/**
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package singa;

option java_package = "org.apache.singa.proto";
/// \file layer.proto is adapted from [Caffe](https://github.com/BVLC/caffe/)'s
/// proto file with commit id c419f8517b1e1b3d7a07fe212fc6c90a70b519ea. We
/// use caffe's protocol for configuring layer hyper-parameters for easy
/// transporting Caffe model into SINGA. Specifically, we do the following
/// changes:
/// 1. we rename LayerParameter to LayerConf to differentiate model parameters
/// 2. we rename xxxParameter to xxxConf for fields of LayerParameter
/// 3. we comment out some fields (using /*...*/) not used in SINGA layer but
///    reserve their tags.
/// 4. we add new fields (commented like 'singa field..') to support our own
///   functionalities.
/// TODO(wangwei) write a proto converter to automatically load caffe models
/// using Python (or C++/Java).

// Specifies the shape (dimensions) of a Blob.
message BlobShape {
  repeated int64 dim = 1 [packed = true];
}

message BlobProto {
  optional BlobShape shape = 7;
  repeated float data = 5 [packed = true];
  repeated float diff = 6 [packed = true];
  repeated double double_data = 8 [packed = true];
  repeated double double_diff = 9 [packed = true];

  // 4D dimensions -- deprecated.  Use "shape" instead.
  optional int32 num = 1 [default = 0];
  optional int32 channels = 2 [default = 0];
  optional int32 height = 3 [default = 0];
  optional int32 width = 4 [default = 0];
}

message FillerConf {
  // The filler type, case insensitive
  optional string type = 1 [default = 'constant'];
  optional float value = 2 [default = 0]; // the value in constant filler
  optional float min = 3 [default = 0]; // the min value in uniform filler
  optional float max = 4 [default = 1]; // the max value in uniform filler
  optional float mean = 5 [default = 0]; // the mean value in Gaussian filler
  optional float std = 6 [default = 1]; // the std value in Gaussian filler
  // The expected number of non-zero output weights for a given input in
  // Gaussian filler -- the default -1 means don't perform sparsification.
  /* optional int32 sparse = 7 [default = -1]; */
  // Normalize the filler variance by fan_in, fan_out, or their average.
  // Applies to 'xavier' and 'msra' fillers.
  enum VarianceNorm {
    FAN_IN = 0;
    FAN_OUT = 1;
    AVERAGE = 2;
  }
  optional VarianceNorm variance_norm = 8 [default = FAN_IN];
}

/// SINGA message
message OptimizerConf {
  // case insensitive
  optional string type = 1 [default = "sgd"];

  // used by RMSprop and Adadelta
  optional float rho = 2 [default = 0.95];

  // used by Adam and AdamMax
  optional float beta_1 = 3 [default = 0.9];
  optional float beta_2 = 4 [default = 0.999];

  // used by vanilla sgd and nesterov
  optional float momentum = 5 [default = 0.9];

  // delta is used to avoid dividing zero
  optional float delta = 6 [default = 1e-8];

  // global regularizer lower priority than ParamSpec regularizer
  optional RegularizerConf regularizer = 10;
  // global constraint lower priority than ParamSpec constraint
  optional ConstraintConf constraint = 11;
}

message ConstraintConf {
  // case insensitive to limit the parameter value/gradient scale
  optional string type = 1 [default = "l2"];
  // e.g., the threshold for limiting the parameter scale.
  optional float threshold = 2;
}

/// SINGA message
message RegularizerConf {
  // case insensitive to regularize the parameters, e.g., L2.
  optional string type = 1 [default = "l2"];
  // e.g., the weight decay for L2 regularizer
  optional float coefficient = 2;
}

// Specifies training parameters (multipliers on global learning constants,
// and the name and other settings used for weight sharing).
message ParamSpec {
  // The names of the parameter blobs -- useful for sharing parameters among
  // layers, but never required otherwise.  To share a parameter between two
  // layers, give it a (non-empty) name.
  optional string name = 1;

  // Whether to require shared weights to have the same shape, or just the same
  // count -- defaults to STRICT if unspecified.
  /*
  optional DimCheckMode share_mode = 2;
  enum DimCheckMode {
    // STRICT (default) requires that num, channels, height, width each match.
    STRICT = 0;
    // PERMISSIVE requires only the count (num*channels*height*width) to match.
    PERMISSIVE = 1;
  }
  */

  // The multiplier on the global learning rate for this parameter.
  optional float lr_mult = 3 [default = 1.0];

  // The multiplier on the global weight decay for this parameter.
  optional float decay_mult = 4 [default = 1.0];

  // SINGA uses this filed internally. Users just configure the fillers in
  // Layer specific conf message as caffe (style).
  optional FillerConf filler = 20;
  optional ConstraintConf constraint = 21;
  optional RegularizerConf regularizer = 22;
}

enum Phase {
  kTrain = 4;
  kEval = 8;
}
// NOTE
// Update the next available ID when you add a new LayerConf field.
//
// LayerConf next available layer-specific ID: 139 (last added: tile_param)
message LayerConf {
  optional string name = 1; // the layer name
  optional string type = 2; // the layer type
  /* repeated string bottom = 3; // the name of each bottom blob */
  /* repeated string top = 4; // the name of each top blob */

  // The train / test phase for computation.
  // optional Phase phase = 10;

  // The amount of weight to assign each top blob in the objective.
  // Each layer assigns a default value, usually of either 0 or 1,
  // to each top blob.
  /* repeated float loss_weight = 5; */

  // Specifies training parameters (multipliers on global learning constants,
  // and the name and other settings used for weight sharing).
  repeated ParamSpec param = 6;

  // The blobs containing the numeric parameters of the layer.
  repeated BlobProto blobs = 7;

  // Specifies on which bottoms the backpropagation should be skipped.
  // The size must be either 0 or equal to the number of bottoms.
  /* repeated bool propagate_down = 11; */

  // Rules controlling whether and when a layer is included in the network,
  // based on the current NetState.  You may specify a non-zero number of rules
  // to include OR exclude, but not both.  If no include or exclude rules are
  // specified, the layer is always included.  If the current NetState meets
  // ANY (i.e., one or more) of the specified rules, the layer is
  // included/excluded.
  /* repeated NetStateRule include = 8; */
  /* repeated NetStateRule exclude = 9; */

  // Confs for data pre-processing.
  /* optional TransformationConf transform_param = 100; */

  // Confs shared by loss layers.
  /* optional LossConf loss_param = 101; */

  // 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 AccuracyConf accuracy_conf = 102;
  optional ArgMaxConf argmax_conf = 103;
  optional ConcatConf concat_conf = 104;
  optional ContrastiveLossConf contrastive_loss_conf = 105;
  optional ConvolutionConf convolution_conf = 106;
  optional RNNConf rnn_conf = 140;
  // optional DataConf data_conf = 107;
  optional DropoutConf dropout_conf = 108;
  // optional DummyDataConf dummy_data_conf = 109;
  optional EltwiseConf eltwise_conf = 110;
  optional EmbedConf embed_conf = 137;
  optional ExpConf exp_conf = 111;
  optional FlattenConf flatten_conf = 135;
  // optional HDF5DataConf hdf5_data_conf = 112;
  // optional HDF5OutputConf hdf5_output_conf = 113;
  optional HingeLossConf hinge_loss_conf = 114;
  // optional ImageDataConf image_data_conf = 115;
  optional InfogainLossConf infogain_loss_conf = 116;
  // use dense_conf to replace this inner_product_conf
  // optional InnerProductConf inner_product_conf = 117;
  optional LogConf log_conf = 134;
  optional LRNConf lrn_conf = 118;
  // optional MemoryDataConf memory_data_conf = 119;
  optional MVNConf mvn_conf = 120;
  optional PoolingConf pooling_conf = 121;
  optional PowerConf power_conf = 122;
  optional PReLUConf prelu_conf = 131;
  // optional PythonConf python_conf = 130;
  optional ReductionConf reduction_conf = 136;
  optional ReLUConf relu_conf = 123;
  optional ReshapeConf reshape_conf = 133;
  optional SigmoidConf sigmoid_conf = 124;
  optional SoftmaxConf softmax_conf = 125;
  optional SPPConf spp_conf = 132;
  optional SliceConf slice_conf = 126;
  optional TanHConf tanh_conf = 127;
  optional ThresholdConf threshold_conf = 128;
  optional TileConf tile_conf = 138;
  //optional WindowDataConf window_data_conf = 129;

  // Used in SINGA
  optional DenseConf dense_conf = 117;
  optional MetricConf metric_conf = 200;
  optional BatchNormConf batchnorm_conf = 202;
  optional SplitConf split_conf = 203;
}

// Message that stores hyper-parameters used to apply transformation
// to the data layer's data
/*
message TransformationConf {
  // 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 float scale = 1 [default = 1];
  // Specify if we want to randomly mirror data.
  optional bool mirror = 2 [default = false];
  // Specify if we would like to randomly crop an image.
  optional uint32 crop_size = 3 [default = 0];
  // mean_file and mean_value cannot be specified at the same time
  optional string mean_file = 4;
  // if specified can be repeated once (would substract it from all the channels)
  // or can be repeated the same number of times as channels
  // (would subtract them from the corresponding channel)
  repeated float mean_value = 5;
  // Force the decoded image to have 3 color channels.
  optional bool force_color = 6 [default = false];
  // Force the decoded image to have 1 color channels.
  optional bool force_gray = 7 [default = false];
}
*/

// Message that stores hyper-parameters shared by loss layers
message LossConf {
  // If specified, ignore instances with the given label.
  optional int32 ignore_label = 1;
  // If true, normalize each batch across all instances (including spatial
  // dimesions, but not ignored instances); else, divide by batch size only.
  optional bool normalize = 2 [default = true];
}

message MetricConf {
  // 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 uint32 top_k = 1 [default = 1];

  // The "label" axis of the prediction blob, whose argmax corresponds to the
  // predicted label -- may be negative to index from the end (e.g., -1 for the
  // last axis).  For example, if axis == 1 and the predictions are
  // (N x C x H x W), the label blob is expected to contain N*H*W ground truth
  // labels with integer values in {0, 1, ..., C-1}.
  optional int32 axis = 2 [default = 1];

  // If specified, ignore instances with the given label.
  optional int32 ignore_label = 3;
}
// Messages that store hyper-parameters used by individual layer types follow, in
// alphabetical order.


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

message ConcatConf {
  // 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 int32 axis = 2 [default = 1];

  // DEPRECATED: alias for "axis" -- does not support negative indexing.
  optional uint32 concat_dim = 1 [default = 1];
}

message ContrastiveLossConf {
  // margin for dissimilar pair
  optional float margin = 1 [default = 1.0];
  // 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 bool legacy_version = 2 [default = false];
}

message ConvolutionConf {
  optional uint32 num_output = 1; // The number of outputs for the layer
  optional bool bias_term = 2 [default = true]; // whether to have bias terms

  // Pad, kernel size, and stride are all given as a single value for equal
  // dimensions in all spatial dimensions, or once per spatial dimension.
  repeated uint32 pad = 3; // The padding size; defaults to 0
  repeated uint32 kernel_size = 4; // The kernel size
  repeated uint32 stride = 6; // The stride; defaults to 1

  // For 2D convolution only, the *_h and *_w versions may also be used to
  // specify both spatial dimensions.
  optional uint32 pad_h = 9 [default = 0]; // The padding height (2D only)
  optional uint32 pad_w = 10 [default = 0]; // 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)

  // SINGA: not supported.
  // optional uint32 group = 5 [default = 1]; // The group size for group conv

  optional FillerConf weight_filler = 7; // The filler for the weight
  optional FillerConf bias_filler = 8; // The filler for the bias
  enum Engine {
    DEFAULT = 0;
    CAFFE = 1;
    CUDNN = 2;
  }
  optional Engine engine = 15 [default = DEFAULT];

  // 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.
  // SINGA: not supported;
  // optional int32 axis = 16 [default = 1];

  // 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.)
  // SINGA: not supported;
  // optional bool force_nd_im2col = 17 [default = false];


  // SINGA: add by xiangrui
  // cudnn workspace size in MB
  optional int32 workspace_byte_limit = 50 [default = 1024];
  // cudnn algorithm preference
  // options: "fastest", "limited_workspace", "no_workspace"
  optional string prefer = 51 [default = "fastest"];
}

message RNNConf {
  optional uint32 hidden_size = 1; // The hidden feature size
  optional uint32 num_stacks = 2; // The number of stacked RNN layers
  optional float dropout = 3 [default = 0];
  optional bool remember_state = 4 [default = false];
  // cudnn inputmode
  // options: "linear", "skip"
  optional string input_mode = 7 [default = "linear"];
  // cudnn direction
  // options: "unidirectional", "bidirectional"
  optional string direction = 8 [default = "unidirectional"];
  // cudnn RNN mode
  // options: "relu", "tanh", "lstm", "gru"
  optional string rnn_mode = 9 [default = "relu"];
}

/*
message DataConf {
  enum DB {
    LEVELDB = 0;
    LMDB = 1;
  }
  // Specify the data source.
  optional string source = 1;
  // Specify the batch size.
  optional uint32 batch_size = 4;
  // 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 uint32 rand_skip = 7 [default = 0];
  optional DB backend = 8 [default = LEVELDB];
  // DEPRECATED. See TransformationConf. 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 float scale = 2 [default = 1];
  optional string mean_file = 3;
  // DEPRECATED. See TransformationConf. Specify if we would like to randomly
  // crop an image.
  optional uint32 crop_size = 5 [default = 0];
  // DEPRECATED. See TransformationConf. Specify if we want to randomly mirror
  // data.
  optional bool mirror = 6 [default = false];
  // Force the encoded image to have 3 color channels
  optional bool force_encoded_color = 9 [default = false];
  // Prefetch queue (Number of batches to prefetch to host memory, increase if
  // data access bandwidth varies).
  optional uint32 prefetch = 10 [default = 4];
}
*/

message DropoutConf {
  optional float dropout_ratio = 1 [default = 0.5]; // dropout ratio
}

// DummyDataLayer fills any number of arbitrarily shaped blobs with random
// (or constant) data generated by "Fillers" (see "message FillerConf").
message DummyDataConf {
  // This layer produces N >= 1 top blobs.  DummyDataConf 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 FillerConf data_filler = 1;
  repeated BlobShape shape = 6;

  // 4D dimensions -- deprecated.  Use "shape" instead.
  repeated uint32 num = 2;
  repeated uint32 channels = 3;
  repeated uint32 height = 4;
  repeated uint32 width = 5;
}

message EltwiseConf {
  enum EltwiseOp {
    PROD = 0;
    SUM = 1;
    MAX = 2;
  }
  optional EltwiseOp operation = 1 [default = SUM]; // element-wise operation
  repeated float coeff = 2; // blob-wise coefficient for SUM operation

  // 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.)
  optional bool stable_prod_grad = 3 [default = true];
}

// Message that stores hyper-parameters used by EmbedLayer
message EmbedConf {
  optional uint32 num_output = 1; // The number of outputs for the layer
  // 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 uint32 input_dim = 2;

  optional bool bias_term = 3 [default = true]; // Whether to use a bias term
  optional FillerConf weight_filler = 4; // The filler for the weight
  optional FillerConf bias_filler = 5; // The filler for the bias

}

// Message that stores hyper-parameters used by ExpLayer
message ExpConf {
  // 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 base = 1 [default = -1.0];
  optional float scale = 2 [default = 1.0];
  optional float shift = 3 [default = 0.0];
}

/// Message that stores hyper-parameters used by FlattenLayer
message FlattenConf {
  // 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 axis = 1 [default = 1];

  // 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).
  optional int32 end_axis = 2 [default = -1];
}

/*
// Message that stores hyper-parameters used by HDF5DataLayer
message HDF5DataConf {
  // Specify the data source.
  optional string source = 1;
  // Specify the batch size.
  optional uint32 batch_size = 2;

  // 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.
  optional bool shuffle = 3 [default = false];
}

message HDF5OutputConf {
  optional string file_name = 1;
}
*/

message HingeLossConf {
  enum Norm {
    L1 = 1;
    L2 = 2;
  }
  // Specify the Norm to use L1 or L2
  optional Norm norm = 1 [default = L1];
}

/*
message ImageDataConf {
  // Specify the data source.
  optional string source = 1;
  // Specify the batch size.
  optional uint32 batch_size = 4 [default = 1];
  // 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 uint32 rand_skip = 7 [default = 0];
  // Whether or not ImageLayer should shuffle the list of files at every epoch.
  optional bool shuffle = 8 [default = false];
  // It will also resize images if new_height or new_width are not zero.
  optional uint32 new_height = 9 [default = 0];
  optional uint32 new_width = 10 [default = 0];
  // Specify if the images are color or gray
  optional bool is_color = 11 [default = true];
  // DEPRECATED. See TransformationConf. 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 float scale = 2 [default = 1];
  optional string mean_file = 3;
  // DEPRECATED. See TransformationConf. Specify if we would like to randomly
  // crop an image.
  optional uint32 crop_size = 5 [default = 0];
  // DEPRECATED. See TransformationConf. Specify if we want to randomly mirror
  // data.
  optional bool mirror = 6 [default = false];
  optional string root_folder = 12 [default = ""];
}
*/

message InfogainLossConf {
  // Specify the infogain matrix source.
  optional string source = 1;
}

message InnerProductConf {
  optional uint32 num_output = 1; // The number of outputs for the layer
  optional bool bias_term = 2 [default = true]; // whether to have bias terms
  optional FillerConf weight_filler = 3; // The filler for the weight
  optional FillerConf bias_filler = 4; // The filler for the bias

  // 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 int32 axis = 5 [default = 1];
}

message DenseConf {
  optional uint32 num_output = 1; // The number of outputs for the layer
  optional bool bias_term = 2 [default = true]; // whether to have bias terms
  optional FillerConf weight_filler = 3; // The filler for the weight
  optional FillerConf bias_filler = 4; // The filler for the bias

  // 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 int32 axis = 5 [default = 1];

  optional bool transpose = 21 [default = false]; // whether transpose or not
}

// Message that stores hyper-parameters used by LogLayer
message LogConf {
  // 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 base = 1 [default = -1.0];
  optional float scale = 2 [default = 1.0];
  optional float shift = 3 [default = 0.0];
}

// Message that stores hyper-parameters used by LRNLayer
message LRNConf {
  optional uint32 local_size = 1 [default = 5];
  optional float alpha = 2 [default = 1.];
  optional float beta = 3 [default = 0.75];
  enum NormRegion {
    ACROSS_CHANNELS = 0;
    WITHIN_CHANNEL = 1;
  }
  optional NormRegion norm_region = 4 [default = ACROSS_CHANNELS];
  optional float k = 5 [default = 1.];
}

message MemoryDataConf {
  optional uint32 batch_size = 1;
  optional uint32 channels = 2;
  optional uint32 height = 3;
  optional uint32 width = 4;
}

message MVNConf {
  // This parameter can be set to false to normalize mean only
  optional bool normalize_variance = 1 [default = true];

  // This parameter can be set to true to perform DNN-like MVN
  optional bool across_channels = 2 [default = false];

  // Epsilon for not dividing by zero while normalizing variance
  optional float eps = 3 [default = 1e-9];
}

message PoolingConf {
  enum PoolMethod {
    MAX = 0;
    AVE = 1;
    STOCHASTIC = 2;
  }
  optional PoolMethod pool = 1 [default = MAX]; // The pooling method
  // Pad, kernel size, and stride are all given as a single value for equal
  // dimensions in height and width or as Y, X pairs.
  optional uint32 pad = 4 [default = 0]; // The padding size (equal in Y, X)
  optional uint32 pad_h = 9 [default = 0]; // The padding height
  optional uint32 pad_w = 10 [default = 0]; // 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 [default = 1]; // The stride (equal in Y, X)
  optional uint32 stride_h = 7; // The stride height
  optional uint32 stride_w = 8; // The stride width
  /*
  enum Engine {
    DEFAULT = 0;
    CAFFE = 1;
    CUDNN = 2;
  }
  optional Engine engine = 11 [default = DEFAULT];
  */
  // 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 global_pooling = 12 [default = false];
  // whether to propagate nan
  optional bool nan_prop = 53 [default = false];

  // Added by xiangrui, 18 Oct, 2016
  optional bool ceil = 60 [default = false];
}

message PowerConf {
  // PowerLayer computes outputs y = (shift + scale * x) ^ power.
  optional float power = 1 [default = 1.0];
  optional float scale = 2 [default = 1.0];
  optional float shift = 3 [default = 0.0];
}
/*
message PythonConf {
  optional string module = 1;
  optional string layer = 2;
  // 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 string param_str = 3 [default = ''];
  // 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.
  optional bool share_in_parallel = 4 [default = false];
}
*/

// Message that stores hyper-parameters used by ReductionLayer
message ReductionConf {
  enum ReductionOp {
    SUM = 1;
    ASUM = 2;
    SUMSQ = 3;
    MEAN = 4;
  }

  optional ReductionOp operation = 1 [default = SUM]; // reduction operation

  // 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 int32 axis = 2 [default = 0];

  optional float coeff = 3 [default = 1.0]; // coefficient for output
}

// Message that stores hyper-parameters used by ReLULayer
message ReLUConf {
  // 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 float negative_slope = 1 [default = 0];
  /*
  enum Engine {
    DEFAULT = 0;
    CAFFE = 1;
    CUDNN = 2;
  }
  optional Engine engine = 2 [default = DEFAULT];
  */
}

message ReshapeConf {
  // 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 BlobShape shape = 1;

  // 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 axis = 2 [default = 0];
  optional int32 num_axes = 3 [default = -1];
}

message SigmoidConf {
  enum Engine {
    DEFAULT = 0;
    CAFFE = 1;
    CUDNN = 2;
  }
  optional Engine engine = 1 [default = DEFAULT];
}

message SliceConf {
  // 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).
  optional int32 axis = 3 [default = 1];
  repeated uint32 slice_point = 2;

  // DEPRECATED: alias for "axis" -- does not support negative indexing.
  optional uint32 slice_dim = 1 [default = 1];
}

// Message that stores hyper-parameters used by SoftmaxLayer, SoftmaxWithLossLayer
message SoftmaxConf {
  enum Engine {
    DEFAULT = 0;
    CAFFE = 1;
    CUDNN = 2;
  }
  optional Engine engine = 1 [default = DEFAULT];

  // 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.
  // optional int32 axis = 2 [default = 1];

  /// The cudnn algorithm preferences
  /// Options are: accurate, fast and log
  optional string algorithm = 50 [default = "accurate"];
}

message TanHConf {
  enum Engine {
    DEFAULT = 0;
    CAFFE = 1;
    CUDNN = 2;
  }
  optional Engine engine = 1 [default = DEFAULT];
}

// Message that stores hyper-parameters used by TileLayer
message TileConf {
  // The index of the axis to tile.
  optional int32 axis = 1 [default = 1];

  // The number of copies (tiles) of the blob to output.
  optional int32 tiles = 2;
}

// Message that stores hyper-parameters used by ThresholdLayer
message ThresholdConf {
  optional float threshold = 1 [default = 0]; // Strictly positive values
}

/*
message WindowDataConf {
  // Specify the data source.
  optional string source = 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 float scale = 2 [default = 1];
  optional string mean_file = 3;
  // Specify the batch size.
  optional uint32 batch_size = 4;
  // Specify if we would like to randomly crop an image.
  optional uint32 crop_size = 5 [default = 0];
  // Specify if we want to randomly mirror data.
  optional bool mirror = 6 [default = false];
  // Foreground (object) overlap threshold
  optional float fg_threshold = 7 [default = 0.5];
  // Background (non-object) overlap threshold
  optional float bg_threshold = 8 [default = 0.5];
  // Fraction of batch that should be foreground objects
  optional float fg_fraction = 9 [default = 0.25];
  // Amount of contextual padding to add around a window
  // (used only by the window_data_layer)
  optional uint32 context_pad = 10 [default = 0];
  // Mode for cropping out a detection window
  // warp: cropped window is warped to a fixed size and aspect ratio
  // square: the tightest square around the window is cropped
  optional string crop_mode = 11 [default = "warp"];
  // cache_images: will load all images in memory for faster access
  optional bool cache_images = 12 [default = false];
  // append root_folder to locate images
  optional string root_folder = 13 [default = ""];
}
*/

message SPPConf {
  enum PoolMethod {
    MAX = 0;
    AVE = 1;
    STOCHASTIC = 2;
  }
  optional uint32 pyramid_height = 1;
  optional PoolMethod pool = 2 [default = MAX]; // The pooling method
  enum Engine {
    DEFAULT = 0;
    CAFFE = 1;
    CUDNN = 2;
  }
  optional Engine engine = 6 [default = DEFAULT];
}

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

  // Initial value of a_i. Default is a_i=0.25 for all i.
  optional FillerConf filler = 1;
  // Whether or not slope paramters are shared across channels.
  optional bool channel_shared = 2 [default = false];

  optional string format = 20 [default = "NCHW"];
}

message BatchNormConf {
  // Used in the moving average computation runningMean =
  // newMean*factor + runningMean*(1-factor).
  optional double factor = 1 [default = 0.9];
}

message SplitConf {
  // Indicate the number of outputs
  optional int32 output_size = 1 [default = 2];
}