Chiebot-Mirror
/
opencv_contrib
8
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Updated proto files, added layers to caffe

Browse Source
pull/991/head
arrybn 8 years ago
parent 478baf937f
commit 0cef050337
15 changed files with 14939 additions and 5084 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 8
      modules/dnn/include/opencv2/dnn/all_layers.hpp
  2. 13915
      modules/dnn/misc/caffe/caffe.pb.cc
  3. 5094
      modules/dnn/misc/caffe/caffe.pb.h
  4. 391
      modules/dnn/src/caffe/caffe.proto
  5. 44
      modules/dnn/src/caffe/caffe_io.cpp
  6. 18
      modules/dnn/src/caffe/layer_loaders.cpp
  7. 2
      modules/dnn/src/init.cpp
  8. 46
      modules/dnn/src/layers/batch_norm_layer.cpp
  9. 6
      modules/dnn/src/layers/batch_norm_layer.hpp
  10. 60
      modules/dnn/src/layers/scale_layer.cpp
  11. 36
      modules/dnn/src/layers/scale_layer.hpp
  12. 10
      modules/dnn/src/torch/torch_importer.cpp
  13. 5
      modules/dnn/test/test_layers.cpp
  14. 5
      modules/dnn/test/test_torch_importer.cpp
  15. 7
      modules/dnn/testdata/dnn/torch/torch_gen_test_data.lua

8
modules/dnn/include/opencv2/dnn/all_layers.hpp
Unescape View File

@ -406,7 +406,7 @@ namespace dnn
class CV_EXPORTS_W BatchNormLayer : public Layer
{
public:
static CV_WRAP Ptr<BatchNormLayer> create(float eps, bool has_weights, bool has_bias);
static CV_WRAP Ptr<BatchNormLayer> create(bool hasWeights, bool hasBias, float epsilon);
};
class CV_EXPORTS_W MaxUnpoolLayer : public Layer
@ -415,6 +415,12 @@ namespace dnn
static CV_WRAP Ptr<MaxUnpoolLayer> create(Size unpoolSize);
};
class CV_EXPORTS_W ScaleLayer : public Layer
{
public:
static CV_WRAP Ptr<ScaleLayer> create(bool hasBias);
};
//! @}
//! @}

13915
modules/dnn/misc/caffe/caffe.pb.cc
View File

File diff suppressed because it is too large Load Diff

5094
modules/dnn/misc/caffe/caffe.pb.h
View File

File diff suppressed because it is too large Load Diff

391
modules/dnn/src/caffe/caffe.proto
Unescape View File

@ -59,6 +59,8 @@ 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];
@ -73,24 +75,6 @@ message BlobProtoVector {
repeated BlobProto blobs = 1;
}
message CropParameter {
// To crop, elements of the first bottom are selected to fit the dimensions
// of the second, reference bottom. The crop is configured by
// - the crop `axis` to pick the dimensions for cropping
// - the crop `offset` to set the shift for all/each dimension
// to align the cropped bottom with the reference bottom.
// All dimensions up to but excluding `axis` are preserved, while
// the dimensions including and trailing `axis` are cropped.
// If only one `offset` is set, then all dimensions are offset by this amount.
// Otherwise, the number of offsets must equal the number of cropped axes to
// shift the crop in each dimension accordingly.
// Note: standard dimensions are N,C,H,W so the default is a spatial crop,
// and `axis` may be negative to index from the end (e.g., -1 for the last
// axis).
optional int32 axis = 1 [default = 2];
repeated uint32 offset = 2;
}
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.
@ -196,12 +180,12 @@ message FillerParameter {
message NetParameter {
optional string name = 1; // consider giving the network a name
// The input blobs to the network.
// DEPRECATED. See InputParameter. The input blobs to the network.
repeated string input = 3;
// The shape of the input blobs.
// DEPRECATED. See InputParameter. The shape of the input blobs.
repeated BlobShape input_shape = 8;
// 4D input dimensions -- deprecated. Use "shape" instead.
// 4D input dimensions -- deprecated. Use "input_shape" instead.
// If specified, for each input blob there should be four
// values specifying the num, channels, height and width of the input blob.
// Thus, there should be a total of (4 * #input) numbers.
@ -231,7 +215,7 @@ message NetParameter {
// NOTE
// Update the next available ID when you add a new SolverParameter field.
//
// SolverParameter next available ID: 37 (last added: iter_size)
// SolverParameter next available ID: 41 (last added: type)
message SolverParameter {
//////////////////////////////////////////////////////////////////////////////
// Specifying the train and test networks
@ -286,7 +270,23 @@ message SolverParameter {
optional int32 max_iter = 7; // the maximum number of iterations
// accumulate gradients over `iter_size` x `batch_size` instances
optional int32 iter_size = 36 [default = 1];
optional string lr_policy = 8; // The learning rate decay policy.
// The learning rate decay policy. The currently implemented learning rate
// policies are as follows:
// - fixed: always return base_lr.
// - step: return base_lr * gamma ^ (floor(iter / step))
// - exp: return base_lr * gamma ^ iter
// - inv: return base_lr * (1 + gamma * iter) ^ (- power)
// - multistep: similar to step but it allows non uniform steps defined by
// stepvalue
// - poly: the effective learning rate follows a polynomial decay, to be
// zero by the max_iter. return base_lr (1 - iter/max_iter) ^ (power)
// - sigmoid: the effective learning rate follows a sigmod decay
// return base_lr ( 1/(1 + exp(-gamma * (iter - stepsize))))
//
// where base_lr, max_iter, gamma, step, stepvalue and power are defined
// in the solver parameter protocol buffer, and iter is the current iteration.
optional string lr_policy = 8;
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.
@ -308,6 +308,11 @@ message SolverParameter {
// 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 bool snapshot_diff = 16 [default = false];
enum SnapshotFormat {
HDF5 = 0;
BINARYPROTO = 1;
}
optional SnapshotFormat snapshot_format = 37 [default = BINARYPROTO];
// the mode solver will use: 0 for CPU and 1 for GPU. Use GPU in default.
enum SolverMode {
CPU = 0;
@ -321,15 +326,17 @@ message SolverParameter {
// (and by default) initialize using a seed derived from the system clock.
optional int64 random_seed = 20 [default = -1];
// Solver type
enum SolverType {
SGD = 0;
NESTEROV = 1;
ADAGRAD = 2;
}
optional SolverType solver_type = 30 [default = SGD];
// numerical stability for AdaGrad
// type of the solver
optional string type = 40 [default = "SGD"];
// numerical stability for RMSProp, AdaGrad and AdaDelta and Adam
optional float delta = 31 [default = 1e-8];
// parameters for the Adam solver
optional float momentum2 = 39 [default = 0.999];
// RMSProp decay value
// MeanSquare(t) = rms_decay*MeanSquare(t-1) + (1-rms_decay)*SquareGradient(t)
optional float rms_decay = 38 [default = 0.99];
// If true, print information about the state of the net that may help with
// debugging learning problems.
@ -337,6 +344,18 @@ message SolverParameter {
// If false, don't save a snapshot after training finishes.
optional bool snapshot_after_train = 28 [default = true];
// DEPRECATED: old solver enum types, use string instead
enum SolverType {
SGD = 0;
NESTEROV = 1;
ADAGRAD = 2;
RMSPROP = 3;
ADADELTA = 4;
ADAM = 5;
}
// DEPRECATED: use type instead of solver_type
optional SolverType solver_type = 30 [default = SGD];
}
// A message that stores the solver snapshots
@ -404,7 +423,7 @@ message ParamSpec {
// NOTE
// Update the next available ID when you add a new LayerParameter field.
//
// LayerParameter next available layer-specific ID: 142 (last added: detection_output_param)
// LayerParameter next available layer-specific ID: 147 (last added: recurrent_param)
message LayerParameter {
optional string name = 1; // the layer name
optional string type = 2; // the layer type
@ -426,7 +445,12 @@ message LayerParameter {
// The blobs containing the numeric parameters of the layer.
repeated BlobProto blobs = 7;
// Specifies on which bottoms the backpropagation should be skipped.
// Specifies whether to backpropagate to each bottom. If unspecified,
// Caffe will automatically infer whether each input needs backpropagation
// to compute parameter gradients. If set to true for some inputs,
// backpropagation to those inputs is forced; if set false for some inputs,
// backpropagation to those inputs is skipped.
//
// The size must be either 0 or equal to the number of bottoms.
repeated bool propagate_down = 11;
@ -453,15 +477,19 @@ message LayerParameter {
// The default for the engine is set by the ENGINE switch at compile-time.
optional AccuracyParameter accuracy_param = 102;
optional ArgMaxParameter argmax_param = 103;
optional BatchNormParameter batch_norm_param = 139;
optional BiasParameter bias_param = 141;
optional ConcatParameter concat_param = 104;
optional ContrastiveLossParameter contrastive_loss_param = 105;
optional ConvolutionParameter convolution_param = 106;
optional CropParameter crop_param = 137;
optional CropParameter crop_param = 144;
optional DataParameter data_param = 107;
optional DetectionOutputParameter detection_output_param = 141;
optional DetectionOutputParameter detection_output_param = 147;
optional DropoutParameter dropout_param = 108;
optional DummyDataParameter dummy_data_param = 109;
optional EltwiseParameter eltwise_param = 110;
optional ELUParameter elu_param = 140;
optional EmbedParameter embed_param = 137;
optional ExpParameter exp_param = 111;
optional FlattenParameter flatten_param = 135;
optional HDF5DataParameter hdf5_data_param = 112;
@ -470,26 +498,31 @@ message LayerParameter {
optional ImageDataParameter image_data_param = 115;
optional InfogainLossParameter infogain_loss_param = 116;
optional InnerProductParameter inner_product_param = 117;
optional InputParameter input_param = 143;
optional LogParameter log_param = 134;
optional LRNParameter lrn_param = 118;
optional MemoryDataParameter memory_data_param = 119;
optional MVNParameter mvn_param = 120;
optional NormalizeBBoxParameter normalize_bbox_param = 139;
optional PermuteParameter permute_param = 138;
optional NormalizeBBoxParameter normalize_bbox_param = 149;
optional PermuteParameter permute_param = 148;
optional ParameterParameter parameter_param = 145;
optional PoolingParameter pooling_param = 121;
optional PowerParameter power_param = 122;
optional PReLUParameter prelu_param = 131;
optional PriorBoxParameter prior_box_param = 140;
optional PriorBoxParameter prior_box_param = 150;
optional PythonParameter python_param = 130;
optional RecurrentParameter recurrent_param = 146;
optional ReductionParameter reduction_param = 136;
optional ReLUParameter relu_param = 123;
optional ReshapeParameter reshape_param = 133;
optional ScaleParameter scale_param = 142;
optional SigmoidParameter sigmoid_param = 124;
optional SliceParameter slice_param = 126;
optional SoftmaxParameter softmax_param = 125;
optional SPPParameter spp_param = 132;
optional SliceParameter slice_param = 126;
optional TanHParameter tanh_param = 127;
optional ThresholdParameter threshold_param = 128;
optional TileParameter tile_param = 138;
optional WindowDataParameter window_data_param = 129;
}
@ -506,7 +539,7 @@ message TransformationParameter {
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)
// if specified can be repeated once (would subtract 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;
@ -520,9 +553,29 @@ message TransformationParameter {
message LossParameter {
// 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];
// How to normalize the loss for loss layers that aggregate across batches,
// spatial dimensions, or other dimensions. Currently only implemented in
// SoftmaxWithLoss and SigmoidCrossEntropyLoss layers.
enum NormalizationMode {
// Divide by the number of examples in the batch times spatial dimensions.
// Outputs that receive the ignore label will NOT be ignored in computing
// the normalization factor.
FULL = 0;
// Divide by the total number of output locations that do not take the
// ignore_label. If ignore_label is not set, this behaves like FULL.
VALID = 1;
// Divide by the batch size.
BATCH_SIZE = 2;
// Do not normalize the loss.
NONE = 3;
}
// For historical reasons, the default normalization for
// SigmoidCrossEntropyLoss is BATCH_SIZE and *not* VALID.
optional NormalizationMode normalization = 3 [default = VALID];
// Deprecated. Ignored if normalization is specified. If normalization
// is not specified, then setting this to false will be equivalent to
// normalization = BATCH_SIZE to be consistent with previous behavior.
optional bool normalize = 2;
}
// Messages that store parameters used by individual layer types follow, in
@ -549,6 +602,11 @@ message ArgMaxParameter {
// 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 ConcatParameter {
@ -562,6 +620,50 @@ message ConcatParameter {
optional uint32 concat_dim = 1 [default = 1];
}
message BatchNormParameter {
// 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 bool use_global_stats = 1;
// How much does the moving average decay each iteration?
optional float moving_average_fraction = 2 [default = .999];
// Small value to add to the variance estimate so that we don't divide by
// zero.
optional float eps = 3 [default = 1e-5];
}
message BiasParameter {
// 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 axis = 1 [default = 1];
// (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 int32 num_axes = 2 [default = 1];
// (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.
optional FillerParameter filler = 3;
}
message ContrastiveLossParameter {
// margin for dissimilar pair
optional float margin = 1 [default = 1.0];
@ -577,18 +679,28 @@ message ContrastiveLossParameter {
message ConvolutionParameter {
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 height and width or as Y, X pairs.
optional uint32 pad = 3 [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 = 4; // The kernel size (square)
optional uint32 kernel_h = 11; // The kernel height
optional uint32 kernel_w = 12; // The kernel width
// 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
// Factor used to dilate the kernel, (implicitly) zero-filling the resulting
// holes. (Kernel dilation is sometimes referred to by its use in the
// algorithme à trous from Holschneider et al. 1987.)
repeated uint32 dilation = 18; // The dilation; 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)
optional uint32 group = 5 [default = 1]; // The group size for group conv
optional uint32 stride = 6 [default = 1]; // The stride (equal in Y, X)
optional uint32 stride_h = 13; // The stride height
optional uint32 stride_w = 14; // The stride width
optional FillerParameter weight_filler = 7; // The filler for the weight
optional FillerParameter bias_filler = 8; // The filler for the bias
enum Engine {
@ -597,12 +709,42 @@ message ConvolutionParameter {
CUDNN = 2;
}
optional Engine engine = 15 [default = DEFAULT];
// Factor used to dilate the kernel, (implicitly) zero-filling the resulting
// holes. (Kernel dilation is sometimes referred to by its use in the
// algorithme a trous from Holschneider et al. 1987.)
optional uint32 dilation_h = 18; // The dilation height
optional uint32 dilation_w = 19; // The dilation width
optional uint32 dilation = 20; // The dilation; defaults to 1
// The axis to interpret as "channels" when performing convolution.
// Preceding dimensions are treated as independent inputs;
// succeeding dimensions are treated as "spatial".
// With (N, C, H, W) inputs, and axis == 1 (the default), we perform
// N independent 2D convolutions, sliding C-channel (or (C/g)-channels, for
// groups g>1) filters across the spatial axes (H, W) of the input.
// With (N, C, D, H, W) inputs, and axis == 1, we perform
// N independent 3D convolutions, sliding (C/g)-channels
// filters across the spatial axes (D, H, W) of the input.
optional 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.)
optional bool force_nd_im2col = 17 [default = false];
}
message CropParameter {
// To crop, elements of the first bottom are selected to fit the dimensions
// of the second, reference bottom. The crop is configured by
// - the crop `axis` to pick the dimensions for cropping
// - the crop `offset` to set the shift for all/each dimension
// to align the cropped bottom with the reference bottom.
// All dimensions up to but excluding `axis` are preserved, while
// the dimensions including and trailing `axis` are cropped.
// If only one `offset` is set, then all dimensions are offset by this amount.
// Otherwise, the number of offsets must equal the number of cropped axes to
// shift the crop in each dimension accordingly.
// Note: standard dimensions are N,C,H,W so the default is a spatial crop,
// and `axis` may be negative to index from the end (e.g., -1 for the last
// axis).
optional int32 axis = 1 [default = 2];
repeated uint32 offset = 2;
}
message DataParameter {
@ -618,6 +760,7 @@ message DataParameter {
// 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 TransformationParameter. For data pre-processing, we can do
@ -633,6 +776,9 @@ message DataParameter {
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 DropoutParameter {
@ -672,6 +818,29 @@ message EltwiseParameter {
optional bool stable_prod_grad = 3 [default = true];
}
// Message that stores parameters used by ELULayer
message ELUParameter {
// Described in:
// Clevert, D.-A., Unterthiner, T., & Hochreiter, S. (2015). Fast and Accurate
// Deep Network Learning by Exponential Linear Units (ELUs). arXiv
optional float alpha = 1 [default = 1];
}
// Message that stores parameters used by EmbedLayer
message EmbedParameter {
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 FillerParameter weight_filler = 4; // The filler for the weight
optional FillerParameter bias_filler = 5; // The filler for the bias
}
// Message that stores parameters used by ExpLayer
message ExpParameter {
// 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,
@ -725,7 +894,7 @@ message ImageDataParameter {
// Specify the data source.
optional string source = 1;
// Specify the batch size.
optional uint32 batch_size = 4;
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
@ -767,6 +936,19 @@ message InnerProductParameter {
// 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];
// Specify whether to transpose the weight matrix or not.
// If transpose == true, any operations will be performed on the transpose
// of the weight matrix. The weight matrix itself is not going to be transposed
// but rather the transfer flag of operations will be toggled accordingly.
optional bool transpose = 6 [default = false];
}
message InputParameter {
// This layer produces N >= 1 top blob(s) to be assigned manually.
// Define N shapes to set a shape for each top.
// Define 1 shape to set the same shape for every top.
// Define no shape to defer to reshaping manually.
repeated BlobShape shape = 1;
}
// Message that stores parameters used by LogLayer
@ -790,6 +972,12 @@ message LRNParameter {
}
optional NormRegion norm_region = 4 [default = ACROSS_CHANNELS];
optional float k = 5 [default = 1.];
enum Engine {
DEFAULT = 0;
CAFFE = 1;
CUDNN = 2;
}
optional Engine engine = 6 [default = DEFAULT];
}
message MemoryDataParameter {
@ -810,6 +998,10 @@ message MVNParameter {
optional float eps = 3 [default = 1e-9];
}
message ParameterParameter {
optional BlobShape shape = 1;
}
message PoolingParameter {
enum PoolMethod {
MAX = 0;
@ -849,6 +1041,34 @@ message PowerParameter {
message PythonParameter {
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 parameters used by RecurrentLayer
message RecurrentParameter {
// The dimension of the output (and usually hidden state) representation --
// must be explicitly set to non-zero.
optional uint32 num_output = 1 [default = 0];
optional FillerParameter weight_filler = 2; // The filler for the weight
optional FillerParameter bias_filler = 3; // The filler for the bias
// Whether to enable displaying debug_info in the unrolled recurrent net.
optional bool debug_info = 4 [default = false];
// Whether to add as additional inputs (bottoms) the initial hidden state
// blobs, and add as additional outputs (tops) the final timestep hidden state
// blobs. The number of additional bottom/top blobs required depends on the
// recurrent architecture -- e.g., 1 for RNNs, 2 for LSTMs.
optional bool expose_hidden = 5 [default = false];
}
// Message that stores parameters used by ReductionLayer
@ -915,7 +1135,7 @@ message ReshapeParameter {
// 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 } }
// reshape_param { shape { dim: 0 dim:-1 dim: 4 } }
//
optional BlobShape shape = 1;
@ -960,6 +1180,43 @@ message ReshapeParameter {
optional int32 num_axes = 3 [default = -1];
}
message ScaleParameter {
// The first axis of bottom[0] (the first input Blob) along which to apply
// bottom[1] (the second input Blob). May be negative to index from the end
// (e.g., -1 for the last axis).
//
// For example, if bottom[0] is 4D with shape 100x3x40x60, the output
// top[0] will have the same shape, and bottom[1] may have any of the
// following shapes (for the given value of axis):
// (axis == 0 == -4) 100; 100x3; 100x3x40; 100x3x40x60
// (axis == 1 == -3) 3; 3x40; 3x40x60
// (axis == 2 == -2) 40; 40x60
// (axis == 3 == -1) 60
// Furthermore, bottom[1] may have the empty shape (regardless of the value of
// "axis") -- a scalar multiplier.
optional int32 axis = 1 [default = 1];
// (num_axes is ignored unless just one bottom is given and the scale is
// a learned parameter of the layer. Otherwise, num_axes is determined by the
// number of axes by the second bottom.)
// The number of axes of the input (bottom[0]) covered by the scale
// parameter, or -1 to cover all axes of bottom[0] starting from `axis`.
// Set num_axes := 0, to multiply with a zero-axis Blob: a scalar.
optional int32 num_axes = 2 [default = 1];
// (filler is ignored unless just one bottom is given and the scale is
// a learned parameter of the layer.)
// The initialization for the learned scale parameter.
// Default is the unit (1) initialization, resulting in the ScaleLayer
// initially performing the identity operation.
optional FillerParameter filler = 3;
// Whether to also learn a bias (equivalent to a ScaleLayer+BiasLayer, but
// may be more efficient). Initialized with bias_filler (defaults to 0).
optional bool bias_term = 4 [default = false];
optional FillerParameter bias_filler = 5;
}
message SigmoidParameter {
enum Engine {
DEFAULT = 0;
@ -1004,6 +1261,16 @@ message TanHParameter {
optional Engine engine = 1 [default = DEFAULT];
}
// Message that stores parameters used by TileLayer
message TileParameter {
// 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 parameters used by ThresholdLayer
message ThresholdParameter {
optional float threshold = 1 [default = 0]; // Strictly positive values
}
@ -1250,7 +1517,7 @@ message PReLUParameter {
// Initial value of a_i. Default is a_i=0.25 for all i.
optional FillerParameter filler = 1;
// Whether or not slope paramters are shared across channels.
// Whether or not slope parameters are shared across channels.
optional bool channel_shared = 2 [default = false];
}

44
modules/dnn/src/caffe/caffe_io.cpp
Unescape View File

@ -155,12 +155,17 @@ bool UpgradeV1LayerParameter(const V1LayerParameter& v1_layer_param,
const char* UpgradeV1LayerType(const V1LayerParameter_LayerType type);
bool NetNeedsBatchNormUpgrade(const NetParameter& net_param);
void UpgradeNetBatchNorm(NetParameter* net_param);
// Check for deprecations and upgrade the NetParameter as needed.
bool UpgradeNetAsNeeded(const string& param_file, NetParameter* param);
bool NetNeedsUpgrade(const NetParameter& net_param) {
return NetNeedsV0ToV1Upgrade(net_param) || NetNeedsV1ToV2Upgrade(net_param);
return NetNeedsV0ToV1Upgrade(net_param) || NetNeedsV1ToV2Upgrade(net_param) ||
NetNeedsBatchNormUpgrade(net_param);
}
bool NetNeedsV0ToV1Upgrade(const NetParameter& net_param) {
@ -340,7 +345,7 @@ bool UpgradeV0LayerParameter(const V1LayerParameter& v0_layer_connection,
}
if (v0_layer_param.has_pad()) {
if (type == "conv") {
layer_param->mutable_convolution_param()->set_pad(v0_layer_param.pad());
layer_param->mutable_convolution_param()->add_pad(v0_layer_param.pad());
} else if (type == "pool") {
layer_param->mutable_pooling_param()->set_pad(v0_layer_param.pad());
} else {
@ -350,7 +355,7 @@ bool UpgradeV0LayerParameter(const V1LayerParameter& v0_layer_connection,
}
if (v0_layer_param.has_kernelsize()) {
if (type == "conv") {
layer_param->mutable_convolution_param()->set_kernel_size(
layer_param->mutable_convolution_param()->add_kernel_size(
v0_layer_param.kernelsize());
} else if (type == "pool") {
layer_param->mutable_pooling_param()->set_kernel_size(
@ -371,7 +376,7 @@ bool UpgradeV0LayerParameter(const V1LayerParameter& v0_layer_connection,
}
if (v0_layer_param.has_stride()) {
if (type == "conv") {
layer_param->mutable_convolution_param()->set_stride(
layer_param->mutable_convolution_param()->add_stride(
v0_layer_param.stride());
} else if (type == "pool") {
layer_param->mutable_pooling_param()->set_stride(
@ -774,6 +779,14 @@ bool UpgradeNetAsNeeded(const string& param_file, NetParameter* param) {
<< "V1LayerParameter";
}
}
// NetParameter uses old style batch norm layers; try to upgrade it.
if (NetNeedsBatchNormUpgrade(*param)) {
LOG(INFO) << "Attempting to upgrade batch norm layers using deprecated "
<< "params: " << param_file;
UpgradeNetBatchNorm(param);
LOG(INFO) << "Successfully upgraded batch norm layers using deprecated "
<< "params.";
}
return success;
}
@ -797,6 +810,29 @@ bool UpgradeV1Net(const NetParameter& v1_net_param, NetParameter* net_param) {
return is_fully_compatible;
}
bool NetNeedsBatchNormUpgrade(const NetParameter& net_param) {
for (int i = 0; i < net_param.layer_size(); ++i) {
// Check if BatchNorm layers declare three parameters, as required by
// the previous BatchNorm layer definition.
if (net_param.layer(i).type() == "BatchNorm"
&& net_param.layer(i).param_size() == 3) {
return true;
}
}
return false;
}
void UpgradeNetBatchNorm(NetParameter* net_param) {
for (int i = 0; i < net_param->layer_size(); ++i) {
// Check if BatchNorm layers declare three parameters, as required by
// the previous BatchNorm layer definition.
if (net_param->layer(i).type() == "BatchNorm"
&& net_param->layer(i).param_size() == 3) {
net_param->mutable_layer(i)->clear_param();
}
}
}
bool UpgradeV1LayerParameter(const V1LayerParameter& v1_layer_param,
LayerParameter* layer_param) {
layer_param->Clear();

18
modules/dnn/src/caffe/layer_loaders.cpp
Unescape View File

@ -286,13 +286,12 @@ template<> //BatchNormLayer specialization
Ptr<Layer> createLayerFromCaffe<BatchNormLayer>(LayerParams& params)
{
const std::vector<Blob> &blobs = params.blobs;
CV_Assert(blobs.size() == 4);
CV_Assert(blobs.size() >= 3);
float eps = params.get<float>("eps");
bool hasWeights = params.get<bool>("has_weight", false);
bool hasBias = params.get<bool>("has_bias", false);
Ptr<BatchNormLayer> l = BatchNormLayer::create(eps, hasWeights, hasBias);
float epsilon = params.get<float>("eps", 1E-5);
Ptr<BatchNormLayer> l = BatchNormLayer::create(hasWeights, hasBias, epsilon);
l->setParamsFrom(params);
return Ptr<Layer>(l);
@ -318,6 +317,15 @@ Ptr<Layer> createLayerFromCaffe<MaxUnpoolLayer>(LayerParams& params)
return Ptr<Layer>(l);
}
template<> //ScaleLayer specialization
Ptr<Layer> createLayerFromCaffe<ScaleLayer>(LayerParams& params)
{
Ptr<ScaleLayer> l = ScaleLayer::create(params.get<bool>("bias_term", false));
l->setParamsFrom(params);
return Ptr<Layer>(l);
}
//Explicit instantiation
template Ptr<Layer> createLayerFromCaffe<ConvolutionLayer>(LayerParams&);
template Ptr<Layer> createLayerFromCaffe<DeconvolutionLayer>(LayerParams&);
@ -342,6 +350,6 @@ template Ptr<Layer> createLayerFromCaffe<EltwiseLayer>(LayerParams&);
template Ptr<Layer> createLayerFromCaffe<BatchNormLayer>(LayerParams&);
template Ptr<Layer> createLayerFromCaffe<ChannelsPReLULayer>(LayerParams&);
template Ptr<Layer> createLayerFromCaffe<MaxUnpoolLayer>(LayerParams&);
template Ptr<Layer> createLayerFromCaffe<ScaleLayer>(LayerParams&);
}
}

2
modules/dnn/src/init.cpp
Unescape View File

@ -52,6 +52,7 @@
#include "layers/normalize_bbox_layer.hpp"
#include "layers/shift_layer.hpp"
#include "layers/padding_layer.hpp"
#include "layers/scale_layer.hpp"
namespace cv
{
@ -109,6 +110,7 @@ void initModule()
REG_RUNTIME_LAYER_CLASS(NormalizeBBox, NormalizeBBoxLayer);
REG_RUNTIME_LAYER_CLASS(Shift, ShiftLayer);
REG_RUNTIME_LAYER_CLASS(Padding, PaddingLayer);
REG_RUNTIME_LAYER_FUNC(Scale, createLayerFromCaffe<ScaleLayer>);
init.status = true;
}

46
modules/dnn/src/layers/batch_norm_layer.cpp
Unescape View File

@ -16,19 +16,21 @@ namespace cv
namespace dnn
{
BatchNormLayerImpl::BatchNormLayerImpl(float eps_, bool hasWeights_, bool hasBias_):
eps(eps_),
BatchNormLayerImpl::BatchNormLayerImpl(bool hasWeights_, bool hasBias_, float epsilon_):
hasWeights(hasWeights_),
hasBias(hasBias_)
hasBias(hasBias_),
epsilon(epsilon_)
{}
void BatchNormLayerImpl::allocate(const std::vector<Blob*> &inputs, std::vector<Blob> &outputs)
{
CV_Assert(blobs.size() == 4);
CV_Assert(blobs.size() >= 2);
outputs.resize(inputs.size());
for (size_t i = 0; i < inputs.size(); i++)
{
CV_Assert(blobs[0].total() == inputs[i]->channels());
CV_Assert(blobs[1].total() == inputs[i]->channels());
outputs[i].create(inputs[i]->shape());
}
}
@ -39,30 +41,46 @@ void BatchNormLayerImpl::forward(std::vector<Blob*> &inputs, std::vector<Blob> &
Blob &inpBlob = *inputs[0];
int weightsBlobIndex = 2;
int biasBlobIndex = weightsBlobIndex + hasWeights;
float varMeanScale = 1;
if (!hasWeights && !hasBias) {
varMeanScale = *blobs[2].ptrf();
if (varMeanScale != 0)
varMeanScale = 1/varMeanScale;
}
Mat invStdMat;
cv::pow(blobs[1].matRefConst()*varMeanScale + epsilon, -0.5, invStdMat);
for (size_t ii = 0; ii < outputs.size(); ii++)
{
Blob &outBlob = outputs[ii];
if (hasWeights)
CV_Assert(inpBlob.channels() == blobs[2].total());
CV_Assert(inpBlob.channels() == blobs[weightsBlobIndex].total());
if (hasBias)
CV_Assert(inpBlob.channels() == blobs[3].total());
CV_Assert(inpBlob.channels() == blobs[biasBlobIndex].total());
for (int n = 0; n < inpBlob.channels(); n++)
for(int num = 0; num < outBlob.num(); num++)
{
for (int n = 0; n < outBlob.channels(); n++)
{
float mean = blobs[0].matRefConst().at<float>(n);
float invstd = 1 / sqrt(blobs[1].matRefConst().at<float>(n) + eps);
float w = hasWeights ? blobs[2].matRefConst().at<float>(n) : 1;
float b = hasBias ? blobs[3].matRefConst().at<float>(n) : 0;
outBlob.getPlane(0, n) = (inpBlob.getPlane(0, n) - mean)*(w*invstd) + b;
float mean = blobs[0].matRefConst().at<float>(n)*varMeanScale;
double invstd = invStdMat.at<float>(n);
float w = hasWeights ? blobs[weightsBlobIndex].matRefConst().at<float>(n) : 1;
float b = hasBias ? blobs[biasBlobIndex].matRefConst().at<float>(n) : 0;
outBlob.getPlane(num, n) = (inpBlob.getPlane(num, n) - mean)*w*invstd + b;
}
}
}
}
Ptr<BatchNormLayer> BatchNormLayer::create(float eps, bool has_weights, bool has_bias)
Ptr<BatchNormLayer> BatchNormLayer::create(bool hasWeights, bool hasBias, float epsilon)
{
return Ptr<BatchNormLayer>(new BatchNormLayerImpl(eps, has_weights, has_bias));
return Ptr<BatchNormLayer>(new BatchNormLayerImpl(hasWeights, hasBias, epsilon));
}
} // namespace dnn

6
modules/dnn/src/layers/batch_norm_layer.hpp
Unescape View File

@ -21,17 +21,17 @@ namespace dnn
class BatchNormLayerImpl : public BatchNormLayer
{
public:
BatchNormLayerImpl(float eps_, bool hasWeights_, bool hasBias_);
BatchNormLayerImpl(bool hasWeights_, bool hasBias_, float epsilon_);
void allocate(const std::vector<Blob*> &inputs, std::vector<Blob> &outputs);
void forward(std::vector<Blob*> &inputs, std::vector<Blob> &outputs);
private:
float eps;
bool hasWeights, hasBias;
float epsilon;
};
}
}
#endif // BATCH_NORM_LAYER_HPP
#endif // __OPENCV_DNN_LAYERS_BATCH_NORM_LAYER_HPP__

60
modules/dnn/src/layers/scale_layer.cpp
Unescape View File

@ -0,0 +1,60 @@
// This file is part of OpenCV project.
// It is subject to the license terms in the LICENSE file found in the top-level directory
// of this distribution and at http://opencv.org/license.html.
// Copyright (C) 2016, Intel Corporation, all rights reserved.
// Third party copyrights are property of their respective owners.
/*
Implementation of Scale layer.
*/
#include "scale_layer.hpp"
namespace cv
{
namespace dnn
{
void ScaleLayerImpl::allocate(const std::vector<Blob*> &inputs, std::vector<Blob> &outputs)
{
CV_Assert(blobs.size() == 1 + hasBias);
outputs.resize(inputs.size());
for (size_t i = 0; i < inputs.size(); i++)
{
outputs[i].create(inputs[i]->shape());
}
}
void ScaleLayerImpl::forward(std::vector<Blob*> &inputs, std::vector<Blob> &outputs)
{
CV_Assert(inputs.size() == 1);
Blob &inpBlob = *inputs[0];
for (size_t ii = 0; ii < outputs.size(); ii++)
{
Blob &outBlob = outputs[ii];
CV_Assert(inpBlob.channels() == blobs[0].total());
if (hasBias)
CV_Assert(inpBlob.channels() == blobs[1].total());
for (int n = 0; n < inpBlob.channels(); n++)
{
float w = blobs[0].matRefConst().at<float>(n);
float b = hasBias ? blobs[1].matRefConst().at<float>(n) : 0;
outBlob.getPlane(0, n) = w*inpBlob.getPlane(0, n) + b;
}
}
}
Ptr<ScaleLayer> ScaleLayer::create(bool hasBias)
{
return Ptr<ScaleLayer>(new ScaleLayerImpl(hasBias));
}
} // namespace dnn
} // namespace cv

36
modules/dnn/src/layers/scale_layer.hpp
Unescape View File

@ -0,0 +1,36 @@
// This file is part of OpenCV project.
// It is subject to the license terms in the LICENSE file found in the top-level directory
// of this distribution and at http://opencv.org/license.html.
// Copyright (C) 2016, Intel Corporation, all rights reserved.
// Third party copyrights are property of their respective owners.
/*
Declaration of scale layer, which multiplies and shifts channels in input blob.
*/
#ifndef __OPENCV_DNN_LAYERS_SCALE_LAYER_HPP__
#define __OPENCV_DNN_LAYERS_SCALE_LAYER_HPP__
#include <opencv2/dnn/all_layers.hpp>
namespace cv
{
namespace dnn
{
class ScaleLayerImpl : public ScaleLayer
{
public:
ScaleLayerImpl(bool hasBias_): hasBias(hasBias_) {}
void allocate(const std::vector<Blob*> &inputs, std::vector<Blob> &outputs);
void forward(std::vector<Blob*> &inputs, std::vector<Blob> &outputs);
private:
bool hasBias;
};
}
}
#endif // __OPENCV_DNN_LAYERS_SCALE_LAYER_HPP__

10
modules/dnn/src/torch/torch_importer.cpp
Unescape View File

@ -575,21 +575,19 @@ struct TorchImporter : public ::cv::dnn::Importer
layerParams.blobs.push_back(tensorParams["running_var"].second);
CV_Assert(scalarParams.has("eps"));
layerParams.set("eps", float(scalarParams.get<double>("eps")));
layerParams.blobs.push_back(Blob());
layerParams.blobs.push_back(Blob());
float eps = float(scalarParams.get<double>("eps"));
layerParams.set("eps", eps);
if (tensorParams.count("weight"))
{
layerParams.set("has_weight", true);
layerParams.blobs[2] = tensorParams["weight"].second;
layerParams.blobs.push_back(tensorParams["weight"].second);
}
if (tensorParams.count("bias"))
{
layerParams.set("has_bias", true);
layerParams.blobs[3] = tensorParams["bias"].second;
layerParams.blobs.push_back(tensorParams["bias"].second);
}
curModule->modules.push_back(newModule);

5
modules/dnn/test/test_layers.cpp
Unescape View File

@ -215,6 +215,11 @@ TEST(Layer_Test_Reshape, squeeze)
EXPECT_EQ(outVec[0].shape(), BlobShape(4, 3, 2));
}
TEST(Layer_Test_BatchNorm, Accuracy)
{
OCL_OFF(testLayerUsingCaffeModels("layer_batch_norm", true));
}
//template<typename XMat>
//static void test_Layer_Concat()
//{

5
modules/dnn/test/test_torch_importer.cpp
Unescape View File

@ -135,6 +135,11 @@ TEST(Torch_Importer, run_deconv)
runTorchNet("net_deconv", "", false);
}
TEST(Torch_Importer, run_batch_norm)
{
runTorchNet("net_batch_norm", "", false);
}
#if defined(ENABLE_TORCH_ENET_TESTS)
TEST(Torch_Importer, ENet_accuracy)

7
modules/dnn/testdata/dnn/torch/torch_gen_test_data.lua vendored
Unescape View File

@ -12,6 +12,9 @@ function fill_net(net)
if net.bias then
net.bias = torch.rand(net.bias:size())
end
if net.train then
net.train = 0
end
end
function save(net, input, label)
@ -69,3 +72,7 @@ save(net_concat, torch.rand(2, 6, 4, 3) - 0.5, 'net_concat')
local net_deconv = nn.Sequential()
net_deconv:add(nn.SpatialFullConvolution(3, 9, 4, 5, 1, 2, 0, 1, 0, 1))
save(net_deconv, torch.rand(2, 3, 4, 3) - 0.5, 'net_deconv')
local net_batch_norm = nn.Sequential()
net_batch_norm:add(nn.SpatialBatchNormalization(3))
save(net_batch_norm, torch.rand(1, 3, 4, 3) - 0.5, 'net_batch_norm')
Write Preview
Loading…
Cancel
Save