 1

• optional uint32 disparity_num = 2

  NOTE: disparity_num must be divided by 4

• optional bool save_disparity = 3

• optional uint32 step_w = 4

• optional uint32 step_h = 5

• optional uint32 step_mode = 6

  0 mean only calculate once, non 0 mean accumulate sum

• optional BTCostVolumeParameter.CostDomainType cost_domain_type = 7

  SOBEL_AND_IMAGE is default correlation

• optional BTCostVolumeParameter.ImplementMode implement_mode = 8

Used in: BTCostVolumeParameter

• SOBEL_ONLY = 0

• IMAGE_ONLY = 1

• SOBEL_AND_IMAGE = 2

Used in: BTCostVolumeParameter

• GPU_MODE = 0

• CPU_MODE = 1

Used in: LayerParameter

• optional float moving_average_fraction = 3

  How much does the moving average decay each iteration?

• optional bool use_global_stats = 1

• optional float eps = 2

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.

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: LayerParameter

• required uint32 coefficient_len = 1

• optional bool has_offset = 2

Used in: LayerParameter

• required uint32 coefficient_len = 1

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

• optional BlobShape shape = 7

• repeated float data = 5

• repeated float diff = 6

• optional int32 num = 1

  5D dimensions -- deprecated. Use "shape" instead.

• optional int32 channels = 2

• optional int32 height = 3

• optional int32 width = 4

• optional int32 depth = 8

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, NetParameter, ReshapeParameter

• repeated int64 dim = 1

CTC parameter

Used in: LayerParameter

• optional float threshold = 1

• optional CTCParameter.Decoder decode_type = 2

Used in: CTCParameter

• best_path = 0

• best_path_thres = 1

• prefix_search = 2

Used in: LayerParameter

• repeated float landmark_x = 1

• repeated float landmark_y = 2

Used in: LayerParameter

• required uint32 group = 1

Used in: LayerParameter

• optional float min = 1

• optional float max = 2

Message that stores parameters used by ConcatLayer

Used in: LayerParameter, V1LayerParameter

• 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.

Message that stores parameters used by ContrastiveLossLayer

Used in: LayerParameter, V1LayerParameter

• optional float margin = 1

  margin for dissimilar pair

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_d = 23

  The padding depth

• 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_d = 22

  The kernel depth

• 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_d = 21

  The stride depth

• optional uint32 stride_h = 13

  The stride height

• optional uint32 stride_w = 14

  The stride width

• optional uint32 hole = 17

• optional uint32 hole_d = 19

• optional uint32 hole_h = 18

• optional uint32 hole_w = 20

Message that stores parameters used by ConvolutionLayer

Used in: LayerParameter, V1LayerParameter

• 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 uint32 hole = 17

• optional uint32 hole_h = 18

• optional uint32 hole_w = 19

• 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 ConvolutionParameter.PPLConvolutionForwardAlgo_t ForwardAlgo = 20

• optional int32 ntile_width = 72

• optional int32 ntile_height = 73

• optional QuantizeParameter quantize_param = 74

  repeated QuantizeParameter quantize_param = 74;

• optional bool is_relu = 77

  fusion relu for ReflectionPadConvolution [ocl]

• repeated QuantizeParameter perchannel_quantize_param = 75

• optional uint32 out_pad = 78

  out pad for pytorch deconv add by jianfei 20200824

  The out_padding size (equal in Y, X)

• optional uint32 out_pad_h = 79

  The out_padding height

• optional uint32 out_pad_w = 80

  The out_padding width

Used in: ConvolutionParameter

• DEFAULT = 0

• CAFFE = 1

• CUDNN = 2

Used in: ConvolutionParameter

• PPL_CONVOLUTION_FORWARD_ALGO_NONE = -1

• PPL_CONVOLUTION_FORWARD_ALGO_IMPLICIT_GEMM = 0

• PPL_CONVOLUTION_FORWARD_ALGO_IMPLICIT_PRECOMP_GEMM = 1

• PPL_CONVOLUTION_FORWARD_ALGO_GEMM = 2

• PPL_CONVOLUTION_FORWARD_ALGO_DIRECT = 3

• PPL_CONVOLUTION_FORWARD_ALGO_FFT = 4

• PPL_CONVOLUTION_FORWARD_ALGO_FFT_TILING = 5

• PPL_CONVOLUTION_FORWARD_ALGO_WINOGRAD_BLK2X2 = 6

• PPL_CONVOLUTION_FORWARD_ALGO_WINOGRAD_BLK4X4 = 7

• PPL_CONVOLUTION_FORWARD_ALGO_WINOGRAD_BLK6X6 = 8

• PPL_CONVOLUTION_FORWARD_ALGO_WINOGRAD_BLK4x4_FLT3x3 = 9

• PPL_CONVOLUTION_FORWARD_ALGO_WINOGRAD_BLK4x4_FLT5X5 = 10

• PPL_CONVOLUTION_FORWARD_ALGO_INVGEMM = 11

• 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 uint32 hole = 17

• optional uint32 hole_h = 18

Used in: LayerParameter

• optional uint32 groups = 1

  groups size per batch

Used in: LayerParameter

• optional int32 shift_step = 1

Message that stores parameters used by CorrelationLayer

Used in: LayerParameter

• optional uint32 pad = 2

  The padding size (equal in Y, X)

• optional uint32 kernel_size = 3

  The kernel size (square)

• optional uint32 max_displacement = 4

  The maximum displacement (square)

• optional uint32 stride_1 = 5

  The stride in blob 1 (equal in Y, X)

• optional uint32 stride_2 = 6

  The stride in blob 2 (equal in Y, X)

• optional int32 single_direction = 8

  For Correlation1D:

  Correlate only to the left (-1) or right (1)

• optional bool do_abs = 7

  Use absolute value of result

• optional CorrelationParameter.CorrelationType correlation_type = 15

  Multiplicative is normal correlation

• optional int32 pad_shift = 16

• optional bool mvn = 9

Used in: CorrelationParameter

• MULTIPLY = 0

• SUBTRACT = 1

Used in: LayerParameter

• optional CropParameter.Type type = 1

• optional uint32 crop_w = 2

• optional uint32 crop_h = 3

• optional bool print_info = 4

Used in: CropParameter

• CENTER = 1

• RANDOM = 2

Message that stores parameters used by CumProdLayer

Used in: LayerParameter

• optional int32 axis = 1

Message that stores parameters used by DataLayer

Used in: LayerParameter, V1LayerParameter

• 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 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

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.

• optional bool encoded = 7

  If true data contains an encoded image that need to be decoded

• optional int32 depth = 8

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_d = 23

  The padding depth

• 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_d = 22

  The kernel depth

• 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_d = 21

  The stride depth

• optional uint32 stride_h = 13

  The stride height

• optional uint32 stride_w = 14

  The stride width

• optional uint32 hole = 17

• optional uint32 hole_d = 19

• optional uint32 hole_h = 18

• optional uint32 hole_w = 20

• optional uint32 out_pad = 24

  The padding size (equal in Y, X)

• optional uint32 out_pad_d = 25

  The padding depth

• optional uint32 out_pad_h = 26

  The padding height

• optional uint32 out_pad_w = 27

  The padding widt

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.

Message that stores parameters used by DropoutLayer

Used in: LayerParameter, V1LayerParameter

• 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, V1LayerParameter

• 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

Used in: LayerParameter

(message has no fields)

Message that stores parameters used by EltwiseLayer

Used in: LayerParameter, V1LayerParameter

• 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 ExpLayer

Used in: LayerParameter, V1LayerParameter

• 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

Used in: BNParameter, BiasParameter, ConvolutionParameter, DummyDataParameter, InnerProductParameter, LSTMParameter, PReLUParameter, PointsCurveParameter, RecurrentParameter, ScaleParameter, V0LayerParameter, ZXYBNParameter

• 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.

/ 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).

Used in: LayerParameter

• required int32 hidden_size = 1

• optional bool bidirectional = 2

Used in: LayerParameter

• optional GridSample3DParameter.PaddingMode padding_mode = 1

• optional bool align_corners = 2

• required int32 output_channel = 3

Used in: GridSample3DParameter

• ZEROS = 0

• BORDER = 1

Used in: LayerParameter

• optional GridSampleParameter.PaddingMode padding_mode = 1

Used in: GridSampleParameter

• ZEROS = 0

• BORDER = 1

Used in: LayerParameter

• optional uint32 group = 1

• optional float moving_average_fraction = 4

• optional bool use_global_stats = 2

• optional float eps = 3

Message that stores parameters used by HDF5DataLayer

Used in: LayerParameter, V1LayerParameter

• 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, V1LayerParameter

• optional string file_name = 1

Used in: LayerParameter

• optional int32 coord_h = 1

• optional int32 coord_w = 2

• optional bool coord_reposition = 3

Used in: LayerParameter, V1LayerParameter

• 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, V1LayerParameter

• 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

Message that stores parameters InfogainLossLayer

Used in: LayerParameter, V1LayerParameter

• optional string source = 1

  Specify the infogain matrix source.

Message that stores parameters used by InnerProductLayer

Used in: LayerParameter, V1LayerParameter

• 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 QuantizeParameter quantize_param = 6

• repeated QuantizeParameter perchannel_quantize_param = 7

Used in: LayerParameter

• optional int32 num_features = 1

• optional float eps = 2

• optional bool affine = 3

Message that stores parameters used by Interp3dLayer

Used in: LayerParameter

• optional int32 depth = 8

  Depth of output

• optional int32 height = 1

  Height of output

• optional int32 width = 2

  Width of output

• optional int32 zoom_factor = 3

  zoom factor

• optional int32 shrink_factor = 4

  shrink factor

• optional int32 pad_beg = 5

  padding at begin of input

• optional int32 pad_end = 6

  padding at end of input

• optional bool align_corners = 7

Message that stores parameters used by InterpLayer

Used in: LayerParameter

• optional int32 height = 1

  Height of output

• optional int32 width = 2

  Width of output

• optional int32 zoom_factor = 3

  zoom factor

• optional int32 shrink_factor = 4

  shrink factor

• optional int32 pad_beg = 5

  padding at begin of input

• optional int32 pad_end = 6

  padding at end of input

• optional bool align_corners = 7

Used in: ROIParameter

• INTERP_BILINEAR = 0

• INTERP_NEAREST = 1

Message that stores parameters used by LRNLayer

Used in: LayerParameter, V1LayerParameter

• optional uint32 local_size = 1

• optional float alpha = 2

• optional float beta = 3

• optional LRNParameter.NormRegion norm_region = 4

• optional float k = 5

Used in: LRNParameter

• ACROSS_CHANNELS = 0

• WITHIN_CHANNEL = 1

Used in: LayerParameter

• optional uint32 num_output = 1

  The number of outputs for the layer

• optional float clipping_threshold = 2

• optional FillerParameter weight_filler = 3

  The filler for weight

• optional FillerParameter bias_filler = 4

  The filler for the bias

• optional uint32 batch_size = 5

NOTE Update the next available ID when you add a new LayerParameter field. LayerParameter next available layer-specific ID: 143 (last added: detection_output_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 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 string top_data_type = 11

  set data type of top blobs;(fp32 fp16 uchar int8 ...)

• optional LayerParameter.PrecisionType forward_precision = 12

• 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 ArgMaxParameter argmax_param = 103

• optional ConcatParameter concat_param = 104

• optional ContrastiveLossParameter contrastive_loss_param = 105

• optional ConvolutionParameter convolution_param = 106

• optional DataParameter data_param = 107

• optional DropoutParameter dropout_param = 108

• optional DummyDataParameter dummy_data_param = 109

• optional EltwiseParameter eltwise_param = 110

• optional ExpParameter exp_param = 111

• 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 LRNParameter lrn_param = 118

• optional MemoryDataParameter memory_data_param = 119

• optional MVNParameter mvn_param = 120

• optional PoolingParameter pooling_param = 121

• optional PoolingSpecificParameter pooling_specific_param = 1210

• optional PowerParameter power_param = 122

• optional ReLUParameter relu_param = 123

• optional SigmoidParameter sigmoid_param = 124

• optional SoftmaxParameter softmax_param = 125

• optional SliceParameter slice_param = 126

• optional TanHParameter tanh_param = 127

• optional ThresholdParameter threshold_param = 128

• optional WindowDataParameter window_data_param = 129

• optional PythonParameter python_param = 130

• optional CTCParameter ctc_param = 131

• optional PReLUParameter prelu_param = 132

• optional ReshapeParameter reshape_param = 133

• optional ROIPoolingParameter roi_pooling_param = 134

• optional AffineTransParameter affine_trans_param = 135

• optional ROIParameter roi_param = 136

• optional AffineTransPointParameter affine_trans_point_param = 137

• optional PermuteParameter permute_param = 138

• optional PriorBoxParameter prior_box_param = 139

• optional CalcAffineMatParameter calc_affine_mat_param = 140

• optional InterpParameter interp_param = 141

• optional DetectionOutputParameter detection_output_param = 142

• optional ReLU6Parameter relu6_param = 143

• optional BiasParameter bias_param = 144

  ! add by linan 2017.11.23 ! original number is 141

  ! <<<

• optional ZXYBNParameter zxybn_param = 145

  ! add by linan 2017.4.20

• optional CorrelationParameter correlation_param = 150

  ! add by linan 2016.12.26

• optional PSROIPoolingParameter psroi_pooling_param = 152

  ! add by pengcuo 2017.02.07

• optional NNUpsampleParameter nn_upsample_param = 163

• optional ROIAlignParameter roi_align_param = 153

  ! add by linan 2017.5.3

• optional RpnProposalLayerParameter rpn_proposal_param = 166

• optional ROIMaskPoolingParameter roi_mask_pooling_param = 176

• optional ChannelShuffleParameter channel_shuffle_param = 177

  ! add by pengcuo 2017.09.07

• optional BNParameter bn_param = 178

• optional ROIAlignPoolingPodParameter roi_align_pooling_pod_param = 205

  ! add pengcuo 2017.8.17

• optional ROIAlignPoolingParameter roi_align_pooling_param = 206

• optional PSROIAlignPoolingParameter psroi_align_pooling_param = 207

• optional AlignmentToROIParameter alignment_to_roi_param = 218

  ! add by pengcuo 2017.09.21

• optional UnpoolingParameter unpooling_param = 243

  ! add by pengcuo 2017.08

• optional LogParameter log_param = 244

• optional ReverseParameter reverse_param = 301

  ! add by linan 2017.10.17

• optional LSTMParameter lstm_param = 302

• optional PriorVBoxParameter prior_vbox_param = 304

  ! <<<

• optional BTCostVolumeParameter btcostvolume_param = 1001

• optional MovingAvgParameter moving_avg_param = 1799

  ! add by yingrui 2017.12.22

• optional SlicingParameter slicing_param = 5180

  ! add by yingrui 2017.10.25

• optional BilateralSlicingParameter bilateral_slicing_param = 5181

• optional BilateralSliceApplyParameter bilateral_slice_apply_param = 5182

• optional AdaptiveBilateralSliceApplyParameter adaptive_bilateral_slice_apply_param = 5183

• optional PointsCurveParameter pointscurve_param = 2000

  ! add by yingrui 2017.11.07

• optional SubpixelDownParameter subpixel_down_param = 2001

• optional SubpixelUpParameter subpixel_up_param = 2002

• optional ClipParameter clip_param = 2003

• optional EltwiseAffineTransformParameter eltwise_affine_transform_param = 2004

• optional TileParameter tile_param = 2005

• optional PadParameter pad_param = 2006

• optional ReduceParameter reduce_param = 2007

• optional Convolution3dParameter convolution3d_param = 2008

  ! add by linan 2019.11.15, 3d layer parameters

• optional Deconvolution3dParameter deconvolution3d_param = 2009

  optional ConvolutionTranspose3dParameter convolution_transpose3d_param = 2009;

• optional ReLU3dParameter relu3d_param = 2010

• optional PReLUParameter prelu3d_param = 2011

• optional ReLU3dParameter leaky_relu3d_param = 2012

• optional ReLU3dParameter elu3d_param = 2013

• optional GroupNorm3dParameter groupnorm3d_param = 2014

• optional BatchNorm3dParameter batchnorm3d_param = 2015

• optional Pooling3dParameter maxpooling3d_param = 2016

• optional Pooling3dParameter avepooling3d_param = 2017

• optional DropoutParameter dropout3d_param = 2018

• optional Interp3dParameter interp3d_param = 2019

• optional Pooling3dParameter pooling3d_param = 2020

• optional ReshapeParameter reshape3d_param = 2022

• optional SoftmaxParameter softmax3d_param = 2023

• optional ArgMaxParameter argmax3d_param = 2024

• optional InnerProductParameter inner_product3d_param = 2025

• optional SliceParameter slice3d_param = 2026

• optional ConcatParameter concat3d_param = 2027

• optional BNParameter bn3d_param = 2028

• optional MatMulParameter matmul3d_param = 2029

• optional TransposeParameter transpose3d_param = 2030

• optional ScaleParameter scale_param = 5001

• optional CropParameter crop_param = 5002

• optional RecurrentParameter recurrent_param = 5004

• optional BatchNormParameter batch_norm_param = 5005

• optional FlattenParameter flatten_param = 5006

• optional ScalesParameter scales_param = 5007

• optional TransposeParameter transpose_param = 5008

• optional HeatMap2CoordParameter heatmap_param = 5009

  ! add by linan 2018.5.28

• optional NormalizeParameter normalize_param = 5010

• optional Correlation2DParameter correlation2d_param = 5011

• optional MatMulParameter matmul_param = 5012

  ! add by linjin 2020.02.19

• optional ParameterParameter parameter_param = 5013

• optional PixelShuffleParameter pixelshuffle_param = 5014

  ! add by liangjiexin 2020.3.2

• optional ROITransformParameter roi_transform_param = 5015

  ! add by liangjiexin 2020.4.15

• optional InstanceNormParameter instance_norm_param = 5016

  ! add by linjin 2020.4.27

• optional GridSampleParameter grid_sample_param = 5018

  ! add by jianfei 2020.8.14

• optional ReduceL2Parameter reducel2_param = 5017

  ! add by jianfei 2020.7.14

• optional MeanParameter mean_param = 5019

  ! add by linjin 2020.8.19

• optional VarianceParameter variance_param = 5020

  ! add by linjin 2020.8.6

• optional GridSample3DParameter grid_sample_3d_param = 5021

  ! add by linjin 2020.9.3

• optional GRUParameter gru_param = 5022

  ! add by liangjiexin 2020.9.10

• optional CorrelationMigParameter correlationmig_param = 5023

  ! add by jianfei 2020.9.27

• optional ArgSortParameter argsort_param = 5024

  ! add by jianfei 2020.10.15

• optional CumProdParameter cumprod_param = 5025

• optional MainTransformParameter main_transform_param = 5026

  ! add by liangjiexin 2020.10.28

• repeated QuantizeParameter quantize_param = 6000

• optional uint32 quantize_bits = 6001

  ! added by tianzichen 2020.10.29 hexagon dsp uint16 quantize bits, used only when PrecisionType = UINT16, range [1, 16] default = 0 means this layer's quantize bits is not specified, will use global quantize bits.

Used in: LayerParameter

• DEFAULT = 0

• INT8 = 1

• FLOAT16 = 2

• FLOAT32 = 3

• INT4B = 4

• UINT8 = 5

• UINT16 = 6

Message that stores parameters used by ExpLayer

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

Used in: LayerParameter, V1LayerParameter

• optional int32 ignore_label = 1

  If specified, ignore instances with the given label.

• optional bool normalize = 2

  If true, normalize each batch across all instances (including spatial dimesions, but not ignored instances); else, divide by batch size only.

Message that stores parameters used by MVNLayer

Used in: LayerParameter, V1LayerParameter

• 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

Used in: LayerParameter

• required int32 roi_pooled_h = 1

• required int32 roi_pooled_w = 2

Used in: LayerParameter

• optional MatMulParameter.MatMulMode mode = 1

  gemm mode

Used in: MatMulParameter

• NN = 1

• NT = 2

• TN = 3

• TT = 4

Used in: LayerParameter

• repeated int32 dim = 1

• optional bool keepdim = 2

Message that stores parameters used by MemoryDataLayer

Used in: LayerParameter, V1LayerParameter

• optional uint32 batch_size = 1

• optional uint32 channels = 2

• optional uint32 height = 3

• optional uint32 width = 4

Used in: LayerParameter

• required float decay = 1

Used in: LayerParameter

• optional uint32 resize = 1

Used in: SolverParameter

• optional string name = 1

  consider giving the network a name

• repeated string input = 3

  The input blobs to the network.

• repeated BlobShape input_shape = 8

  The shape of the input blobs.

• repeated int32 input_dim = 4

  4D input dimensions -- deprecated. Use "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

Used in: LayerParameter, V1LayerParameter

• 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

Used in: DetectionOutputParameter

• optional float nms_threshold = 1

  Threshold to be used in nms.

• optional int32 top_k = 2

  Maximum number of results to be kept.

Used in: LayerParameter

• optional float coeff = 1

• optional NormalizeParameter.NormalizeMethod mode = 2

Used in: NormalizeParameter

• L1 = 1

• L2 = 2

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.

• optional QuantizeParameter quantize_param = 3

Used in: LayerParameter

• required float spatial_scale = 1

• required int32 output_dim = 2

  output channel number

• required int32 group_size = 3

  equal to pooled_size

• optional int32 sample_num = 4

Message that stores parameters used by PSROIPoolingLayer

Used in: LayerParameter

• required float spatial_scale = 1

• required int32 output_dim = 2

  output channel number

• required int32 group_size = 3

  equal to pooled_size

• optional float roi_scale = 4

  scale for roi

Used in: LayerParameter

• optional int32 pad = 1

• optional PadParameter.PadMode mode = 2

• optional int32 pad_w = 3

• optional int32 pad_h = 4

Used in: PadParameter

• REFLECTION = 1

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 int32 batch = 1

• optional int32 m = 2

• optional int32 n = 3

• optional int32 channel = 4

• optional int32 height = 5

• optional int32 width = 6

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

Used in: LayerParameter

• required int32 upscale_factor = 1

Used in: LayerParameter

• optional uint32 numpoints = 1

• optional FillerParameter slope_filler = 2

  The filler for the slope

• optional FillerParameter bias_filler = 3

  The filler for the bias

Message that stores parameters used by PoolingLayer

Used in: LayerParameter

• optional Pooling3dParameter.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_d = 11

  The padding depth

• 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_d = 14

  The kernel depth

• 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_d = 15

  The stride depth

• optional uint32 stride_h = 7

  The stride height

• optional uint32 stride_w = 8

  The stride width

• 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

• optional bool ceil_mode = 13

Used in: Pooling3dParameter

• MAX = 0

• AVE = 1

Message that stores parameters used by PoolingLayer

Used in: LayerParameter, V1LayerParameter

• 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

• optional bool ceil_mode = 13

Used in: PoolingParameter

• DEFAULT = 0

• CAFFE = 1

• CUDNN = 2

Used in: PoolingParameter

• MAX = 0

• AVE = 1

• STOCHASTIC = 2

• AVE_COUNT_INCLUDE_PADDING = 3

• AVE_COUNT_EXCLUDE_PADDING = 4

Used in: LayerParameter

• required PoolingSpecificParameter.PoolSpecificMethod pool = 1

• required uint32 spe_w = 2

• required uint32 spe_h = 3

Used in: PoolingSpecificParameter

• MAX = 0

• AVE = 1

Message that stores parameters used by PowerLayer

Used in: LayerParameter, V1LayerParameter

• 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

• optional float min_size = 1

  Minimum box size (in pixels). Required!

• optional 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.

Encode/decode type.

Used in: DetectionOutputParameter

• CORNER = 1

• CENTER_SIZE = 2

Used in: LayerParameter

• repeated float height = 1

  Encode/decode type. Minimum box size (in pixels). Required!

• optional float width = 2

• 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.

Message that stores parameters used by PythonLayer

Used in: LayerParameter

• optional string module = 1

• optional string layer = 2

Used in: ConvolutionParameter, InnerProductParameter, LayerParameter, PReLUParameter

• optional string type = 1

• optional float step = 2

  each one in uint8_t represents how much in float.

• optional float range_min = 3

  what 0 represents.

• optional float range_max = 4

  what 255 represents.

• optional uint32 zero_point = 5

  what 0.0f is represented in uint8

• optional bool adjust_range = 6

  whether to adjust range_min and range_max such that zero_point can be precisely represented by integer.

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

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

• optional int32 sample_num = 4

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

• optional int32 sample_num = 4

Used in: LayerParameter

• optional int32 pooled_h = 1

• optional int32 pooled_w = 2

• optional float spatial_scale = 3

• optional int32 half_part = 4

• optional float roi_scale = 5

• optional float mask_scale = 6

Used in: LayerParameter

• required uint32 crop_h = 1

• required uint32 crop_w = 2

• repeated float center_x = 3

• repeated float center_y = 4

• optional InterpType type = 5

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

Used in: LayerParameter

• required int32 roi_pooled_h = 1

• required int32 roi_pooled_w = 2

Used in: LayerParameter

• optional float negative_slope = 1

• optional bool channel_shared = 2

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.

Message that stores parameters used by ReLULayer

Used in: LayerParameter, V1LayerParameter

• 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 not-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.

Used in: LayerParameter

• optional int32 axes = 1

• optional int32 keepdims = 2

Used in: LayerParameter

• optional int32 axis = 1

  The index of the axis to tile.

• optional int32 mode = 2

  The number of copies (tiles) of the blob to output.

• MEAN = 0

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: -1 dim: 0 dim: 2 } }

• 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

Used in: LayerParameter

• optional int32 axis = 1

Used in: LayerParameter

• optional int32 feat_stride = 1

• optional int32 allowed_border = 2

• optional RpnProposalLayerParameter.TestDescParam test_desc_param = 3

• optional RpnProposalLayerParameter.TrainDescParam train_desc_param = 4

• repeated int32 anchor_scales = 5

• repeated float anchor_ratios = 6

• optional float score = 7

• optional bool withOutSoftmax = 8

• optional float bbox_reg_xy_limit = 9

• optional float bbox_reg_hw_temp = 10

• optional float bbox_reg_hw_ratio_thresh_hi = 11

• optional float bbox_reg_hw_ratio_thresh_lo = 12

Used in: RpnProposalLayerParameter

• optional int32 rpn_pre_nms_top_n = 1

• optional int32 rpn_post_nms_top_n = 2

• optional int32 rpn_min_size = 3

• optional float rpn_nms_thresh = 4

Used in: RpnProposalLayerParameter

• optional int32 rpn_pre_nms_top_n = 1

• optional int32 rpn_post_nms_top_n = 2

• optional int32 rpn_min_size = 3

• optional float rpn_nms_thresh = 4

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.

Used in: LayerParameter

• optional int32 axis = 1

• optional int32 num_axes = 2

• optional FillerParameter filler = 3

• optional bool bias_term = 4

• optional FillerParameter bias_filler = 5

Used in: LayerParameter

• optional float alpha = 1

• optional float beta = 2

Message that stores parameters used by SigmoidLayer

Used in: LayerParameter, V1LayerParameter

• optional SigmoidParameter.Engine engine = 1

Used in: SigmoidParameter

• DEFAULT = 0

• CAFFE = 1

• CUDNN = 2

Message that stores parameters used by SliceLayer

Used in: LayerParameter, V1LayerParameter

• 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.

Used in: LayerParameter

• optional uint32 coefficient_len = 1

• optional int32 depth_d = 2

  the grid depth to be considered.

• optional float scale_x = 3

  scale in range [0, 1] along width

• optional float scale_y = 4

  scale in range [0, 1] along height

• optional int32 offset_x = 5

  padding(or offset) along width

• optional int32 offset_y = 6

  padding(or offset) along height

• optional int32 offset_z = 7

  padding(or offset) along depth

Message that stores parameters used by SoftmaxLayer, SoftmaxWithLossLayer

Used in: LayerParameter, V1LayerParameter

• 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: 36 (last added: clip_gradients)

//////////////////////////////////////////////////////////////////////////// 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 = 33

  Display the loss averaged over the last average_loss 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 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"

• 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.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 SolverParameter.SolverType solver_type = 30

• optional float delta = 31

  numerical stability for AdaGrad

• 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

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

Used in: LayerParameter

• optional uint32 downsample = 1

Used in: LayerParameter

• optional uint32 upsample = 1

• optional SubpixelUpParameter.DataType output_datatype = 2

• optional SubpixelUpParameter.ModeType mode = 3

Used in: SubpixelUpParameter

• FLOAT32 = 0

• UINT8 = 1

Used in: SubpixelUpParameter

• caffe = 0

• pytorch = 1

Message that stores parameters used by TanHLayer

Used in: LayerParameter, V1LayerParameter

• optional TanHParameter.Engine engine = 1

Used in: TanHParameter

• DEFAULT = 0

• CAFFE = 1

• CUDNN = 2

Message that stores parameters used by ThresholdLayer

Used in: LayerParameter, V1LayerParameter

• 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.

• required 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

Used in: LayerParameter, V1LayerParameter

• 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

  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)

Used in: LayerParameter

• repeated int32 dim = 1

Used in: LayerParameter

• optional UnpoolingParameter.UnpoolMethod unpool = 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 uint32 unpool_size = 12

  destined unpooled map size

• optional uint32 unpool_h = 13

  destined unpooled map height

• optional uint32 unpool_w = 14

  destined unpooled map width

• optional UnpoolingParameter.Engine engine = 11

Used in: UnpoolingParameter

• DEFAULT = 0

• CAFFE = 1

Used in: UnpoolingParameter

• MAX = 0

• AVE = 1

• TILE = 2

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 int32 ntile_width = 72

• optional int32 ntile_height = 73

• 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

• repeated int32 dim = 1

• optional bool keepdim = 2

Message that stores parameters used by WindowDataLayer

Used in: LayerParameter, V1LayerParameter

• 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

• optional bool cache_images = 12

  cache_images: will load all images in memory for faster access

• optional string root_folder = 13

  append root_folder to locate images

Used in: LayerParameter

• optional FillerParameter slope_filler = 1

  ! PPL Will ignore FillerParameter ! But caffe use Filler to init blobs_.

• optional FillerParameter bias_filler = 2

• optional float momentum = 3

• optional float eps = 4

• optional bool frozen = 5

• optional ZXYBNParameter.Engine engine = 6

Used in: ZXYBNParameter

• DEFAULT = 0

• CAFFE = 1

• CUDNN = 2