SSD win config

template <typename Dtype>
inline void setConvolutionDesc(cudnnConvolutionDescriptor_t* conv,
    cudnnTensorDescriptor_t bottom, cudnnFilterDescriptor_t filter,
    int pad_h, int pad_w, int stride_h, int stride_w) {
#if CUDNN_VERSION_MIN(6, 0, 0)
  CUDNN_CHECK(cudnnSetConvolution2dDescriptor(*conv,
      pad_h, pad_w, stride_h, stride_w, 1, 1, CUDNN_CROSS_CORRELATION,
      dataType<Dtype>::type));
#else
    CUDNN_CHECK(cudnnSetConvolution2dDescriptor(*conv,
      pad_h, pad_w, stride_h, stride_w, 1, 1, CUDNN_CROSS_CORRELATION));
#endif
}

42:
// The label (display) name and label id.
message LabelMapItem {
  // Both name and label are required.
  optional string name = 1;
  optional int32 label = 2;
  // display_name is optional.
  optional string display_name = 3;
}

message LabelMap {
  repeated LabelMapItem item = 1;
}

// Sample a bbox in the normalized space [0, 1] with provided constraints.
message Sampler {
  // Minimum scale of the sampled bbox.
  optional float min_scale = 1 [default = 1.];
  // Maximum scale of the sampled bbox.
  optional float max_scale = 2 [default = 1.];

  // Minimum aspect ratio of the sampled bbox.
  optional float min_aspect_ratio = 3 [default = 1.];
  // Maximum aspect ratio of the sampled bbox.
  optional float max_aspect_ratio = 4 [default = 1.];
}

// Constraints for selecting sampled bbox.
message SampleConstraint {
  // Minimum Jaccard overlap between sampled bbox and all bboxes in
  // AnnotationGroup.
  optional float min_jaccard_overlap = 1;
  // Maximum Jaccard overlap between sampled bbox and all bboxes in
  // AnnotationGroup.
  optional float max_jaccard_overlap = 2;

  // Minimum coverage of sampled bbox by all bboxes in AnnotationGroup.
  optional float min_sample_coverage = 3;
  // Maximum coverage of sampled bbox by all bboxes in AnnotationGroup.
  optional float max_sample_coverage = 4;

  // Minimum coverage of all bboxes in AnnotationGroup by sampled bbox.
  optional float min_object_coverage = 5;
  // Maximum coverage of all bboxes in AnnotationGroup by sampled bbox.
  optional float max_object_coverage = 6;
}

// Sample a batch of bboxes with provided constraints.
message BatchSampler {
  // Use original image as the source for sampling.
  optional bool use_original_image = 1 [default = true];

  // Constraints for sampling bbox.
  optional Sampler sampler = 2;

  // Constraints for determining if a sampled bbox is positive or negative.
  optional SampleConstraint sample_constraint = 3;

  // If provided, break when found certain number of samples satisfing the
  // sample_constraint.
  optional uint32 max_sample = 4;

  // Maximum number of trials for sampling to avoid infinite loop.
  optional uint32 max_trials = 5 [default = 100];
}

// Condition for emitting annotations.
message EmitConstraint {
  enum EmitType {
    CENTER = 0;
    MIN_OVERLAP = 1;
  }
  optional EmitType emit_type = 1 [default = CENTER];
  // If emit_type is MIN_OVERLAP, provide the emit_overlap.
  optional float emit_overlap = 2;
}

// The normalized bounding box [0, 1] w.r.t. the input image size.
message NormalizedBBox {
  optional float xmin = 1;
  optional float ymin = 2;
  optional float xmax = 3;
  optional float ymax = 4;
  optional int32 label = 5;
  optional bool difficult = 6;
  optional float score = 7;
  optional float size = 8;
}

// Annotation for each object instance.
message Annotation {
  optional int32 instance_id = 1 [default = 0];
  optional NormalizedBBox bbox = 2;
}

// Group of annotations for a particular label.
message AnnotationGroup {
  optional int32 group_label = 1;
  repeated Annotation annotation = 2;
}

// An extension of Datum which contains "rich" annotations.
message AnnotatedDatum {
  enum AnnotationType {
    BBOX = 0;
  }
  optional Datum datum = 1;
  // If there are "rich" annotations, specify the type of annotation.
  // Currently it only supports bounding box.
  // If there are no "rich" annotations, use label in datum instead.
  optional AnnotationType type = 2;
  // Each group contains annotation for a particular class.
  repeated AnnotationGroup annotation_group = 3;
}
----------------------------------------------------------------------

  repeated NetState test_state = 27;
252:
 // Evaluation type.
  optional string eval_type = 41 [default = "classification"];
  // ap_version: different ways of computing Average Precision.
  //    Check https://sanchom.wordpress.com/tag/average-precision/ for details.
  //    11point: the 11-point interpolated average precision. Used in VOC2007.
  //    MaxIntegral: maximally interpolated AP. Used in VOC2012/ILSVRC.
  //    Integral: the natural integral of the precision-recall curve.
  optional string ap_version = 42 [default = "Integral"];
  // If true, display per class result.
  optional bool show_per_class_result = 44 [default = false];
  
 ---------------------------------------------------------------------- 
  repeated int32 stepvalue = 34;
 311:
    // the stepsize for learning rate policy "plateau"
  repeated int32 plateau_winsize = 43;
  
 ---------------------------------------------------------------------- 
 
  optional int32 current_step = 4 [default = 0]; // The current step for learning rate
  379:
  optional float minimum_loss = 5 [default = 1E38]; // Historical minimum loss
  optional int32 iter_last_event = 6 [default = 0]; // The iteration when last lr-update or min_loss-update happend
---------------------------------------------------------------------- 
 optional AccuracyParameter accuracy_param = 102;
 493:
 optional AnnotatedDataParameter annotated_data_param = 200;
  optional DetectionEvaluateParameter detection_evaluate_param = 205;
  optional DetectionOutputParameter detection_output_param = 204;
  optional MultiBoxLossParameter multibox_loss_param = 201;
  optional NormalizeParameter norm_param = 206;
  optional PermuteParameter permute_param = 202;
  optional PriorBoxParameter prior_box_param = 203;
  optional VideoDataParameter video_data_param = 207;
  
  
---------------------------------------------------------------------- 
TransformationParameter
{
   ....
  // Specify if we would like to randomly crop an image.
  optional uint32 crop_size = 3 [default = 0];
  558:
    optional uint32 crop_h = 11 [default = 0];
  optional uint32 crop_w = 12 [default = 0];
    // Resize policy
  optional ResizeParameter resize_param = 8;
  // Noise policy
  optional NoiseParameter noise_param = 9;
  // Distortion policy
  optional DistortionParameter distort_param = 13;
  // Expand policy
  optional ExpansionParameter expand_param = 14;
  // Constraint for emitting the annotation after transformation.
  optional EmitConstraint emit_constraint = 10;


---------------------------------------------------------------------- 

// Message that stores parameters used by data transformer for resize policy
message ResizeParameter {
  //Probability of using this resize policy
  optional float prob = 1 [default = 1];

  enum Resize_mode {
    WARP = 1;
    FIT_SMALL_SIZE = 2;
    FIT_LARGE_SIZE_AND_PAD = 3;
  }
  optional Resize_mode resize_mode = 2 [default = WARP];
  optional uint32 height = 3 [default = 0];
  optional uint32 width = 4 [default = 0];
  // A parameter used to update bbox in FIT_SMALL_SIZE mode.
  optional uint32 height_scale = 8 [default = 0];
  optional uint32 width_scale = 9 [default = 0];

  enum Pad_mode {
    CONSTANT = 1;
    MIRRORED = 2;
    REPEAT_NEAREST = 3;
  }
  // Padding mode for BE_SMALL_SIZE_AND_PAD mode and object centering
  optional Pad_mode pad_mode = 5 [default = CONSTANT];
  // if specified can be repeated once (would fill all the channels)
  // or can be repeated the same number of times as channels
  // (would use it them to the corresponding channel)
  repeated float pad_value = 6;

  enum Interp_mode { //Same as in OpenCV
    LINEAR = 1;
    AREA = 2;
    NEAREST = 3;
    CUBIC = 4;
    LANCZOS4 = 5;
  }
  //interpolation for for resizing
  repeated Interp_mode interp_mode = 7;
}

message SaltPepperParameter {
  //Percentage of pixels
  optional float fraction = 1 [default = 0];
  repeated float value = 2;
}

// Message that stores parameters used by data transformer for transformation
// policy
message NoiseParameter {
  //Probability of using this resize policy
  optional float prob = 1 [default = 0];
  // Histogram equalized
  optional bool hist_eq = 2 [default = false];
  // Color inversion
  optional bool inverse = 3 [default = false];
  // Grayscale
  optional bool decolorize = 4 [default = false];
  // Gaussian blur
  optional bool gauss_blur = 5 [default = false];

  // JPEG compression quality (-1 = no compression)
  optional float jpeg = 6 [default = -1];

  // Posterization
  optional bool posterize = 7 [default = false];

  // Erosion
  optional bool erode = 8 [default = false];

  // Salt-and-pepper noise
  optional bool saltpepper = 9 [default = false];

  optional SaltPepperParameter saltpepper_param = 10;

  // Local histogram equalization
  optional bool clahe = 11 [default = false];

  // Color space conversion
  optional bool convert_to_hsv = 12 [default = false];

  // Color space conversion
  optional bool convert_to_lab = 13 [default = false];
}

// Message that stores parameters used by data transformer for distortion policy
message DistortionParameter {
  // The probability of adjusting brightness.
  optional float brightness_prob = 1 [default = 0.0];
  // Amount to add to the pixel values within [-delta, delta].
  // The possible value is within [0, 255]. Recommend 32.
  optional float brightness_delta = 2 [default = 0.0];

  // The probability of adjusting contrast.
  optional float contrast_prob = 3 [default = 0.0];
  // Lower bound for random contrast factor. Recommend 0.5.
  optional float contrast_lower = 4 [default = 0.0];
  // Upper bound for random contrast factor. Recommend 1.5.
  optional float contrast_upper = 5 [default = 0.0];

  // The probability of adjusting hue.
  optional float hue_prob = 6 [default = 0.0];
  // Amount to add to the hue channel within [-delta, delta].
  // The possible value is within [0, 180]. Recommend 36.
  optional float hue_delta = 7 [default = 0.0];

  // The probability of adjusting saturation.
  optional float saturation_prob = 8 [default = 0.0];
  // Lower bound for the random saturation factor. Recommend 0.5.
  optional float saturation_lower = 9 [default = 0.0];
  // Upper bound for the random saturation factor. Recommend 1.5.
  optional float saturation_upper = 10 [default = 0.0];

  // The probability of randomly order the image channels.
  optional float random_order_prob = 11 [default = 0.0];
}

// Message that stores parameters used by data transformer for expansion policy
message ExpansionParameter {
  //Probability of using this expansion policy
  optional float prob = 1 [default = 1];

  // The ratio to expand the image.
  optional float max_expand_ratio = 2 [default = 1.];
}

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


// Message that store parameters used by DetectionEvaluateLayer
message DetectionEvaluateParameter {
  // Number of classes that are actually predicted. Required!
  optional uint32 num_classes = 1;
  // Label id for background class. Needed for sanity check so that
  // background class is neither in the ground truth nor the detections.
  optional uint32 background_label_id = 2 [default = 0];
  // Threshold for deciding true/false positive.
  optional float overlap_threshold = 3 [default = 0.5];
  // If true, also consider difficult ground truth for evaluation.
  optional bool evaluate_difficult_gt = 4 [default = true];
  // A file which contains a list of names and sizes with same order
  // of the input DB. The file is in the following format:
  //    name height width
  //    ...
  // If provided, we will scale the prediction and ground truth NormalizedBBox
  // for evaluation.
  optional string name_size_file = 5;
  // The resize parameter used in converting NormalizedBBox to original image.
  optional ResizeParameter resize_param = 6;
}

message NonMaximumSuppressionParameter {
  // Threshold to be used in nms.
  optional float nms_threshold = 1 [default = 0.3];
  // Maximum number of results to be kept.
  optional int32 top_k = 2;
  // Parameter for adaptive nms.
  optional float eta = 3 [default = 1.0];
}

message SaveOutputParameter {
  // Output directory. If not empty, we will save the results.
  optional string output_directory = 1;
  // Output name prefix.
  optional string output_name_prefix = 2;
  // Output format.
  //    VOC - PASCAL VOC output format.
  //    COCO - MS COCO output format.
  optional string output_format = 3;
  // If you want to output results, must also provide the following two files.
  // Otherwise, we will ignore saving results.
  // label map file.
  optional string label_map_file = 4;
  // 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 string name_size_file = 5;
  // Number of test images. It can be less than the lines specified in
  // name_size_file. For example, when we only want to evaluate on part
  // of the test images.
  optional uint32 num_test_image = 6;
  // The resize parameter used in saving the data.
  optional ResizeParameter resize_param = 7;
}

// Message that store parameters used by DetectionOutputLayer
message DetectionOutputParameter {
  // Number of classes to be predicted. Required!
  optional uint32 num_classes = 1;
  // If true, bounding box are shared among different classes.
  optional bool share_location = 2 [default = true];
  // Background label id. If there is no background class,
  // set it as -1.
  optional int32 background_label_id = 3 [default = 0];
  // Parameters used for non maximum suppression.
  optional NonMaximumSuppressionParameter nms_param = 4;
  // Parameters used for saving detection results.
  optional SaveOutputParameter save_output_param = 5;
  // Type of coding method for bbox.
  optional PriorBoxParameter.CodeType code_type = 6 [default = CORNER];
  // If true, variance is encoded in target; otherwise we need to adjust the
  // predicted offset accordingly.
  optional bool variance_encoded_in_target = 8 [default = false];
  // Number of total bboxes to be kept per image after nms step.
  // -1 means keeping all bboxes after nms step.
  optional int32 keep_top_k = 7 [default = -1];
  // Only consider detections whose confidences are larger than a threshold.
  // If not provided, consider all boxes.
  optional float confidence_threshold = 9;
  // If true, visualize the detection results.
  optional bool visualize = 10 [default = false];
  // The threshold used to visualize the detection results.
  optional float visualize_threshold = 11;
  // If provided, save outputs to video file.
  optional string save_file = 12;
}



// Message that store parameters used by MultiBoxLossLayer
message MultiBoxLossParameter {
  // Localization loss type.
  enum LocLossType {
    L2 = 0;
    SMOOTH_L1 = 1;
  }
  optional LocLossType loc_loss_type = 1 [default = SMOOTH_L1];
  // Confidence loss type.
  enum ConfLossType {
    SOFTMAX = 0;
    LOGISTIC = 1;
  }
  optional ConfLossType conf_loss_type = 2 [default = SOFTMAX];
  // Weight for localization loss.
  optional float loc_weight = 3 [default = 1.0];
  // Number of classes to be predicted. Required!
  optional uint32 num_classes = 4;
  // If true, bounding box are shared among different classes.
  optional bool share_location = 5 [default = true];
  // Matching method during training.
  enum MatchType {
    BIPARTITE = 0;
    PER_PREDICTION = 1;
  }
  optional MatchType match_type = 6 [default = PER_PREDICTION];
  // If match_type is PER_PREDICTION, use overlap_threshold to
  // determine the extra matching bboxes.
  optional float overlap_threshold = 7 [default = 0.5];
  // Use prior for matching.
  optional bool use_prior_for_matching = 8 [default = true];
  // Background label id.
  optional uint32 background_label_id = 9 [default = 0];
  // If true, also consider difficult ground truth.
  optional bool use_difficult_gt = 10 [default = true];
  // If true, perform negative mining.
  // DEPRECATED: use mining_type instead.
  optional bool do_neg_mining = 11;
  // The negative/positive ratio.
  optional float neg_pos_ratio = 12 [default = 3.0];
  // The negative overlap upperbound for the unmatched predictions.
  optional float neg_overlap = 13 [default = 0.5];
  // Type of coding method for bbox.
  optional PriorBoxParameter.CodeType code_type = 14 [default = CORNER];
  // If true, encode the variance of prior box in the loc loss target instead of
  // in bbox.
  optional bool encode_variance_in_target = 16 [default = false];
  // If true, map all object classes to agnostic class. It is useful for learning
  // objectness detector.
  optional bool map_object_to_agnostic = 17 [default = false];
  // If true, ignore cross boundary bbox during matching.
  // Cross boundary bbox is a bbox who is outside of the image region.
  optional bool ignore_cross_boundary_bbox = 18 [default = false];
  // If true, only backpropagate on corners which are inside of the image
  // region when encode_type is CORNER or CORNER_SIZE.
  optional bool bp_inside = 19 [default = false];
  // Mining type during training.
  //   NONE : use all negatives.
  //   MAX_NEGATIVE : select negatives based on the score.
  //   HARD_EXAMPLE : select hard examples based on "Training Region-based Object Detectors with Online Hard Example Mining", Shrivastava et.al.
  enum MiningType {
    NONE = 0;
    MAX_NEGATIVE = 1;
    HARD_EXAMPLE = 2;
  }
  optional MiningType mining_type = 20 [default = MAX_NEGATIVE];
  // Parameters used for non maximum suppression durig hard example mining.
  optional NonMaximumSuppressionParameter nms_param = 21;
  optional int32 sample_size = 22 [default = 64];
  optional bool use_prior_for_nms = 23 [default = false];
}



// Message that stores parameters used by NormalizeLayer
message NormalizeParameter {
  optional bool across_spatial = 1 [default = true];
  // Initial value of scale. Default is 1.0 for all
  optional FillerParameter scale_filler = 2;
  // Whether or not scale parameters are shared across channels.
  optional bool channel_shared = 3 [default = true];
  // Epsilon for not dividing by zero while normalizing variance
  optional float eps = 4 [default = 1e-10];
}

message PermuteParameter {
  // 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.
  repeated uint32 order = 1;
}



// Message that store parameters used by PriorBoxLayer
message PriorBoxParameter {
  // Encode/decode type.
  enum CodeType {
    CORNER = 1;
    CENTER_SIZE = 2;
    CORNER_SIZE = 3;
  }
  // Minimum box size (in pixels). Required!
  repeated float min_size = 1;
  // Maximum box size (in pixels). Required!
  repeated float max_size = 2;
  // Various of aspect ratios. Duplicate ratios will be ignored.
  // If none is provided, we use default ratio 1.
  repeated float aspect_ratio = 3;
  // 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 flip = 4 [default = true];
  // If true, will clip the prior so that it is within [0, 1]
  optional bool clip = 5 [default = false];
  // Variance for adjusting the prior bboxes.
  repeated float variance = 6;
  // 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_size = 7;
  // Either img_size or img_h/img_w should be specified; not both.
  optional uint32 img_h = 8;
  optional uint32 img_w = 9;

  // Explicitly provide the step size.
  optional float step = 10;
  // Either step or step_h/step_w should be specified; not both.
  optional float step_h = 11;
  optional float step_w = 12;

  // Offset to the top left corner of each cell.
  optional float offset = 13 [default = 0.5];
}

message VideoDataParameter{
  enum VideoType {
    WEBCAM = 0;
    VIDEO = 1;
  }
  optional VideoType video_type = 1 [default = WEBCAM];
  optional int32 device_id = 2 [default = 0];
  optional string video_file = 3;
  // Number of frames to be skipped before processing a frame.
  optional uint32 skip_frames = 4 [default = 0];
}
---------------------------------------------------------------------- 



---------------------------------------------------------------------- 


----------------------------------------------------------------------