From: Dmitry Kurtaev Date: Wed, 13 Dec 2017 16:06:30 +0000 (+0300) Subject: Faster-RCNN models support X-Git-Tag: accepted/tizen/6.0/unified/20201030.111113~286^2 X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=08112f3821745c9792a1dcd7c60dea96b5843343;p=platform%2Fupstream%2Fopencv.git Faster-RCNN models support --- diff --git a/modules/dnn/include/opencv2/dnn/all_layers.hpp b/modules/dnn/include/opencv2/dnn/all_layers.hpp index 4822918..b0d78f5 100644 --- a/modules/dnn/include/opencv2/dnn/all_layers.hpp +++ b/modules/dnn/include/opencv2/dnn/all_layers.hpp @@ -74,7 +74,7 @@ CV__DNN_EXPERIMENTAL_NS_BEGIN class CV_EXPORTS BlankLayer : public Layer { public: - static Ptr create(const LayerParams ¶ms); + static Ptr create(const LayerParams ¶ms); }; //! LSTM recurrent layer @@ -567,6 +567,12 @@ CV__DNN_EXPERIMENTAL_NS_BEGIN static Ptr create(const LayerParams& params); }; + class CV_EXPORTS ProposalLayer : public Layer + { + public: + static Ptr create(const LayerParams& params); + }; + //! @} //! @} CV__DNN_EXPERIMENTAL_NS_END diff --git a/modules/dnn/misc/caffe/opencv-caffe.pb.cc b/modules/dnn/misc/caffe/opencv-caffe.pb.cc index 4051470..a7db718 100644 --- a/modules/dnn/misc/caffe/opencv-caffe.pb.cc +++ b/modules/dnn/misc/caffe/opencv-caffe.pb.cc @@ -253,6 +253,9 @@ const ::google::protobuf::internal::GeneratedMessageReflection* const ::google::protobuf::Descriptor* ROIPoolingParameter_descriptor_ = NULL; const ::google::protobuf::internal::GeneratedMessageReflection* ROIPoolingParameter_reflection_ = NULL; +const ::google::protobuf::Descriptor* ProposalParameter_descriptor_ = NULL; +const ::google::protobuf::internal::GeneratedMessageReflection* + ProposalParameter_reflection_ = NULL; const ::google::protobuf::EnumDescriptor* Type_descriptor_ = NULL; const ::google::protobuf::EnumDescriptor* Phase_descriptor_ = NULL; @@ -592,7 +595,7 @@ void protobuf_AssignDesc_opencv_2dcaffe_2eproto() { GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(ParamSpec, _internal_metadata_)); ParamSpec_DimCheckMode_descriptor_ = ParamSpec_descriptor_->enum_type(0); LayerParameter_descriptor_ = file->message_type(15); - static const int LayerParameter_offsets_[63] = { + static const int LayerParameter_offsets_[64] = { GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(LayerParameter, name_), GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(LayerParameter, type_), GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(LayerParameter, bottom_), @@ -641,6 +644,7 @@ void protobuf_AssignDesc_opencv_2dcaffe_2eproto() { GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(LayerParameter, power_param_), GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(LayerParameter, prelu_param_), GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(LayerParameter, prior_box_param_), + GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(LayerParameter, proposal_param_), GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(LayerParameter, python_param_), GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(LayerParameter, recurrent_param_), GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(LayerParameter, reduction_param_), @@ -905,8 +909,9 @@ void protobuf_AssignDesc_opencv_2dcaffe_2eproto() { sizeof(SaveOutputParameter), GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(SaveOutputParameter, _internal_metadata_)); DropoutParameter_descriptor_ = file->message_type(29); - static const int DropoutParameter_offsets_[1] = { + static const int DropoutParameter_offsets_[2] = { GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(DropoutParameter, dropout_ratio_), + GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(DropoutParameter, scale_train_), }; DropoutParameter_reflection_ = ::google::protobuf::internal::GeneratedMessageReflection::NewGeneratedMessageReflection( @@ -1661,6 +1666,27 @@ void protobuf_AssignDesc_opencv_2dcaffe_2eproto() { -1, sizeof(ROIPoolingParameter), GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(ROIPoolingParameter, _internal_metadata_)); + ProposalParameter_descriptor_ = file->message_type(69); + static const int ProposalParameter_offsets_[8] = { + GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(ProposalParameter, feat_stride_), + GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(ProposalParameter, base_size_), + GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(ProposalParameter, min_size_), + GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(ProposalParameter, ratio_), + GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(ProposalParameter, scale_), + GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(ProposalParameter, pre_nms_topn_), + GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(ProposalParameter, post_nms_topn_), + GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(ProposalParameter, nms_thresh_), + }; + ProposalParameter_reflection_ = + ::google::protobuf::internal::GeneratedMessageReflection::NewGeneratedMessageReflection( + ProposalParameter_descriptor_, + ProposalParameter::internal_default_instance(), + ProposalParameter_offsets_, + GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(ProposalParameter, _has_bits_), + -1, + -1, + sizeof(ProposalParameter), + GOOGLE_PROTOBUF_GENERATED_MESSAGE_FIELD_OFFSET(ProposalParameter, _internal_metadata_)); Type_descriptor_ = file->enum_type(0); Phase_descriptor_ = file->enum_type(1); } @@ -1814,6 +1840,8 @@ void protobuf_RegisterTypes(const ::std::string&) { NormalizedBBox_descriptor_, NormalizedBBox::internal_default_instance()); ::google::protobuf::MessageFactory::InternalRegisterGeneratedMessage( ROIPoolingParameter_descriptor_, ROIPoolingParameter::internal_default_instance()); + ::google::protobuf::MessageFactory::InternalRegisterGeneratedMessage( + ProposalParameter_descriptor_, ProposalParameter::internal_default_instance()); } } // namespace @@ -1962,6 +1990,8 @@ void protobuf_ShutdownFile_opencv_2dcaffe_2eproto() { delete NormalizedBBox_reflection_; ROIPoolingParameter_default_instance_.Shutdown(); delete ROIPoolingParameter_reflection_; + ProposalParameter_default_instance_.Shutdown(); + delete ProposalParameter_reflection_; } void protobuf_InitDefaults_opencv_2dcaffe_2eproto_impl() { @@ -2067,6 +2097,7 @@ void protobuf_InitDefaults_opencv_2dcaffe_2eproto_impl() { PReLUParameter_default_instance_.DefaultConstruct(); NormalizedBBox_default_instance_.DefaultConstruct(); ROIPoolingParameter_default_instance_.DefaultConstruct(); + ProposalParameter_default_instance_.DefaultConstruct(); BlobShape_default_instance_.get_mutable()->InitAsDefaultInstance(); BlobProto_default_instance_.get_mutable()->InitAsDefaultInstance(); BlobProtoVector_default_instance_.get_mutable()->InitAsDefaultInstance(); @@ -2136,6 +2167,7 @@ void protobuf_InitDefaults_opencv_2dcaffe_2eproto_impl() { PReLUParameter_default_instance_.get_mutable()->InitAsDefaultInstance(); NormalizedBBox_default_instance_.get_mutable()->InitAsDefaultInstance(); ROIPoolingParameter_default_instance_.get_mutable()->InitAsDefaultInstance(); + ProposalParameter_default_instance_.get_mutable()->InitAsDefaultInstance(); } GOOGLE_PROTOBUF_DECLARE_ONCE(protobuf_InitDefaults_opencv_2dcaffe_2eproto_once_); @@ -2246,7 +2278,7 @@ void protobuf_AddDesc_opencv_2dcaffe_2eproto_impl() { "\t\0228\n\nshare_mode\030\002 \001(\0162$.opencv_caffe.Par" "amSpec.DimCheckMode\022\022\n\007lr_mult\030\003 \001(\002:\0011\022" "\025\n\ndecay_mult\030\004 \001(\002:\0011\"*\n\014DimCheckMode\022\n" - "\n\006STRICT\020\000\022\016\n\nPERMISSIVE\020\001\"\246\031\n\016LayerPara" + "\n\006STRICT\020\000\022\016\n\nPERMISSIVE\020\001\"\340\031\n\016LayerPara" "meter\022\014\n\004name\030\001 \001(\t\022\014\n\004type\030\002 \001(\t\022\016\n\006bot" "tom\030\003 \003(\t\022\013\n\003top\030\004 \003(\t\022\"\n\005phase\030\n \001(\0162\023." "opencv_caffe.Phase\022\023\n\013loss_weight\030\005 \003(\002\022" @@ -2307,306 +2339,313 @@ void protobuf_AddDesc_opencv_2dcaffe_2eproto_impl() { "Parameter\0222\n\013prelu_param\030\203\001 \001(\0132\034.opencv" "_caffe.PReLUParameter\0229\n\017prior_box_param" "\030\226\001 \001(\0132\037.opencv_caffe.PriorBoxParameter" - "\0224\n\014python_param\030\202\001 \001(\0132\035.opencv_caffe.P" - "ythonParameter\022:\n\017recurrent_param\030\222\001 \001(\013" - "2 .opencv_caffe.RecurrentParameter\022:\n\017re" - "duction_param\030\210\001 \001(\0132 .opencv_caffe.Redu" - "ctionParameter\022/\n\nrelu_param\030{ \001(\0132\033.ope" - "ncv_caffe.ReLUParameter\0226\n\rreshape_param" - "\030\205\001 \001(\0132\036.opencv_caffe.ReshapeParameter\022" - "\?\n\021roi_pooling_param\030\327\307\370\003 \001(\0132!.opencv_c" - "affe.ROIPoolingParameter\0222\n\013scale_param\030" - "\216\001 \001(\0132\034.opencv_caffe.ScaleParameter\0225\n\r" - "sigmoid_param\030| \001(\0132\036.opencv_caffe.Sigmo" - "idParameter\0225\n\rsoftmax_param\030} \001(\0132\036.ope" - "ncv_caffe.SoftmaxParameter\022.\n\tspp_param\030" - "\204\001 \001(\0132\032.opencv_caffe.SPPParameter\0221\n\013sl" - "ice_param\030~ \001(\0132\034.opencv_caffe.SlicePara" - "meter\022/\n\ntanh_param\030\177 \001(\0132\033.opencv_caffe" - ".TanHParameter\022:\n\017threshold_param\030\200\001 \001(\013" - "2 .opencv_caffe.ThresholdParameter\0220\n\nti" - "le_param\030\212\001 \001(\0132\033.opencv_caffe.TileParam" - "eter\022=\n\021window_data_param\030\201\001 \001(\0132!.openc" - "v_caffe.WindowDataParameter\"\266\001\n\027Transfor" - "mationParameter\022\020\n\005scale\030\001 \001(\002:\0011\022\025\n\006mir" - "ror\030\002 \001(\010:\005false\022\024\n\tcrop_size\030\003 \001(\r:\0010\022\021" - "\n\tmean_file\030\004 \001(\t\022\022\n\nmean_value\030\005 \003(\002\022\032\n" - "\013force_color\030\006 \001(\010:\005false\022\031\n\nforce_gray\030" - "\007 \001(\010:\005false\"\311\001\n\rLossParameter\022\024\n\014ignore" - "_label\030\001 \001(\005\022K\n\rnormalization\030\003 \001(\0162-.op" - "encv_caffe.LossParameter.NormalizationMo" - "de:\005VALID\022\021\n\tnormalize\030\002 \001(\010\"B\n\021Normaliz" - "ationMode\022\010\n\004FULL\020\000\022\t\n\005VALID\020\001\022\016\n\nBATCH_" - "SIZE\020\002\022\010\n\004NONE\020\003\"L\n\021AccuracyParameter\022\020\n" - "\005top_k\030\001 \001(\r:\0011\022\017\n\004axis\030\002 \001(\005:\0011\022\024\n\014igno" - "re_label\030\003 \001(\005\"M\n\017ArgMaxParameter\022\032\n\013out" - "_max_val\030\001 \001(\010:\005false\022\020\n\005top_k\030\002 \001(\r:\0011\022" - "\014\n\004axis\030\003 \001(\005\"9\n\017ConcatParameter\022\017\n\004axis" - "\030\002 \001(\005:\0011\022\025\n\nconcat_dim\030\001 \001(\r:\0011\"j\n\022Batc" - "hNormParameter\022\030\n\020use_global_stats\030\001 \001(\010" - "\022&\n\027moving_average_fraction\030\002 \001(\002:\0050.999" - "\022\022\n\003eps\030\003 \001(\002:\0051e-05\"d\n\rBiasParameter\022\017\n" - "\004axis\030\001 \001(\005:\0011\022\023\n\010num_axes\030\002 \001(\005:\0011\022-\n\006f" - "iller\030\003 \001(\0132\035.opencv_caffe.FillerParamet" - "er\"L\n\030ContrastiveLossParameter\022\021\n\006margin" - "\030\001 \001(\002:\0011\022\035\n\016legacy_version\030\002 \001(\010:\005false" - "\"\221\004\n\024ConvolutionParameter\022\022\n\nnum_output\030" - "\001 \001(\r\022\027\n\tbias_term\030\002 \001(\010:\004true\022\013\n\003pad\030\003 " - "\003(\r\022\023\n\013kernel_size\030\004 \003(\r\022\016\n\006stride\030\006 \003(\r" - "\022\020\n\010dilation\030\022 \003(\r\022\020\n\005pad_h\030\t \001(\r:\0010\022\020\n\005" - "pad_w\030\n \001(\r:\0010\022\020\n\010kernel_h\030\013 \001(\r\022\020\n\010kern" - "el_w\030\014 \001(\r\022\020\n\010stride_h\030\r \001(\r\022\020\n\010stride_w" - "\030\016 \001(\r\022\020\n\005group\030\005 \001(\r:\0011\0224\n\rweight_fille" - "r\030\007 \001(\0132\035.opencv_caffe.FillerParameter\0222" - "\n\013bias_filler\030\010 \001(\0132\035.opencv_caffe.Fille" - "rParameter\022B\n\006engine\030\017 \001(\0162).opencv_caff" - "e.ConvolutionParameter.Engine:\007DEFAULT\022\017" - "\n\004axis\030\020 \001(\005:\0011\022\036\n\017force_nd_im2col\030\021 \001(\010" - ":\005false\"+\n\006Engine\022\013\n\007DEFAULT\020\000\022\t\n\005CAFFE\020" - "\001\022\t\n\005CUDNN\020\002\"0\n\rCropParameter\022\017\n\004axis\030\001 " - "\001(\005:\0012\022\016\n\006offset\030\002 \003(\r\"\253\002\n\rDataParameter" - "\022\016\n\006source\030\001 \001(\t\022\022\n\nbatch_size\030\004 \001(\r\022\024\n\t" - "rand_skip\030\007 \001(\r:\0010\0228\n\007backend\030\010 \001(\0162\036.op" - "encv_caffe.DataParameter.DB:\007LEVELDB\022\020\n\005" - "scale\030\002 \001(\002:\0011\022\021\n\tmean_file\030\003 \001(\t\022\024\n\tcro" - "p_size\030\005 \001(\r:\0010\022\025\n\006mirror\030\006 \001(\010:\005false\022\"" - "\n\023force_encoded_color\030\t \001(\010:\005false\022\023\n\010pr" - "efetch\030\n \001(\r:\0014\"\033\n\002DB\022\013\n\007LEVELDB\020\000\022\010\n\004LM" - "DB\020\001\"[\n\036NonMaximumSuppressionParameter\022\032" - "\n\rnms_threshold\030\001 \001(\002:\0030.3\022\r\n\005top_k\030\002 \001(" - "\005\022\016\n\003eta\030\003 \001(\002:\0011\"\252\001\n\023SaveOutputParamete" - "r\022\030\n\020output_directory\030\001 \001(\t\022\032\n\022output_na" - "me_prefix\030\002 \001(\t\022\025\n\routput_format\030\003 \001(\t\022\026" - "\n\016label_map_file\030\004 \001(\t\022\026\n\016name_size_file" - "\030\005 \001(\t\022\026\n\016num_test_image\030\006 \001(\r\".\n\020Dropou" - "tParameter\022\032\n\rdropout_ratio\030\001 \001(\002:\0030.5\"\256" - "\001\n\022DummyDataParameter\0222\n\013data_filler\030\001 \003" - "(\0132\035.opencv_caffe.FillerParameter\022&\n\005sha" - "pe\030\006 \003(\0132\027.opencv_caffe.BlobShape\022\013\n\003num" - "\030\002 \003(\r\022\020\n\010channels\030\003 \003(\r\022\016\n\006height\030\004 \003(\r" - "\022\r\n\005width\030\005 \003(\r\"\254\001\n\020EltwiseParameter\022@\n\t" - "operation\030\001 \001(\0162(.opencv_caffe.EltwisePa" - "rameter.EltwiseOp:\003SUM\022\r\n\005coeff\030\002 \003(\002\022\036\n" - "\020stable_prod_grad\030\003 \001(\010:\004true\"\'\n\tEltwise" - "Op\022\010\n\004PROD\020\000\022\007\n\003SUM\020\001\022\007\n\003MAX\020\002\" \n\014ELUPar" - "ameter\022\020\n\005alpha\030\001 \001(\002:\0011\"\272\001\n\016EmbedParame" - "ter\022\022\n\nnum_output\030\001 \001(\r\022\021\n\tinput_dim\030\002 \001" - "(\r\022\027\n\tbias_term\030\003 \001(\010:\004true\0224\n\rweight_fi" - "ller\030\004 \001(\0132\035.opencv_caffe.FillerParamete" - "r\0222\n\013bias_filler\030\005 \001(\0132\035.opencv_caffe.Fi" - "llerParameter\"D\n\014ExpParameter\022\020\n\004base\030\001 " - "\001(\002:\002-1\022\020\n\005scale\030\002 \001(\002:\0011\022\020\n\005shift\030\003 \001(\002" - ":\0010\"9\n\020FlattenParameter\022\017\n\004axis\030\001 \001(\005:\0011" - "\022\024\n\010end_axis\030\002 \001(\005:\002-1\"O\n\021HDF5DataParame" - "ter\022\016\n\006source\030\001 \001(\t\022\022\n\nbatch_size\030\002 \001(\r\022" - "\026\n\007shuffle\030\003 \001(\010:\005false\"(\n\023HDF5OutputPar" - "ameter\022\021\n\tfile_name\030\001 \001(\t\"e\n\022HingeLossPa" - "rameter\0227\n\004norm\030\001 \001(\0162%.opencv_caffe.Hin" - "geLossParameter.Norm:\002L1\"\026\n\004Norm\022\006\n\002L1\020\001" - "\022\006\n\002L2\020\002\"\227\002\n\022ImageDataParameter\022\016\n\006sourc" - "e\030\001 \001(\t\022\025\n\nbatch_size\030\004 \001(\r:\0011\022\024\n\trand_s" - "kip\030\007 \001(\r:\0010\022\026\n\007shuffle\030\010 \001(\010:\005false\022\025\n\n" - "new_height\030\t \001(\r:\0010\022\024\n\tnew_width\030\n \001(\r:\001" - "0\022\026\n\010is_color\030\013 \001(\010:\004true\022\020\n\005scale\030\002 \001(\002" - ":\0011\022\021\n\tmean_file\030\003 \001(\t\022\024\n\tcrop_size\030\005 \001(" - "\r:\0010\022\025\n\006mirror\030\006 \001(\010:\005false\022\025\n\013root_fold" - "er\030\014 \001(\t:\000\"\'\n\025InfogainLossParameter\022\016\n\006s" - "ource\030\001 \001(\t\"\331\001\n\025InnerProductParameter\022\022\n" - "\nnum_output\030\001 \001(\r\022\027\n\tbias_term\030\002 \001(\010:\004tr" - "ue\0224\n\rweight_filler\030\003 \001(\0132\035.opencv_caffe" - ".FillerParameter\0222\n\013bias_filler\030\004 \001(\0132\035." - "opencv_caffe.FillerParameter\022\017\n\004axis\030\005 \001" - "(\005:\0011\022\030\n\ttranspose\030\006 \001(\010:\005false\"8\n\016Input" - "Parameter\022&\n\005shape\030\001 \003(\0132\027.opencv_caffe." - "BlobShape\"D\n\014LogParameter\022\020\n\004base\030\001 \001(\002:" - "\002-1\022\020\n\005scale\030\002 \001(\002:\0011\022\020\n\005shift\030\003 \001(\002:\0010\"" - "\306\002\n\014LRNParameter\022\025\n\nlocal_size\030\001 \001(\r:\0015\022" - "\020\n\005alpha\030\002 \001(\002:\0011\022\022\n\004beta\030\003 \001(\002:\0040.75\022K\n" - "\013norm_region\030\004 \001(\0162%.opencv_caffe.LRNPar" - "ameter.NormRegion:\017ACROSS_CHANNELS\022\014\n\001k\030" - "\005 \001(\002:\0011\022:\n\006engine\030\006 \001(\0162!.opencv_caffe." - "LRNParameter.Engine:\007DEFAULT\"5\n\nNormRegi" - "on\022\023\n\017ACROSS_CHANNELS\020\000\022\022\n\016WITHIN_CHANNE" - "L\020\001\"+\n\006Engine\022\013\n\007DEFAULT\020\000\022\t\n\005CAFFE\020\001\022\t\n" - "\005CUDNN\020\002\"Z\n\023MemoryDataParameter\022\022\n\nbatch" - "_size\030\001 \001(\r\022\020\n\010channels\030\002 \001(\r\022\016\n\006height\030" - "\003 \001(\r\022\r\n\005width\030\004 \001(\r\"d\n\014MVNParameter\022 \n\022" - "normalize_variance\030\001 \001(\010:\004true\022\036\n\017across" - "_channels\030\002 \001(\010:\005false\022\022\n\003eps\030\003 \001(\002:\0051e-" - "09\"<\n\022ParameterParameter\022&\n\005shape\030\001 \001(\0132" - "\027.opencv_caffe.BlobShape\"\311\003\n\020PoolingPara" - "meter\022<\n\004pool\030\001 \001(\0162).opencv_caffe.Pooli" - "ngParameter.PoolMethod:\003MAX\022\016\n\003pad\030\004 \001(\r" - ":\0010\022\020\n\005pad_h\030\t \001(\r:\0010\022\020\n\005pad_w\030\n \001(\r:\0010\022" - "\023\n\013kernel_size\030\002 \001(\r\022\020\n\010kernel_h\030\005 \001(\r\022\020" - "\n\010kernel_w\030\006 \001(\r\022\021\n\006stride\030\003 \001(\r:\0011\022\020\n\010s" - "tride_h\030\007 \001(\r\022\020\n\010stride_w\030\010 \001(\r\022>\n\006engin" - "e\030\013 \001(\0162%.opencv_caffe.PoolingParameter." - "Engine:\007DEFAULT\022\035\n\016global_pooling\030\014 \001(\010:" - "\005false\022\027\n\tceil_mode\030\r \001(\010:\004true\".\n\nPoolM" - "ethod\022\007\n\003MAX\020\000\022\007\n\003AVE\020\001\022\016\n\nSTOCHASTIC\020\002\"" - "+\n\006Engine\022\013\n\007DEFAULT\020\000\022\t\n\005CAFFE\020\001\022\t\n\005CUD" - "NN\020\002\"F\n\016PowerParameter\022\020\n\005power\030\001 \001(\002:\0011" - "\022\020\n\005scale\030\002 \001(\002:\0011\022\020\n\005shift\030\003 \001(\002:\0010\"g\n\017" - "PythonParameter\022\016\n\006module\030\001 \001(\t\022\r\n\005layer" - "\030\002 \001(\t\022\023\n\tparam_str\030\003 \001(\t:\000\022 \n\021share_in_" - "parallel\030\004 \001(\010:\005false\"\316\001\n\022RecurrentParam" - "eter\022\025\n\nnum_output\030\001 \001(\r:\0010\0224\n\rweight_fi" - "ller\030\002 \001(\0132\035.opencv_caffe.FillerParamete" - "r\0222\n\013bias_filler\030\003 \001(\0132\035.opencv_caffe.Fi" - "llerParameter\022\031\n\ndebug_info\030\004 \001(\010:\005false" - "\022\034\n\rexpose_hidden\030\005 \001(\010:\005false\"\264\001\n\022Reduc" - "tionParameter\022D\n\toperation\030\001 \001(\0162,.openc" - "v_caffe.ReductionParameter.ReductionOp:\003" - "SUM\022\017\n\004axis\030\002 \001(\005:\0010\022\020\n\005coeff\030\003 \001(\002:\0011\"5" - "\n\013ReductionOp\022\007\n\003SUM\020\001\022\010\n\004ASUM\020\002\022\t\n\005SUMS" - "Q\020\003\022\010\n\004MEAN\020\004\"\224\001\n\rReLUParameter\022\031\n\016negat" - "ive_slope\030\001 \001(\002:\0010\022;\n\006engine\030\002 \001(\0162\".ope" - "ncv_caffe.ReLUParameter.Engine:\007DEFAULT\"" + "\0228\n\016proposal_param\030\311\001 \001(\0132\037.opencv_caffe" + ".ProposalParameter\0224\n\014python_param\030\202\001 \001(" + "\0132\035.opencv_caffe.PythonParameter\022:\n\017recu" + "rrent_param\030\222\001 \001(\0132 .opencv_caffe.Recurr" + "entParameter\022:\n\017reduction_param\030\210\001 \001(\0132 " + ".opencv_caffe.ReductionParameter\022/\n\nrelu" + "_param\030{ \001(\0132\033.opencv_caffe.ReLUParamete" + "r\0226\n\rreshape_param\030\205\001 \001(\0132\036.opencv_caffe" + ".ReshapeParameter\022\?\n\021roi_pooling_param\030\327" + "\307\370\003 \001(\0132!.opencv_caffe.ROIPoolingParamet" + "er\0222\n\013scale_param\030\216\001 \001(\0132\034.opencv_caffe." + "ScaleParameter\0225\n\rsigmoid_param\030| \001(\0132\036." + "opencv_caffe.SigmoidParameter\0225\n\rsoftmax" + "_param\030} \001(\0132\036.opencv_caffe.SoftmaxParam" + "eter\022.\n\tspp_param\030\204\001 \001(\0132\032.opencv_caffe." + "SPPParameter\0221\n\013slice_param\030~ \001(\0132\034.open" + "cv_caffe.SliceParameter\022/\n\ntanh_param\030\177 " + "\001(\0132\033.opencv_caffe.TanHParameter\022:\n\017thre" + "shold_param\030\200\001 \001(\0132 .opencv_caffe.Thresh" + "oldParameter\0220\n\ntile_param\030\212\001 \001(\0132\033.open" + "cv_caffe.TileParameter\022=\n\021window_data_pa" + "ram\030\201\001 \001(\0132!.opencv_caffe.WindowDataPara" + "meter\"\266\001\n\027TransformationParameter\022\020\n\005sca" + "le\030\001 \001(\002:\0011\022\025\n\006mirror\030\002 \001(\010:\005false\022\024\n\tcr" + "op_size\030\003 \001(\r:\0010\022\021\n\tmean_file\030\004 \001(\t\022\022\n\nm" + "ean_value\030\005 \003(\002\022\032\n\013force_color\030\006 \001(\010:\005fa" + "lse\022\031\n\nforce_gray\030\007 \001(\010:\005false\"\311\001\n\rLossP" + "arameter\022\024\n\014ignore_label\030\001 \001(\005\022K\n\rnormal" + "ization\030\003 \001(\0162-.opencv_caffe.LossParamet" + "er.NormalizationMode:\005VALID\022\021\n\tnormalize" + "\030\002 \001(\010\"B\n\021NormalizationMode\022\010\n\004FULL\020\000\022\t\n" + "\005VALID\020\001\022\016\n\nBATCH_SIZE\020\002\022\010\n\004NONE\020\003\"L\n\021Ac" + "curacyParameter\022\020\n\005top_k\030\001 \001(\r:\0011\022\017\n\004axi" + "s\030\002 \001(\005:\0011\022\024\n\014ignore_label\030\003 \001(\005\"M\n\017ArgM" + "axParameter\022\032\n\013out_max_val\030\001 \001(\010:\005false\022" + "\020\n\005top_k\030\002 \001(\r:\0011\022\014\n\004axis\030\003 \001(\005\"9\n\017Conca" + "tParameter\022\017\n\004axis\030\002 \001(\005:\0011\022\025\n\nconcat_di" + "m\030\001 \001(\r:\0011\"j\n\022BatchNormParameter\022\030\n\020use_" + "global_stats\030\001 \001(\010\022&\n\027moving_average_fra" + "ction\030\002 \001(\002:\0050.999\022\022\n\003eps\030\003 \001(\002:\0051e-05\"d" + "\n\rBiasParameter\022\017\n\004axis\030\001 \001(\005:\0011\022\023\n\010num_" + "axes\030\002 \001(\005:\0011\022-\n\006filler\030\003 \001(\0132\035.opencv_c" + "affe.FillerParameter\"L\n\030ContrastiveLossP" + "arameter\022\021\n\006margin\030\001 \001(\002:\0011\022\035\n\016legacy_ve" + "rsion\030\002 \001(\010:\005false\"\221\004\n\024ConvolutionParame" + "ter\022\022\n\nnum_output\030\001 \001(\r\022\027\n\tbias_term\030\002 \001" + "(\010:\004true\022\013\n\003pad\030\003 \003(\r\022\023\n\013kernel_size\030\004 \003" + "(\r\022\016\n\006stride\030\006 \003(\r\022\020\n\010dilation\030\022 \003(\r\022\020\n\005" + "pad_h\030\t \001(\r:\0010\022\020\n\005pad_w\030\n \001(\r:\0010\022\020\n\010kern" + "el_h\030\013 \001(\r\022\020\n\010kernel_w\030\014 \001(\r\022\020\n\010stride_h" + "\030\r \001(\r\022\020\n\010stride_w\030\016 \001(\r\022\020\n\005group\030\005 \001(\r:" + "\0011\0224\n\rweight_filler\030\007 \001(\0132\035.opencv_caffe" + ".FillerParameter\0222\n\013bias_filler\030\010 \001(\0132\035." + "opencv_caffe.FillerParameter\022B\n\006engine\030\017" + " \001(\0162).opencv_caffe.ConvolutionParameter" + ".Engine:\007DEFAULT\022\017\n\004axis\030\020 \001(\005:\0011\022\036\n\017for" + "ce_nd_im2col\030\021 \001(\010:\005false\"+\n\006Engine\022\013\n\007D" + "EFAULT\020\000\022\t\n\005CAFFE\020\001\022\t\n\005CUDNN\020\002\"0\n\rCropPa" + "rameter\022\017\n\004axis\030\001 \001(\005:\0012\022\016\n\006offset\030\002 \003(\r" + "\"\253\002\n\rDataParameter\022\016\n\006source\030\001 \001(\t\022\022\n\nba" + "tch_size\030\004 \001(\r\022\024\n\trand_skip\030\007 \001(\r:\0010\0228\n\007" + "backend\030\010 \001(\0162\036.opencv_caffe.DataParamet" + "er.DB:\007LEVELDB\022\020\n\005scale\030\002 \001(\002:\0011\022\021\n\tmean" + "_file\030\003 \001(\t\022\024\n\tcrop_size\030\005 \001(\r:\0010\022\025\n\006mir" + "ror\030\006 \001(\010:\005false\022\"\n\023force_encoded_color\030" + "\t \001(\010:\005false\022\023\n\010prefetch\030\n \001(\r:\0014\"\033\n\002DB\022" + "\013\n\007LEVELDB\020\000\022\010\n\004LMDB\020\001\"[\n\036NonMaximumSupp" + "ressionParameter\022\032\n\rnms_threshold\030\001 \001(\002:" + "\0030.3\022\r\n\005top_k\030\002 \001(\005\022\016\n\003eta\030\003 \001(\002:\0011\"\252\001\n\023" + "SaveOutputParameter\022\030\n\020output_directory\030" + "\001 \001(\t\022\032\n\022output_name_prefix\030\002 \001(\t\022\025\n\rout" + "put_format\030\003 \001(\t\022\026\n\016label_map_file\030\004 \001(\t" + "\022\026\n\016name_size_file\030\005 \001(\t\022\026\n\016num_test_ima" + "ge\030\006 \001(\r\"I\n\020DropoutParameter\022\032\n\rdropout_" + "ratio\030\001 \001(\002:\0030.5\022\031\n\013scale_train\030\002 \001(\010:\004t" + "rue\"\256\001\n\022DummyDataParameter\0222\n\013data_fille" + "r\030\001 \003(\0132\035.opencv_caffe.FillerParameter\022&" + "\n\005shape\030\006 \003(\0132\027.opencv_caffe.BlobShape\022\013" + "\n\003num\030\002 \003(\r\022\020\n\010channels\030\003 \003(\r\022\016\n\006height\030" + "\004 \003(\r\022\r\n\005width\030\005 \003(\r\"\254\001\n\020EltwiseParamete" + "r\022@\n\toperation\030\001 \001(\0162(.opencv_caffe.Eltw" + "iseParameter.EltwiseOp:\003SUM\022\r\n\005coeff\030\002 \003" + "(\002\022\036\n\020stable_prod_grad\030\003 \001(\010:\004true\"\'\n\tEl" + "twiseOp\022\010\n\004PROD\020\000\022\007\n\003SUM\020\001\022\007\n\003MAX\020\002\" \n\014E" + "LUParameter\022\020\n\005alpha\030\001 \001(\002:\0011\"\272\001\n\016EmbedP" + "arameter\022\022\n\nnum_output\030\001 \001(\r\022\021\n\tinput_di" + "m\030\002 \001(\r\022\027\n\tbias_term\030\003 \001(\010:\004true\0224\n\rweig" + "ht_filler\030\004 \001(\0132\035.opencv_caffe.FillerPar" + "ameter\0222\n\013bias_filler\030\005 \001(\0132\035.opencv_caf" + "fe.FillerParameter\"D\n\014ExpParameter\022\020\n\004ba" + "se\030\001 \001(\002:\002-1\022\020\n\005scale\030\002 \001(\002:\0011\022\020\n\005shift\030" + "\003 \001(\002:\0010\"9\n\020FlattenParameter\022\017\n\004axis\030\001 \001" + "(\005:\0011\022\024\n\010end_axis\030\002 \001(\005:\002-1\"O\n\021HDF5DataP" + "arameter\022\016\n\006source\030\001 \001(\t\022\022\n\nbatch_size\030\002" + " \001(\r\022\026\n\007shuffle\030\003 \001(\010:\005false\"(\n\023HDF5Outp" + "utParameter\022\021\n\tfile_name\030\001 \001(\t\"e\n\022HingeL" + "ossParameter\0227\n\004norm\030\001 \001(\0162%.opencv_caff" + "e.HingeLossParameter.Norm:\002L1\"\026\n\004Norm\022\006\n" + "\002L1\020\001\022\006\n\002L2\020\002\"\227\002\n\022ImageDataParameter\022\016\n\006" + "source\030\001 \001(\t\022\025\n\nbatch_size\030\004 \001(\r:\0011\022\024\n\tr" + "and_skip\030\007 \001(\r:\0010\022\026\n\007shuffle\030\010 \001(\010:\005fals" + "e\022\025\n\nnew_height\030\t \001(\r:\0010\022\024\n\tnew_width\030\n " + "\001(\r:\0010\022\026\n\010is_color\030\013 \001(\010:\004true\022\020\n\005scale\030" + "\002 \001(\002:\0011\022\021\n\tmean_file\030\003 \001(\t\022\024\n\tcrop_size" + "\030\005 \001(\r:\0010\022\025\n\006mirror\030\006 \001(\010:\005false\022\025\n\013root" + "_folder\030\014 \001(\t:\000\"\'\n\025InfogainLossParameter" + "\022\016\n\006source\030\001 \001(\t\"\331\001\n\025InnerProductParamet" + "er\022\022\n\nnum_output\030\001 \001(\r\022\027\n\tbias_term\030\002 \001(" + "\010:\004true\0224\n\rweight_filler\030\003 \001(\0132\035.opencv_" + "caffe.FillerParameter\0222\n\013bias_filler\030\004 \001" + "(\0132\035.opencv_caffe.FillerParameter\022\017\n\004axi" + "s\030\005 \001(\005:\0011\022\030\n\ttranspose\030\006 \001(\010:\005false\"8\n\016" + "InputParameter\022&\n\005shape\030\001 \003(\0132\027.opencv_c" + "affe.BlobShape\"D\n\014LogParameter\022\020\n\004base\030\001" + " \001(\002:\002-1\022\020\n\005scale\030\002 \001(\002:\0011\022\020\n\005shift\030\003 \001(" + "\002:\0010\"\306\002\n\014LRNParameter\022\025\n\nlocal_size\030\001 \001(" + "\r:\0015\022\020\n\005alpha\030\002 \001(\002:\0011\022\022\n\004beta\030\003 \001(\002:\0040." + "75\022K\n\013norm_region\030\004 \001(\0162%.opencv_caffe.L" + "RNParameter.NormRegion:\017ACROSS_CHANNELS\022" + "\014\n\001k\030\005 \001(\002:\0011\022:\n\006engine\030\006 \001(\0162!.opencv_c" + "affe.LRNParameter.Engine:\007DEFAULT\"5\n\nNor" + "mRegion\022\023\n\017ACROSS_CHANNELS\020\000\022\022\n\016WITHIN_C" + "HANNEL\020\001\"+\n\006Engine\022\013\n\007DEFAULT\020\000\022\t\n\005CAFFE" + "\020\001\022\t\n\005CUDNN\020\002\"Z\n\023MemoryDataParameter\022\022\n\n" + "batch_size\030\001 \001(\r\022\020\n\010channels\030\002 \001(\r\022\016\n\006he" + "ight\030\003 \001(\r\022\r\n\005width\030\004 \001(\r\"d\n\014MVNParamete" + "r\022 \n\022normalize_variance\030\001 \001(\010:\004true\022\036\n\017a" + "cross_channels\030\002 \001(\010:\005false\022\022\n\003eps\030\003 \001(\002" + ":\0051e-09\"<\n\022ParameterParameter\022&\n\005shape\030\001" + " \001(\0132\027.opencv_caffe.BlobShape\"\311\003\n\020Poolin" + "gParameter\022<\n\004pool\030\001 \001(\0162).opencv_caffe." + "PoolingParameter.PoolMethod:\003MAX\022\016\n\003pad\030" + "\004 \001(\r:\0010\022\020\n\005pad_h\030\t \001(\r:\0010\022\020\n\005pad_w\030\n \001(" + "\r:\0010\022\023\n\013kernel_size\030\002 \001(\r\022\020\n\010kernel_h\030\005 " + "\001(\r\022\020\n\010kernel_w\030\006 \001(\r\022\021\n\006stride\030\003 \001(\r:\0011" + "\022\020\n\010stride_h\030\007 \001(\r\022\020\n\010stride_w\030\010 \001(\r\022>\n\006" + "engine\030\013 \001(\0162%.opencv_caffe.PoolingParam" + "eter.Engine:\007DEFAULT\022\035\n\016global_pooling\030\014" + " \001(\010:\005false\022\027\n\tceil_mode\030\r \001(\010:\004true\".\n\n" + "PoolMethod\022\007\n\003MAX\020\000\022\007\n\003AVE\020\001\022\016\n\nSTOCHAST" + "IC\020\002\"+\n\006Engine\022\013\n\007DEFAULT\020\000\022\t\n\005CAFFE\020\001\022\t" + "\n\005CUDNN\020\002\"F\n\016PowerParameter\022\020\n\005power\030\001 \001" + "(\002:\0011\022\020\n\005scale\030\002 \001(\002:\0011\022\020\n\005shift\030\003 \001(\002:\001" + "0\"g\n\017PythonParameter\022\016\n\006module\030\001 \001(\t\022\r\n\005" + "layer\030\002 \001(\t\022\023\n\tparam_str\030\003 \001(\t:\000\022 \n\021shar" + "e_in_parallel\030\004 \001(\010:\005false\"\316\001\n\022Recurrent" + "Parameter\022\025\n\nnum_output\030\001 \001(\r:\0010\0224\n\rweig" + "ht_filler\030\002 \001(\0132\035.opencv_caffe.FillerPar" + "ameter\0222\n\013bias_filler\030\003 \001(\0132\035.opencv_caf" + "fe.FillerParameter\022\031\n\ndebug_info\030\004 \001(\010:\005" + "false\022\034\n\rexpose_hidden\030\005 \001(\010:\005false\"\264\001\n\022" + "ReductionParameter\022D\n\toperation\030\001 \001(\0162,." + "opencv_caffe.ReductionParameter.Reductio" + "nOp:\003SUM\022\017\n\004axis\030\002 \001(\005:\0010\022\020\n\005coeff\030\003 \001(\002" + ":\0011\"5\n\013ReductionOp\022\007\n\003SUM\020\001\022\010\n\004ASUM\020\002\022\t\n" + "\005SUMSQ\020\003\022\010\n\004MEAN\020\004\"\224\001\n\rReLUParameter\022\031\n\016" + "negative_slope\030\001 \001(\002:\0010\022;\n\006engine\030\002 \001(\0162" + "\".opencv_caffe.ReLUParameter.Engine:\007DEF" + "AULT\"+\n\006Engine\022\013\n\007DEFAULT\020\000\022\t\n\005CAFFE\020\001\022\t" + "\n\005CUDNN\020\002\"a\n\020ReshapeParameter\022&\n\005shape\030\001" + " \001(\0132\027.opencv_caffe.BlobShape\022\017\n\004axis\030\002 " + "\001(\005:\0010\022\024\n\010num_axes\030\003 \001(\005:\002-1\"\263\001\n\016ScalePa" + "rameter\022\017\n\004axis\030\001 \001(\005:\0011\022\023\n\010num_axes\030\002 \001" + "(\005:\0011\022-\n\006filler\030\003 \001(\0132\035.opencv_caffe.Fil" + "lerParameter\022\030\n\tbias_term\030\004 \001(\010:\005false\0222" + "\n\013bias_filler\030\005 \001(\0132\035.opencv_caffe.Fille" + "rParameter\"\177\n\020SigmoidParameter\022>\n\006engine" + "\030\001 \001(\0162%.opencv_caffe.SigmoidParameter.E" + "ngine:\007DEFAULT\"+\n\006Engine\022\013\n\007DEFAULT\020\000\022\t\n" + "\005CAFFE\020\001\022\t\n\005CUDNN\020\002\"L\n\016SliceParameter\022\017\n" + "\004axis\030\003 \001(\005:\0011\022\023\n\013slice_point\030\002 \003(\r\022\024\n\ts" + "lice_dim\030\001 \001(\r:\0011\"\220\001\n\020SoftmaxParameter\022>" + "\n\006engine\030\001 \001(\0162%.opencv_caffe.SoftmaxPar" + "ameter.Engine:\007DEFAULT\022\017\n\004axis\030\002 \001(\005:\0011\"" "+\n\006Engine\022\013\n\007DEFAULT\020\000\022\t\n\005CAFFE\020\001\022\t\n\005CUD" - "NN\020\002\"a\n\020ReshapeParameter\022&\n\005shape\030\001 \001(\0132" - "\027.opencv_caffe.BlobShape\022\017\n\004axis\030\002 \001(\005:\001" - "0\022\024\n\010num_axes\030\003 \001(\005:\002-1\"\263\001\n\016ScaleParamet" - "er\022\017\n\004axis\030\001 \001(\005:\0011\022\023\n\010num_axes\030\002 \001(\005:\0011" - "\022-\n\006filler\030\003 \001(\0132\035.opencv_caffe.FillerPa" - "rameter\022\030\n\tbias_term\030\004 \001(\010:\005false\0222\n\013bia" - "s_filler\030\005 \001(\0132\035.opencv_caffe.FillerPara" - "meter\"\177\n\020SigmoidParameter\022>\n\006engine\030\001 \001(" - "\0162%.opencv_caffe.SigmoidParameter.Engine" - ":\007DEFAULT\"+\n\006Engine\022\013\n\007DEFAULT\020\000\022\t\n\005CAFF" - "E\020\001\022\t\n\005CUDNN\020\002\"L\n\016SliceParameter\022\017\n\004axis" - "\030\003 \001(\005:\0011\022\023\n\013slice_point\030\002 \003(\r\022\024\n\tslice_" - "dim\030\001 \001(\r:\0011\"\220\001\n\020SoftmaxParameter\022>\n\006eng" - "ine\030\001 \001(\0162%.opencv_caffe.SoftmaxParamete" - "r.Engine:\007DEFAULT\022\017\n\004axis\030\002 \001(\005:\0011\"+\n\006En" - "gine\022\013\n\007DEFAULT\020\000\022\t\n\005CAFFE\020\001\022\t\n\005CUDNN\020\002\"" - "y\n\rTanHParameter\022;\n\006engine\030\001 \001(\0162\".openc" - "v_caffe.TanHParameter.Engine:\007DEFAULT\"+\n" - "\006Engine\022\013\n\007DEFAULT\020\000\022\t\n\005CAFFE\020\001\022\t\n\005CUDNN" - "\020\002\"/\n\rTileParameter\022\017\n\004axis\030\001 \001(\005:\0011\022\r\n\005" - "tiles\030\002 \001(\005\"*\n\022ThresholdParameter\022\024\n\tthr" - "eshold\030\001 \001(\002:\0010\"\301\002\n\023WindowDataParameter\022" - "\016\n\006source\030\001 \001(\t\022\020\n\005scale\030\002 \001(\002:\0011\022\021\n\tmea" - "n_file\030\003 \001(\t\022\022\n\nbatch_size\030\004 \001(\r\022\024\n\tcrop" - "_size\030\005 \001(\r:\0010\022\025\n\006mirror\030\006 \001(\010:\005false\022\031\n" - "\014fg_threshold\030\007 \001(\002:\0030.5\022\031\n\014bg_threshold" - "\030\010 \001(\002:\0030.5\022\031\n\013fg_fraction\030\t \001(\002:\0040.25\022\026" - "\n\013context_pad\030\n \001(\r:\0010\022\027\n\tcrop_mode\030\013 \001(" - "\t:\004warp\022\033\n\014cache_images\030\014 \001(\010:\005false\022\025\n\013" - "root_folder\030\r \001(\t:\000\"\371\001\n\014SPPParameter\022\026\n\016" - "pyramid_height\030\001 \001(\r\0228\n\004pool\030\002 \001(\0162%.ope" - "ncv_caffe.SPPParameter.PoolMethod:\003MAX\022:" - "\n\006engine\030\006 \001(\0162!.opencv_caffe.SPPParamet" - "er.Engine:\007DEFAULT\".\n\nPoolMethod\022\007\n\003MAX\020" - "\000\022\007\n\003AVE\020\001\022\016\n\nSTOCHASTIC\020\002\"+\n\006Engine\022\013\n\007" - "DEFAULT\020\000\022\t\n\005CAFFE\020\001\022\t\n\005CUDNN\020\002\"\334\025\n\020V1La" - "yerParameter\022\016\n\006bottom\030\002 \003(\t\022\013\n\003top\030\003 \003(" - "\t\022\014\n\004name\030\004 \001(\t\022+\n\007include\030 \003(\0132\032.openc" - "v_caffe.NetStateRule\022+\n\007exclude\030! \003(\0132\032." - "opencv_caffe.NetStateRule\0226\n\004type\030\005 \001(\0162" - "(.opencv_caffe.V1LayerParameter.LayerTyp" - "e\022&\n\005blobs\030\006 \003(\0132\027.opencv_caffe.BlobProt" - "o\022\016\n\005param\030\351\007 \003(\t\022E\n\017blob_share_mode\030\352\007 " - "\003(\0162+.opencv_caffe.V1LayerParameter.DimC" - "heckMode\022\020\n\010blobs_lr\030\007 \003(\002\022\024\n\014weight_dec" - "ay\030\010 \003(\002\022\023\n\013loss_weight\030# \003(\002\0227\n\016accurac" - "y_param\030\033 \001(\0132\037.opencv_caffe.AccuracyPar" - "ameter\0223\n\014argmax_param\030\027 \001(\0132\035.opencv_ca" - "ffe.ArgMaxParameter\0223\n\014concat_param\030\t \001(" - "\0132\035.opencv_caffe.ConcatParameter\022F\n\026cont" - "rastive_loss_param\030( \001(\0132&.opencv_caffe." - "ContrastiveLossParameter\022=\n\021convolution_" - "param\030\n \001(\0132\".opencv_caffe.ConvolutionPa" - "rameter\022/\n\ndata_param\030\013 \001(\0132\033.opencv_caf" - "fe.DataParameter\0225\n\rdropout_param\030\014 \001(\0132" - "\036.opencv_caffe.DropoutParameter\022:\n\020dummy" - "_data_param\030\032 \001(\0132 .opencv_caffe.DummyDa" - "taParameter\0225\n\reltwise_param\030\030 \001(\0132\036.ope" - "ncv_caffe.EltwiseParameter\022-\n\texp_param\030" - ") \001(\0132\032.opencv_caffe.ExpParameter\0228\n\017hdf" - "5_data_param\030\r \001(\0132\037.opencv_caffe.HDF5Da" - "taParameter\022<\n\021hdf5_output_param\030\016 \001(\0132!" - ".opencv_caffe.HDF5OutputParameter\022:\n\020hin" - "ge_loss_param\030\035 \001(\0132 .opencv_caffe.Hinge" - "LossParameter\022:\n\020image_data_param\030\017 \001(\0132" - " .opencv_caffe.ImageDataParameter\022@\n\023inf" - "ogain_loss_param\030\020 \001(\0132#.opencv_caffe.In" - "fogainLossParameter\022@\n\023inner_product_par" - "am\030\021 \001(\0132#.opencv_caffe.InnerProductPara" - "meter\022-\n\tlrn_param\030\022 \001(\0132\032.opencv_caffe." - "LRNParameter\022<\n\021memory_data_param\030\026 \001(\0132" - "!.opencv_caffe.MemoryDataParameter\022-\n\tmv" - "n_param\030\" \001(\0132\032.opencv_caffe.MVNParamete" - "r\0225\n\rpooling_param\030\023 \001(\0132\036.opencv_caffe." - "PoolingParameter\0221\n\013power_param\030\025 \001(\0132\034." - "opencv_caffe.PowerParameter\022/\n\nrelu_para" - "m\030\036 \001(\0132\033.opencv_caffe.ReLUParameter\0225\n\r" - "sigmoid_param\030& \001(\0132\036.opencv_caffe.Sigmo" - "idParameter\0225\n\rsoftmax_param\030\' \001(\0132\036.ope" - "ncv_caffe.SoftmaxParameter\0221\n\013slice_para" - "m\030\037 \001(\0132\034.opencv_caffe.SliceParameter\022/\n" - "\ntanh_param\030% \001(\0132\033.opencv_caffe.TanHPar" - "ameter\0229\n\017threshold_param\030\031 \001(\0132 .opencv" - "_caffe.ThresholdParameter\022<\n\021window_data" - "_param\030\024 \001(\0132!.opencv_caffe.WindowDataPa" - "rameter\022>\n\017transform_param\030$ \001(\0132%.openc" - "v_caffe.TransformationParameter\022/\n\nloss_" - "param\030* \001(\0132\033.opencv_caffe.LossParameter" - "\022-\n\005layer\030\001 \001(\0132\036.opencv_caffe.V0LayerPa" - "rameter\"\330\004\n\tLayerType\022\010\n\004NONE\020\000\022\n\n\006ABSVA" - "L\020#\022\014\n\010ACCURACY\020\001\022\n\n\006ARGMAX\020\036\022\010\n\004BNLL\020\002\022" - "\n\n\006CONCAT\020\003\022\024\n\020CONTRASTIVE_LOSS\020%\022\017\n\013CON" - "VOLUTION\020\004\022\010\n\004DATA\020\005\022\021\n\rDECONVOLUTION\020\'\022" - "\013\n\007DROPOUT\020\006\022\016\n\nDUMMY_DATA\020 \022\022\n\016EUCLIDEA" - "N_LOSS\020\007\022\013\n\007ELTWISE\020\031\022\007\n\003EXP\020&\022\013\n\007FLATTE" - "N\020\010\022\r\n\tHDF5_DATA\020\t\022\017\n\013HDF5_OUTPUT\020\n\022\016\n\nH" - "INGE_LOSS\020\034\022\n\n\006IM2COL\020\013\022\016\n\nIMAGE_DATA\020\014\022" - "\021\n\rINFOGAIN_LOSS\020\r\022\021\n\rINNER_PRODUCT\020\016\022\007\n" - "\003LRN\020\017\022\017\n\013MEMORY_DATA\020\035\022\035\n\031MULTINOMIAL_L" - "OGISTIC_LOSS\020\020\022\007\n\003MVN\020\"\022\013\n\007POOLING\020\021\022\t\n\005" - "POWER\020\032\022\010\n\004RELU\020\022\022\013\n\007SIGMOID\020\023\022\036\n\032SIGMOI" - "D_CROSS_ENTROPY_LOSS\020\033\022\013\n\007SILENCE\020$\022\013\n\007S" - "OFTMAX\020\024\022\020\n\014SOFTMAX_LOSS\020\025\022\t\n\005SPLIT\020\026\022\t\n" - "\005SLICE\020!\022\010\n\004TANH\020\027\022\017\n\013WINDOW_DATA\020\030\022\r\n\tT" - "HRESHOLD\020\037\"*\n\014DimCheckMode\022\n\n\006STRICT\020\000\022\016" - "\n\nPERMISSIVE\020\001\"\240\010\n\020V0LayerParameter\022\014\n\004n" - "ame\030\001 \001(\t\022\014\n\004type\030\002 \001(\t\022\022\n\nnum_output\030\003 " - "\001(\r\022\026\n\010biasterm\030\004 \001(\010:\004true\0224\n\rweight_fi" - "ller\030\005 \001(\0132\035.opencv_caffe.FillerParamete" - "r\0222\n\013bias_filler\030\006 \001(\0132\035.opencv_caffe.Fi" - "llerParameter\022\016\n\003pad\030\007 \001(\r:\0010\022\022\n\nkernels" - "ize\030\010 \001(\r\022\020\n\005group\030\t \001(\r:\0011\022\021\n\006stride\030\n " - "\001(\r:\0011\022<\n\004pool\030\013 \001(\0162).opencv_caffe.V0La" - "yerParameter.PoolMethod:\003MAX\022\032\n\rdropout_" - "ratio\030\014 \001(\002:\0030.5\022\025\n\nlocal_size\030\r \001(\r:\0015\022" - "\020\n\005alpha\030\016 \001(\002:\0011\022\022\n\004beta\030\017 \001(\002:\0040.75\022\014\n" - "\001k\030\026 \001(\002:\0011\022\016\n\006source\030\020 \001(\t\022\020\n\005scale\030\021 \001" - "(\002:\0011\022\020\n\010meanfile\030\022 \001(\t\022\021\n\tbatchsize\030\023 \001" - "(\r\022\023\n\010cropsize\030\024 \001(\r:\0010\022\025\n\006mirror\030\025 \001(\010:" - "\005false\022&\n\005blobs\0302 \003(\0132\027.opencv_caffe.Blo" - "bProto\022\020\n\010blobs_lr\0303 \003(\002\022\024\n\014weight_decay" - "\0304 \003(\002\022\024\n\trand_skip\0305 \001(\r:\0010\022\035\n\020det_fg_t" - "hreshold\0306 \001(\002:\0030.5\022\035\n\020det_bg_threshold\030" - "7 \001(\002:\0030.5\022\035\n\017det_fg_fraction\0308 \001(\002:\0040.2" - "5\022\032\n\017det_context_pad\030: \001(\r:\0010\022\033\n\rdet_cro" - "p_mode\030; \001(\t:\004warp\022\022\n\007new_num\030< \001(\005:\0010\022\027" - "\n\014new_channels\030= \001(\005:\0010\022\025\n\nnew_height\030> " - "\001(\005:\0010\022\024\n\tnew_width\030\? \001(\005:\0010\022\035\n\016shuffle_" - "images\030@ \001(\010:\005false\022\025\n\nconcat_dim\030A \001(\r:" - "\0011\022=\n\021hdf5_output_param\030\351\007 \001(\0132!.opencv_" - "caffe.HDF5OutputParameter\".\n\nPoolMethod\022" - "\007\n\003MAX\020\000\022\007\n\003AVE\020\001\022\016\n\nSTOCHASTIC\020\002\"^\n\016PRe" - "LUParameter\022-\n\006filler\030\001 \001(\0132\035.opencv_caf" - "fe.FillerParameter\022\035\n\016channel_shared\030\002 \001" - "(\010:\005false\"\207\001\n\016NormalizedBBox\022\014\n\004xmin\030\001 \001" - "(\002\022\014\n\004ymin\030\002 \001(\002\022\014\n\004xmax\030\003 \001(\002\022\014\n\004ymax\030\004" - " \001(\002\022\r\n\005label\030\005 \001(\005\022\021\n\tdifficult\030\006 \001(\010\022\r" - "\n\005score\030\007 \001(\002\022\014\n\004size\030\010 \001(\002\"Y\n\023ROIPoolin" - "gParameter\022\023\n\010pooled_h\030\001 \001(\r:\0010\022\023\n\010poole" - "d_w\030\002 \001(\r:\0010\022\030\n\rspatial_scale\030\003 \001(\002:\0011*=" - "\n\004Type\022\n\n\006DOUBLE\020\000\022\t\n\005FLOAT\020\001\022\013\n\007FLOAT16" - "\020\002\022\007\n\003INT\020\003\022\010\n\004UINT\020\004*\034\n\005Phase\022\t\n\005TRAIN\020" - "\000\022\010\n\004TEST\020\001", 18331); + "NN\020\002\"y\n\rTanHParameter\022;\n\006engine\030\001 \001(\0162\"." + "opencv_caffe.TanHParameter.Engine:\007DEFAU" + "LT\"+\n\006Engine\022\013\n\007DEFAULT\020\000\022\t\n\005CAFFE\020\001\022\t\n\005" + "CUDNN\020\002\"/\n\rTileParameter\022\017\n\004axis\030\001 \001(\005:\001" + "1\022\r\n\005tiles\030\002 \001(\005\"*\n\022ThresholdParameter\022\024" + "\n\tthreshold\030\001 \001(\002:\0010\"\301\002\n\023WindowDataParam" + "eter\022\016\n\006source\030\001 \001(\t\022\020\n\005scale\030\002 \001(\002:\0011\022\021" + "\n\tmean_file\030\003 \001(\t\022\022\n\nbatch_size\030\004 \001(\r\022\024\n" + "\tcrop_size\030\005 \001(\r:\0010\022\025\n\006mirror\030\006 \001(\010:\005fal" + "se\022\031\n\014fg_threshold\030\007 \001(\002:\0030.5\022\031\n\014bg_thre" + "shold\030\010 \001(\002:\0030.5\022\031\n\013fg_fraction\030\t \001(\002:\0040" + ".25\022\026\n\013context_pad\030\n \001(\r:\0010\022\027\n\tcrop_mode" + "\030\013 \001(\t:\004warp\022\033\n\014cache_images\030\014 \001(\010:\005fals" + "e\022\025\n\013root_folder\030\r \001(\t:\000\"\371\001\n\014SPPParamete" + "r\022\026\n\016pyramid_height\030\001 \001(\r\0228\n\004pool\030\002 \001(\0162" + "%.opencv_caffe.SPPParameter.PoolMethod:\003" + "MAX\022:\n\006engine\030\006 \001(\0162!.opencv_caffe.SPPPa" + "rameter.Engine:\007DEFAULT\".\n\nPoolMethod\022\007\n" + "\003MAX\020\000\022\007\n\003AVE\020\001\022\016\n\nSTOCHASTIC\020\002\"+\n\006Engin" + "e\022\013\n\007DEFAULT\020\000\022\t\n\005CAFFE\020\001\022\t\n\005CUDNN\020\002\"\334\025\n" + "\020V1LayerParameter\022\016\n\006bottom\030\002 \003(\t\022\013\n\003top" + "\030\003 \003(\t\022\014\n\004name\030\004 \001(\t\022+\n\007include\030 \003(\0132\032." + "opencv_caffe.NetStateRule\022+\n\007exclude\030! \003" + "(\0132\032.opencv_caffe.NetStateRule\0226\n\004type\030\005" + " \001(\0162(.opencv_caffe.V1LayerParameter.Lay" + "erType\022&\n\005blobs\030\006 \003(\0132\027.opencv_caffe.Blo" + "bProto\022\016\n\005param\030\351\007 \003(\t\022E\n\017blob_share_mod" + "e\030\352\007 \003(\0162+.opencv_caffe.V1LayerParameter" + ".DimCheckMode\022\020\n\010blobs_lr\030\007 \003(\002\022\024\n\014weigh" + "t_decay\030\010 \003(\002\022\023\n\013loss_weight\030# \003(\002\0227\n\016ac" + "curacy_param\030\033 \001(\0132\037.opencv_caffe.Accura" + "cyParameter\0223\n\014argmax_param\030\027 \001(\0132\035.open" + "cv_caffe.ArgMaxParameter\0223\n\014concat_param" + "\030\t \001(\0132\035.opencv_caffe.ConcatParameter\022F\n" + "\026contrastive_loss_param\030( \001(\0132&.opencv_c" + "affe.ContrastiveLossParameter\022=\n\021convolu" + "tion_param\030\n \001(\0132\".opencv_caffe.Convolut" + "ionParameter\022/\n\ndata_param\030\013 \001(\0132\033.openc" + "v_caffe.DataParameter\0225\n\rdropout_param\030\014" + " \001(\0132\036.opencv_caffe.DropoutParameter\022:\n\020" + "dummy_data_param\030\032 \001(\0132 .opencv_caffe.Du" + "mmyDataParameter\0225\n\reltwise_param\030\030 \001(\0132" + "\036.opencv_caffe.EltwiseParameter\022-\n\texp_p" + "aram\030) \001(\0132\032.opencv_caffe.ExpParameter\0228" + "\n\017hdf5_data_param\030\r \001(\0132\037.opencv_caffe.H" + "DF5DataParameter\022<\n\021hdf5_output_param\030\016 " + "\001(\0132!.opencv_caffe.HDF5OutputParameter\022:" + "\n\020hinge_loss_param\030\035 \001(\0132 .opencv_caffe." + "HingeLossParameter\022:\n\020image_data_param\030\017" + " \001(\0132 .opencv_caffe.ImageDataParameter\022@" + "\n\023infogain_loss_param\030\020 \001(\0132#.opencv_caf" + "fe.InfogainLossParameter\022@\n\023inner_produc" + "t_param\030\021 \001(\0132#.opencv_caffe.InnerProduc" + "tParameter\022-\n\tlrn_param\030\022 \001(\0132\032.opencv_c" + "affe.LRNParameter\022<\n\021memory_data_param\030\026" + " \001(\0132!.opencv_caffe.MemoryDataParameter\022" + "-\n\tmvn_param\030\" \001(\0132\032.opencv_caffe.MVNPar" + "ameter\0225\n\rpooling_param\030\023 \001(\0132\036.opencv_c" + "affe.PoolingParameter\0221\n\013power_param\030\025 \001" + "(\0132\034.opencv_caffe.PowerParameter\022/\n\nrelu" + "_param\030\036 \001(\0132\033.opencv_caffe.ReLUParamete" + "r\0225\n\rsigmoid_param\030& \001(\0132\036.opencv_caffe." + "SigmoidParameter\0225\n\rsoftmax_param\030\' \001(\0132" + "\036.opencv_caffe.SoftmaxParameter\0221\n\013slice" + "_param\030\037 \001(\0132\034.opencv_caffe.SliceParamet" + "er\022/\n\ntanh_param\030% \001(\0132\033.opencv_caffe.Ta" + "nHParameter\0229\n\017threshold_param\030\031 \001(\0132 .o" + "pencv_caffe.ThresholdParameter\022<\n\021window" + "_data_param\030\024 \001(\0132!.opencv_caffe.WindowD" + "ataParameter\022>\n\017transform_param\030$ \001(\0132%." + "opencv_caffe.TransformationParameter\022/\n\n" + "loss_param\030* \001(\0132\033.opencv_caffe.LossPara" + "meter\022-\n\005layer\030\001 \001(\0132\036.opencv_caffe.V0La" + "yerParameter\"\330\004\n\tLayerType\022\010\n\004NONE\020\000\022\n\n\006" + "ABSVAL\020#\022\014\n\010ACCURACY\020\001\022\n\n\006ARGMAX\020\036\022\010\n\004BN" + "LL\020\002\022\n\n\006CONCAT\020\003\022\024\n\020CONTRASTIVE_LOSS\020%\022\017" + "\n\013CONVOLUTION\020\004\022\010\n\004DATA\020\005\022\021\n\rDECONVOLUTI" + "ON\020\'\022\013\n\007DROPOUT\020\006\022\016\n\nDUMMY_DATA\020 \022\022\n\016EUC" + "LIDEAN_LOSS\020\007\022\013\n\007ELTWISE\020\031\022\007\n\003EXP\020&\022\013\n\007F" + "LATTEN\020\010\022\r\n\tHDF5_DATA\020\t\022\017\n\013HDF5_OUTPUT\020\n" + "\022\016\n\nHINGE_LOSS\020\034\022\n\n\006IM2COL\020\013\022\016\n\nIMAGE_DA" + "TA\020\014\022\021\n\rINFOGAIN_LOSS\020\r\022\021\n\rINNER_PRODUCT" + "\020\016\022\007\n\003LRN\020\017\022\017\n\013MEMORY_DATA\020\035\022\035\n\031MULTINOM" + "IAL_LOGISTIC_LOSS\020\020\022\007\n\003MVN\020\"\022\013\n\007POOLING\020" + "\021\022\t\n\005POWER\020\032\022\010\n\004RELU\020\022\022\013\n\007SIGMOID\020\023\022\036\n\032S" + "IGMOID_CROSS_ENTROPY_LOSS\020\033\022\013\n\007SILENCE\020$" + "\022\013\n\007SOFTMAX\020\024\022\020\n\014SOFTMAX_LOSS\020\025\022\t\n\005SPLIT" + "\020\026\022\t\n\005SLICE\020!\022\010\n\004TANH\020\027\022\017\n\013WINDOW_DATA\020\030" + "\022\r\n\tTHRESHOLD\020\037\"*\n\014DimCheckMode\022\n\n\006STRIC" + "T\020\000\022\016\n\nPERMISSIVE\020\001\"\240\010\n\020V0LayerParameter" + "\022\014\n\004name\030\001 \001(\t\022\014\n\004type\030\002 \001(\t\022\022\n\nnum_outp" + "ut\030\003 \001(\r\022\026\n\010biasterm\030\004 \001(\010:\004true\0224\n\rweig" + "ht_filler\030\005 \001(\0132\035.opencv_caffe.FillerPar" + "ameter\0222\n\013bias_filler\030\006 \001(\0132\035.opencv_caf" + "fe.FillerParameter\022\016\n\003pad\030\007 \001(\r:\0010\022\022\n\nke" + "rnelsize\030\010 \001(\r\022\020\n\005group\030\t \001(\r:\0011\022\021\n\006stri" + "de\030\n \001(\r:\0011\022<\n\004pool\030\013 \001(\0162).opencv_caffe" + ".V0LayerParameter.PoolMethod:\003MAX\022\032\n\rdro" + "pout_ratio\030\014 \001(\002:\0030.5\022\025\n\nlocal_size\030\r \001(" + "\r:\0015\022\020\n\005alpha\030\016 \001(\002:\0011\022\022\n\004beta\030\017 \001(\002:\0040." + "75\022\014\n\001k\030\026 \001(\002:\0011\022\016\n\006source\030\020 \001(\t\022\020\n\005scal" + "e\030\021 \001(\002:\0011\022\020\n\010meanfile\030\022 \001(\t\022\021\n\tbatchsiz" + "e\030\023 \001(\r\022\023\n\010cropsize\030\024 \001(\r:\0010\022\025\n\006mirror\030\025" + " \001(\010:\005false\022&\n\005blobs\0302 \003(\0132\027.opencv_caff" + "e.BlobProto\022\020\n\010blobs_lr\0303 \003(\002\022\024\n\014weight_" + "decay\0304 \003(\002\022\024\n\trand_skip\0305 \001(\r:\0010\022\035\n\020det" + "_fg_threshold\0306 \001(\002:\0030.5\022\035\n\020det_bg_thres" + "hold\0307 \001(\002:\0030.5\022\035\n\017det_fg_fraction\0308 \001(\002" + ":\0040.25\022\032\n\017det_context_pad\030: \001(\r:\0010\022\033\n\rde" + "t_crop_mode\030; \001(\t:\004warp\022\022\n\007new_num\030< \001(\005" + ":\0010\022\027\n\014new_channels\030= \001(\005:\0010\022\025\n\nnew_heig" + "ht\030> \001(\005:\0010\022\024\n\tnew_width\030\? \001(\005:\0010\022\035\n\016shu" + "ffle_images\030@ \001(\010:\005false\022\025\n\nconcat_dim\030A" + " \001(\r:\0011\022=\n\021hdf5_output_param\030\351\007 \001(\0132!.op" + "encv_caffe.HDF5OutputParameter\".\n\nPoolMe" + "thod\022\007\n\003MAX\020\000\022\007\n\003AVE\020\001\022\016\n\nSTOCHASTIC\020\002\"^" + "\n\016PReLUParameter\022-\n\006filler\030\001 \001(\0132\035.openc" + "v_caffe.FillerParameter\022\035\n\016channel_share" + "d\030\002 \001(\010:\005false\"\207\001\n\016NormalizedBBox\022\014\n\004xmi" + "n\030\001 \001(\002\022\014\n\004ymin\030\002 \001(\002\022\014\n\004xmax\030\003 \001(\002\022\014\n\004y" + "max\030\004 \001(\002\022\r\n\005label\030\005 \001(\005\022\021\n\tdifficult\030\006 " + "\001(\010\022\r\n\005score\030\007 \001(\002\022\014\n\004size\030\010 \001(\002\"Y\n\023ROIP" + "oolingParameter\022\023\n\010pooled_h\030\001 \001(\r:\0010\022\023\n\010" + "pooled_w\030\002 \001(\r:\0010\022\030\n\rspatial_scale\030\003 \001(\002" + ":\0011\"\310\001\n\021ProposalParameter\022\027\n\013feat_stride" + "\030\001 \001(\r:\00216\022\025\n\tbase_size\030\002 \001(\r:\00216\022\024\n\010min" + "_size\030\003 \001(\r:\00216\022\r\n\005ratio\030\004 \003(\002\022\r\n\005scale\030" + "\005 \003(\002\022\032\n\014pre_nms_topn\030\006 \001(\r:\0046000\022\032\n\rpos" + "t_nms_topn\030\007 \001(\r:\003300\022\027\n\nnms_thresh\030\010 \001(" + "\002:\0030.7*=\n\004Type\022\n\n\006DOUBLE\020\000\022\t\n\005FLOAT\020\001\022\013\n" + "\007FLOAT16\020\002\022\007\n\003INT\020\003\022\010\n\004UINT\020\004*\034\n\005Phase\022\t" + "\n\005TRAIN\020\000\022\010\n\004TEST\020\001", 18619); ::google::protobuf::MessageFactory::InternalRegisterGeneratedFile( "opencv-caffe.proto", &protobuf_RegisterTypes); ::google::protobuf::internal::OnShutdown(&protobuf_ShutdownFile_opencv_2dcaffe_2eproto); @@ -15448,6 +15487,7 @@ const int LayerParameter::kPoolingParamFieldNumber; const int LayerParameter::kPowerParamFieldNumber; const int LayerParameter::kPreluParamFieldNumber; const int LayerParameter::kPriorBoxParamFieldNumber; +const int LayerParameter::kProposalParamFieldNumber; const int LayerParameter::kPythonParamFieldNumber; const int LayerParameter::kRecurrentParamFieldNumber; const int LayerParameter::kReductionParamFieldNumber; @@ -15547,6 +15587,8 @@ void LayerParameter::InitAsDefaultInstance() { ::opencv_caffe::PReLUParameter::internal_default_instance()); prior_box_param_ = const_cast< ::opencv_caffe::PriorBoxParameter*>( ::opencv_caffe::PriorBoxParameter::internal_default_instance()); + proposal_param_ = const_cast< ::opencv_caffe::ProposalParameter*>( + ::opencv_caffe::ProposalParameter::internal_default_instance()); python_param_ = const_cast< ::opencv_caffe::PythonParameter*>( ::opencv_caffe::PythonParameter::internal_default_instance()); recurrent_param_ = const_cast< ::opencv_caffe::RecurrentParameter*>( @@ -15627,6 +15669,7 @@ void LayerParameter::SharedCtor() { power_param_ = NULL; prelu_param_ = NULL; prior_box_param_ = NULL; + proposal_param_ = NULL; python_param_ = NULL; recurrent_param_ = NULL; reduction_param_ = NULL; @@ -15692,6 +15735,7 @@ void LayerParameter::SharedDtor() { delete power_param_; delete prelu_param_; delete prior_box_param_; + delete proposal_param_; delete python_param_; delete recurrent_param_; delete reduction_param_; @@ -15868,6 +15912,9 @@ void LayerParameter::Clear() { } } if (_has_bits_[48 / 32] & 16711680u) { + if (has_proposal_param()) { + if (proposal_param_ != NULL) proposal_param_->::opencv_caffe::ProposalParameter::Clear(); + } if (has_python_param()) { if (python_param_ != NULL) python_param_->::opencv_caffe::PythonParameter::Clear(); } @@ -15889,11 +15936,11 @@ void LayerParameter::Clear() { if (has_scale_param()) { if (scale_param_ != NULL) scale_param_->::opencv_caffe::ScaleParameter::Clear(); } + } + if (_has_bits_[56 / 32] & 4278190080u) { if (has_sigmoid_param()) { if (sigmoid_param_ != NULL) sigmoid_param_->::opencv_caffe::SigmoidParameter::Clear(); } - } - if (_has_bits_[56 / 32] & 2130706432u) { if (has_softmax_param()) { if (softmax_param_ != NULL) softmax_param_->::opencv_caffe::SoftmaxParameter::Clear(); } @@ -16793,6 +16840,19 @@ bool LayerParameter::MergePartialFromCodedStream( } else { goto handle_unusual; } + if (input->ExpectTag(1610)) goto parse_proposal_param; + break; + } + + // optional .opencv_caffe.ProposalParameter proposal_param = 201; + case 201: { + if (tag == 1610) { + parse_proposal_param: + DO_(::google::protobuf::internal::WireFormatLite::ReadMessageNoVirtual( + input, mutable_proposal_param())); + } else { + goto handle_unusual; + } if (input->ExpectTag(66133690)) goto parse_roi_pooling_param; break; } @@ -17223,6 +17283,12 @@ void LayerParameter::SerializeWithCachedSizes( 150, *this->prior_box_param_, output); } + // optional .opencv_caffe.ProposalParameter proposal_param = 201; + if (has_proposal_param()) { + ::google::protobuf::internal::WireFormatLite::WriteMessageMaybeToArray( + 201, *this->proposal_param_, output); + } + // optional .opencv_caffe.ROIPoolingParameter roi_pooling_param = 8266711; if (has_roi_pooling_param()) { ::google::protobuf::internal::WireFormatLite::WriteMessageMaybeToArray( @@ -17685,6 +17751,13 @@ void LayerParameter::SerializeWithCachedSizes( 150, *this->prior_box_param_, false, target); } + // optional .opencv_caffe.ProposalParameter proposal_param = 201; + if (has_proposal_param()) { + target = ::google::protobuf::internal::WireFormatLite:: + InternalWriteMessageNoVirtualToArray( + 201, *this->proposal_param_, false, target); + } + // optional .opencv_caffe.ROIPoolingParameter roi_pooling_param = 8266711; if (has_roi_pooling_param()) { target = ::google::protobuf::internal::WireFormatLite:: @@ -17996,6 +18069,13 @@ size_t LayerParameter::ByteSizeLong() const { } if (_has_bits_[48 / 32] & 16711680u) { + // optional .opencv_caffe.ProposalParameter proposal_param = 201; + if (has_proposal_param()) { + total_size += 2 + + ::google::protobuf::internal::WireFormatLite::MessageSizeNoVirtual( + *this->proposal_param_); + } + // optional .opencv_caffe.PythonParameter python_param = 130; if (has_python_param()) { total_size += 2 + @@ -18045,6 +18125,8 @@ size_t LayerParameter::ByteSizeLong() const { *this->scale_param_); } + } + if (_has_bits_[56 / 32] & 4278190080u) { // optional .opencv_caffe.SigmoidParameter sigmoid_param = 124; if (has_sigmoid_param()) { total_size += 2 + @@ -18052,8 +18134,6 @@ size_t LayerParameter::ByteSizeLong() const { *this->sigmoid_param_); } - } - if (_has_bits_[56 / 32] & 2130706432u) { // optional .opencv_caffe.SoftmaxParameter softmax_param = 125; if (has_softmax_param()) { total_size += 2 + @@ -18365,6 +18445,9 @@ void LayerParameter::UnsafeMergeFrom(const LayerParameter& from) { } } if (from._has_bits_[48 / 32] & (0xffu << (48 % 32))) { + if (from.has_proposal_param()) { + mutable_proposal_param()->::opencv_caffe::ProposalParameter::MergeFrom(from.proposal_param()); + } if (from.has_python_param()) { mutable_python_param()->::opencv_caffe::PythonParameter::MergeFrom(from.python_param()); } @@ -18386,11 +18469,11 @@ void LayerParameter::UnsafeMergeFrom(const LayerParameter& from) { if (from.has_scale_param()) { mutable_scale_param()->::opencv_caffe::ScaleParameter::MergeFrom(from.scale_param()); } + } + if (from._has_bits_[56 / 32] & (0xffu << (56 % 32))) { if (from.has_sigmoid_param()) { mutable_sigmoid_param()->::opencv_caffe::SigmoidParameter::MergeFrom(from.sigmoid_param()); } - } - if (from._has_bits_[56 / 32] & (0xffu << (56 % 32))) { if (from.has_softmax_param()) { mutable_softmax_param()->::opencv_caffe::SoftmaxParameter::MergeFrom(from.softmax_param()); } @@ -18491,6 +18574,7 @@ void LayerParameter::InternalSwap(LayerParameter* other) { std::swap(power_param_, other->power_param_); std::swap(prelu_param_, other->prelu_param_); std::swap(prior_box_param_, other->prior_box_param_); + std::swap(proposal_param_, other->proposal_param_); std::swap(python_param_, other->python_param_); std::swap(recurrent_param_, other->recurrent_param_); std::swap(reduction_param_, other->reduction_param_); @@ -20611,15 +20695,60 @@ void LayerParameter::set_allocated_prior_box_param(::opencv_caffe::PriorBoxParam // @@protoc_insertion_point(field_set_allocated:opencv_caffe.LayerParameter.prior_box_param) } +// optional .opencv_caffe.ProposalParameter proposal_param = 201; +bool LayerParameter::has_proposal_param() const { + return (_has_bits_[1] & 0x00010000u) != 0; +} +void LayerParameter::set_has_proposal_param() { + _has_bits_[1] |= 0x00010000u; +} +void LayerParameter::clear_has_proposal_param() { + _has_bits_[1] &= ~0x00010000u; +} +void LayerParameter::clear_proposal_param() { + if (proposal_param_ != NULL) proposal_param_->::opencv_caffe::ProposalParameter::Clear(); + clear_has_proposal_param(); +} +const ::opencv_caffe::ProposalParameter& LayerParameter::proposal_param() const { + // @@protoc_insertion_point(field_get:opencv_caffe.LayerParameter.proposal_param) + return proposal_param_ != NULL ? *proposal_param_ + : *::opencv_caffe::ProposalParameter::internal_default_instance(); +} +::opencv_caffe::ProposalParameter* LayerParameter::mutable_proposal_param() { + set_has_proposal_param(); + if (proposal_param_ == NULL) { + proposal_param_ = new ::opencv_caffe::ProposalParameter; + } + // @@protoc_insertion_point(field_mutable:opencv_caffe.LayerParameter.proposal_param) + return proposal_param_; +} +::opencv_caffe::ProposalParameter* LayerParameter::release_proposal_param() { + // @@protoc_insertion_point(field_release:opencv_caffe.LayerParameter.proposal_param) + clear_has_proposal_param(); + ::opencv_caffe::ProposalParameter* temp = proposal_param_; + proposal_param_ = NULL; + return temp; +} +void LayerParameter::set_allocated_proposal_param(::opencv_caffe::ProposalParameter* proposal_param) { + delete proposal_param_; + proposal_param_ = proposal_param; + if (proposal_param) { + set_has_proposal_param(); + } else { + clear_has_proposal_param(); + } + // @@protoc_insertion_point(field_set_allocated:opencv_caffe.LayerParameter.proposal_param) +} + // optional .opencv_caffe.PythonParameter python_param = 130; bool LayerParameter::has_python_param() const { - return (_has_bits_[1] & 0x00010000u) != 0; + return (_has_bits_[1] & 0x00020000u) != 0; } void LayerParameter::set_has_python_param() { - _has_bits_[1] |= 0x00010000u; + _has_bits_[1] |= 0x00020000u; } void LayerParameter::clear_has_python_param() { - _has_bits_[1] &= ~0x00010000u; + _has_bits_[1] &= ~0x00020000u; } void LayerParameter::clear_python_param() { if (python_param_ != NULL) python_param_->::opencv_caffe::PythonParameter::Clear(); @@ -20658,13 +20787,13 @@ void LayerParameter::set_allocated_python_param(::opencv_caffe::PythonParameter* // optional .opencv_caffe.RecurrentParameter recurrent_param = 146; bool LayerParameter::has_recurrent_param() const { - return (_has_bits_[1] & 0x00020000u) != 0; + return (_has_bits_[1] & 0x00040000u) != 0; } void LayerParameter::set_has_recurrent_param() { - _has_bits_[1] |= 0x00020000u; + _has_bits_[1] |= 0x00040000u; } void LayerParameter::clear_has_recurrent_param() { - _has_bits_[1] &= ~0x00020000u; + _has_bits_[1] &= ~0x00040000u; } void LayerParameter::clear_recurrent_param() { if (recurrent_param_ != NULL) recurrent_param_->::opencv_caffe::RecurrentParameter::Clear(); @@ -20703,13 +20832,13 @@ void LayerParameter::set_allocated_recurrent_param(::opencv_caffe::RecurrentPara // optional .opencv_caffe.ReductionParameter reduction_param = 136; bool LayerParameter::has_reduction_param() const { - return (_has_bits_[1] & 0x00040000u) != 0; + return (_has_bits_[1] & 0x00080000u) != 0; } void LayerParameter::set_has_reduction_param() { - _has_bits_[1] |= 0x00040000u; + _has_bits_[1] |= 0x00080000u; } void LayerParameter::clear_has_reduction_param() { - _has_bits_[1] &= ~0x00040000u; + _has_bits_[1] &= ~0x00080000u; } void LayerParameter::clear_reduction_param() { if (reduction_param_ != NULL) reduction_param_->::opencv_caffe::ReductionParameter::Clear(); @@ -20748,13 +20877,13 @@ void LayerParameter::set_allocated_reduction_param(::opencv_caffe::ReductionPara // optional .opencv_caffe.ReLUParameter relu_param = 123; bool LayerParameter::has_relu_param() const { - return (_has_bits_[1] & 0x00080000u) != 0; + return (_has_bits_[1] & 0x00100000u) != 0; } void LayerParameter::set_has_relu_param() { - _has_bits_[1] |= 0x00080000u; + _has_bits_[1] |= 0x00100000u; } void LayerParameter::clear_has_relu_param() { - _has_bits_[1] &= ~0x00080000u; + _has_bits_[1] &= ~0x00100000u; } void LayerParameter::clear_relu_param() { if (relu_param_ != NULL) relu_param_->::opencv_caffe::ReLUParameter::Clear(); @@ -20793,13 +20922,13 @@ void LayerParameter::set_allocated_relu_param(::opencv_caffe::ReLUParameter* rel // optional .opencv_caffe.ReshapeParameter reshape_param = 133; bool LayerParameter::has_reshape_param() const { - return (_has_bits_[1] & 0x00100000u) != 0; + return (_has_bits_[1] & 0x00200000u) != 0; } void LayerParameter::set_has_reshape_param() { - _has_bits_[1] |= 0x00100000u; + _has_bits_[1] |= 0x00200000u; } void LayerParameter::clear_has_reshape_param() { - _has_bits_[1] &= ~0x00100000u; + _has_bits_[1] &= ~0x00200000u; } void LayerParameter::clear_reshape_param() { if (reshape_param_ != NULL) reshape_param_->::opencv_caffe::ReshapeParameter::Clear(); @@ -20838,13 +20967,13 @@ void LayerParameter::set_allocated_reshape_param(::opencv_caffe::ReshapeParamete // optional .opencv_caffe.ROIPoolingParameter roi_pooling_param = 8266711; bool LayerParameter::has_roi_pooling_param() const { - return (_has_bits_[1] & 0x00200000u) != 0; + return (_has_bits_[1] & 0x00400000u) != 0; } void LayerParameter::set_has_roi_pooling_param() { - _has_bits_[1] |= 0x00200000u; + _has_bits_[1] |= 0x00400000u; } void LayerParameter::clear_has_roi_pooling_param() { - _has_bits_[1] &= ~0x00200000u; + _has_bits_[1] &= ~0x00400000u; } void LayerParameter::clear_roi_pooling_param() { if (roi_pooling_param_ != NULL) roi_pooling_param_->::opencv_caffe::ROIPoolingParameter::Clear(); @@ -20883,13 +21012,13 @@ void LayerParameter::set_allocated_roi_pooling_param(::opencv_caffe::ROIPoolingP // optional .opencv_caffe.ScaleParameter scale_param = 142; bool LayerParameter::has_scale_param() const { - return (_has_bits_[1] & 0x00400000u) != 0; + return (_has_bits_[1] & 0x00800000u) != 0; } void LayerParameter::set_has_scale_param() { - _has_bits_[1] |= 0x00400000u; + _has_bits_[1] |= 0x00800000u; } void LayerParameter::clear_has_scale_param() { - _has_bits_[1] &= ~0x00400000u; + _has_bits_[1] &= ~0x00800000u; } void LayerParameter::clear_scale_param() { if (scale_param_ != NULL) scale_param_->::opencv_caffe::ScaleParameter::Clear(); @@ -20928,13 +21057,13 @@ void LayerParameter::set_allocated_scale_param(::opencv_caffe::ScaleParameter* s // optional .opencv_caffe.SigmoidParameter sigmoid_param = 124; bool LayerParameter::has_sigmoid_param() const { - return (_has_bits_[1] & 0x00800000u) != 0; + return (_has_bits_[1] & 0x01000000u) != 0; } void LayerParameter::set_has_sigmoid_param() { - _has_bits_[1] |= 0x00800000u; + _has_bits_[1] |= 0x01000000u; } void LayerParameter::clear_has_sigmoid_param() { - _has_bits_[1] &= ~0x00800000u; + _has_bits_[1] &= ~0x01000000u; } void LayerParameter::clear_sigmoid_param() { if (sigmoid_param_ != NULL) sigmoid_param_->::opencv_caffe::SigmoidParameter::Clear(); @@ -20973,13 +21102,13 @@ void LayerParameter::set_allocated_sigmoid_param(::opencv_caffe::SigmoidParamete // optional .opencv_caffe.SoftmaxParameter softmax_param = 125; bool LayerParameter::has_softmax_param() const { - return (_has_bits_[1] & 0x01000000u) != 0; + return (_has_bits_[1] & 0x02000000u) != 0; } void LayerParameter::set_has_softmax_param() { - _has_bits_[1] |= 0x01000000u; + _has_bits_[1] |= 0x02000000u; } void LayerParameter::clear_has_softmax_param() { - _has_bits_[1] &= ~0x01000000u; + _has_bits_[1] &= ~0x02000000u; } void LayerParameter::clear_softmax_param() { if (softmax_param_ != NULL) softmax_param_->::opencv_caffe::SoftmaxParameter::Clear(); @@ -21018,13 +21147,13 @@ void LayerParameter::set_allocated_softmax_param(::opencv_caffe::SoftmaxParamete // optional .opencv_caffe.SPPParameter spp_param = 132; bool LayerParameter::has_spp_param() const { - return (_has_bits_[1] & 0x02000000u) != 0; + return (_has_bits_[1] & 0x04000000u) != 0; } void LayerParameter::set_has_spp_param() { - _has_bits_[1] |= 0x02000000u; + _has_bits_[1] |= 0x04000000u; } void LayerParameter::clear_has_spp_param() { - _has_bits_[1] &= ~0x02000000u; + _has_bits_[1] &= ~0x04000000u; } void LayerParameter::clear_spp_param() { if (spp_param_ != NULL) spp_param_->::opencv_caffe::SPPParameter::Clear(); @@ -21063,13 +21192,13 @@ void LayerParameter::set_allocated_spp_param(::opencv_caffe::SPPParameter* spp_p // optional .opencv_caffe.SliceParameter slice_param = 126; bool LayerParameter::has_slice_param() const { - return (_has_bits_[1] & 0x04000000u) != 0; + return (_has_bits_[1] & 0x08000000u) != 0; } void LayerParameter::set_has_slice_param() { - _has_bits_[1] |= 0x04000000u; + _has_bits_[1] |= 0x08000000u; } void LayerParameter::clear_has_slice_param() { - _has_bits_[1] &= ~0x04000000u; + _has_bits_[1] &= ~0x08000000u; } void LayerParameter::clear_slice_param() { if (slice_param_ != NULL) slice_param_->::opencv_caffe::SliceParameter::Clear(); @@ -21108,13 +21237,13 @@ void LayerParameter::set_allocated_slice_param(::opencv_caffe::SliceParameter* s // optional .opencv_caffe.TanHParameter tanh_param = 127; bool LayerParameter::has_tanh_param() const { - return (_has_bits_[1] & 0x08000000u) != 0; + return (_has_bits_[1] & 0x10000000u) != 0; } void LayerParameter::set_has_tanh_param() { - _has_bits_[1] |= 0x08000000u; + _has_bits_[1] |= 0x10000000u; } void LayerParameter::clear_has_tanh_param() { - _has_bits_[1] &= ~0x08000000u; + _has_bits_[1] &= ~0x10000000u; } void LayerParameter::clear_tanh_param() { if (tanh_param_ != NULL) tanh_param_->::opencv_caffe::TanHParameter::Clear(); @@ -21153,13 +21282,13 @@ void LayerParameter::set_allocated_tanh_param(::opencv_caffe::TanHParameter* tan // optional .opencv_caffe.ThresholdParameter threshold_param = 128; bool LayerParameter::has_threshold_param() const { - return (_has_bits_[1] & 0x10000000u) != 0; + return (_has_bits_[1] & 0x20000000u) != 0; } void LayerParameter::set_has_threshold_param() { - _has_bits_[1] |= 0x10000000u; + _has_bits_[1] |= 0x20000000u; } void LayerParameter::clear_has_threshold_param() { - _has_bits_[1] &= ~0x10000000u; + _has_bits_[1] &= ~0x20000000u; } void LayerParameter::clear_threshold_param() { if (threshold_param_ != NULL) threshold_param_->::opencv_caffe::ThresholdParameter::Clear(); @@ -21198,13 +21327,13 @@ void LayerParameter::set_allocated_threshold_param(::opencv_caffe::ThresholdPara // optional .opencv_caffe.TileParameter tile_param = 138; bool LayerParameter::has_tile_param() const { - return (_has_bits_[1] & 0x20000000u) != 0; + return (_has_bits_[1] & 0x40000000u) != 0; } void LayerParameter::set_has_tile_param() { - _has_bits_[1] |= 0x20000000u; + _has_bits_[1] |= 0x40000000u; } void LayerParameter::clear_has_tile_param() { - _has_bits_[1] &= ~0x20000000u; + _has_bits_[1] &= ~0x40000000u; } void LayerParameter::clear_tile_param() { if (tile_param_ != NULL) tile_param_->::opencv_caffe::TileParameter::Clear(); @@ -21243,13 +21372,13 @@ void LayerParameter::set_allocated_tile_param(::opencv_caffe::TileParameter* til // optional .opencv_caffe.WindowDataParameter window_data_param = 129; bool LayerParameter::has_window_data_param() const { - return (_has_bits_[1] & 0x40000000u) != 0; + return (_has_bits_[1] & 0x80000000u) != 0; } void LayerParameter::set_has_window_data_param() { - _has_bits_[1] |= 0x40000000u; + _has_bits_[1] |= 0x80000000u; } void LayerParameter::clear_has_window_data_param() { - _has_bits_[1] &= ~0x40000000u; + _has_bits_[1] &= ~0x80000000u; } void LayerParameter::clear_window_data_param() { if (window_data_param_ != NULL) window_data_param_->::opencv_caffe::WindowDataParameter::Clear(); @@ -28938,6 +29067,7 @@ inline const SaveOutputParameter* SaveOutputParameter::internal_default_instance #if !defined(_MSC_VER) || _MSC_VER >= 1900 const int DropoutParameter::kDropoutRatioFieldNumber; +const int DropoutParameter::kScaleTrainFieldNumber; #endif // !defined(_MSC_VER) || _MSC_VER >= 1900 DropoutParameter::DropoutParameter() @@ -28961,6 +29091,7 @@ DropoutParameter::DropoutParameter(const DropoutParameter& from) void DropoutParameter::SharedCtor() { _cached_size_ = 0; dropout_ratio_ = 0.5f; + scale_train_ = true; } DropoutParameter::~DropoutParameter() { @@ -28998,7 +29129,10 @@ DropoutParameter* DropoutParameter::New(::google::protobuf::Arena* arena) const void DropoutParameter::Clear() { // @@protoc_insertion_point(message_clear_start:opencv_caffe.DropoutParameter) - dropout_ratio_ = 0.5f; + if (_has_bits_[0 / 32] & 3u) { + dropout_ratio_ = 0.5f; + scale_train_ = true; + } _has_bits_.Clear(); if (_internal_metadata_.have_unknown_fields()) { mutable_unknown_fields()->Clear(); @@ -29025,6 +29159,21 @@ bool DropoutParameter::MergePartialFromCodedStream( } else { goto handle_unusual; } + if (input->ExpectTag(16)) goto parse_scale_train; + break; + } + + // optional bool scale_train = 2 [default = true]; + case 2: { + if (tag == 16) { + parse_scale_train: + set_has_scale_train(); + DO_((::google::protobuf::internal::WireFormatLite::ReadPrimitive< + bool, ::google::protobuf::internal::WireFormatLite::TYPE_BOOL>( + input, &scale_train_))); + } else { + goto handle_unusual; + } if (input->ExpectAtEnd()) goto success; break; } @@ -29059,6 +29208,11 @@ void DropoutParameter::SerializeWithCachedSizes( ::google::protobuf::internal::WireFormatLite::WriteFloat(1, this->dropout_ratio(), output); } + // optional bool scale_train = 2 [default = true]; + if (has_scale_train()) { + ::google::protobuf::internal::WireFormatLite::WriteBool(2, this->scale_train(), output); + } + if (_internal_metadata_.have_unknown_fields()) { ::google::protobuf::internal::WireFormat::SerializeUnknownFields( unknown_fields(), output); @@ -29075,6 +29229,11 @@ void DropoutParameter::SerializeWithCachedSizes( target = ::google::protobuf::internal::WireFormatLite::WriteFloatToArray(1, this->dropout_ratio(), target); } + // optional bool scale_train = 2 [default = true]; + if (has_scale_train()) { + target = ::google::protobuf::internal::WireFormatLite::WriteBoolToArray(2, this->scale_train(), target); + } + if (_internal_metadata_.have_unknown_fields()) { target = ::google::protobuf::internal::WireFormat::SerializeUnknownFieldsToArray( unknown_fields(), target); @@ -29087,11 +29246,18 @@ size_t DropoutParameter::ByteSizeLong() const { // @@protoc_insertion_point(message_byte_size_start:opencv_caffe.DropoutParameter) size_t total_size = 0; - // optional float dropout_ratio = 1 [default = 0.5]; - if (has_dropout_ratio()) { - total_size += 1 + 4; - } + if (_has_bits_[0 / 32] & 3u) { + // optional float dropout_ratio = 1 [default = 0.5]; + if (has_dropout_ratio()) { + total_size += 1 + 4; + } + + // optional bool scale_train = 2 [default = true]; + if (has_scale_train()) { + total_size += 1 + 1; + } + } if (_internal_metadata_.have_unknown_fields()) { total_size += ::google::protobuf::internal::WireFormat::ComputeUnknownFieldsSize( @@ -29134,6 +29300,9 @@ void DropoutParameter::UnsafeMergeFrom(const DropoutParameter& from) { if (from.has_dropout_ratio()) { set_dropout_ratio(from.dropout_ratio()); } + if (from.has_scale_train()) { + set_scale_train(from.scale_train()); + } } if (from._internal_metadata_.have_unknown_fields()) { ::google::protobuf::UnknownFieldSet::MergeToInternalMetdata( @@ -29166,6 +29335,7 @@ void DropoutParameter::Swap(DropoutParameter* other) { } void DropoutParameter::InternalSwap(DropoutParameter* other) { std::swap(dropout_ratio_, other->dropout_ratio_); + std::swap(scale_train_, other->scale_train_); std::swap(_has_bits_[0], other->_has_bits_[0]); _internal_metadata_.Swap(&other->_internal_metadata_); std::swap(_cached_size_, other->_cached_size_); @@ -29206,6 +29376,30 @@ void DropoutParameter::set_dropout_ratio(float value) { // @@protoc_insertion_point(field_set:opencv_caffe.DropoutParameter.dropout_ratio) } +// optional bool scale_train = 2 [default = true]; +bool DropoutParameter::has_scale_train() const { + return (_has_bits_[0] & 0x00000002u) != 0; +} +void DropoutParameter::set_has_scale_train() { + _has_bits_[0] |= 0x00000002u; +} +void DropoutParameter::clear_has_scale_train() { + _has_bits_[0] &= ~0x00000002u; +} +void DropoutParameter::clear_scale_train() { + scale_train_ = true; + clear_has_scale_train(); +} +bool DropoutParameter::scale_train() const { + // @@protoc_insertion_point(field_get:opencv_caffe.DropoutParameter.scale_train) + return scale_train_; +} +void DropoutParameter::set_scale_train(bool value) { + set_has_scale_train(); + scale_train_ = value; + // @@protoc_insertion_point(field_set:opencv_caffe.DropoutParameter.scale_train) +} + inline const DropoutParameter* DropoutParameter::internal_default_instance() { return &DropoutParameter_default_instance_.get(); } @@ -54806,6 +55000,752 @@ inline const ROIPoolingParameter* ROIPoolingParameter::internal_default_instance } #endif // PROTOBUF_INLINE_NOT_IN_HEADERS +// =================================================================== + +#if !defined(_MSC_VER) || _MSC_VER >= 1900 +const int ProposalParameter::kFeatStrideFieldNumber; +const int ProposalParameter::kBaseSizeFieldNumber; +const int ProposalParameter::kMinSizeFieldNumber; +const int ProposalParameter::kRatioFieldNumber; +const int ProposalParameter::kScaleFieldNumber; +const int ProposalParameter::kPreNmsTopnFieldNumber; +const int ProposalParameter::kPostNmsTopnFieldNumber; +const int ProposalParameter::kNmsThreshFieldNumber; +#endif // !defined(_MSC_VER) || _MSC_VER >= 1900 + +ProposalParameter::ProposalParameter() + : ::google::protobuf::Message(), _internal_metadata_(NULL) { + if (this != internal_default_instance()) protobuf_InitDefaults_opencv_2dcaffe_2eproto(); + SharedCtor(); + // @@protoc_insertion_point(constructor:opencv_caffe.ProposalParameter) +} + +void ProposalParameter::InitAsDefaultInstance() { +} + +ProposalParameter::ProposalParameter(const ProposalParameter& from) + : ::google::protobuf::Message(), + _internal_metadata_(NULL) { + SharedCtor(); + UnsafeMergeFrom(from); + // @@protoc_insertion_point(copy_constructor:opencv_caffe.ProposalParameter) +} + +void ProposalParameter::SharedCtor() { + _cached_size_ = 0; + feat_stride_ = 16u; + base_size_ = 16u; + min_size_ = 16u; + pre_nms_topn_ = 6000u; + post_nms_topn_ = 300u; + nms_thresh_ = 0.7f; +} + +ProposalParameter::~ProposalParameter() { + // @@protoc_insertion_point(destructor:opencv_caffe.ProposalParameter) + SharedDtor(); +} + +void ProposalParameter::SharedDtor() { +} + +void ProposalParameter::SetCachedSize(int size) const { + GOOGLE_SAFE_CONCURRENT_WRITES_BEGIN(); + _cached_size_ = size; + GOOGLE_SAFE_CONCURRENT_WRITES_END(); +} +const ::google::protobuf::Descriptor* ProposalParameter::descriptor() { + protobuf_AssignDescriptorsOnce(); + return ProposalParameter_descriptor_; +} + +const ProposalParameter& ProposalParameter::default_instance() { + protobuf_InitDefaults_opencv_2dcaffe_2eproto(); + return *internal_default_instance(); +} + +::google::protobuf::internal::ExplicitlyConstructed ProposalParameter_default_instance_; + +ProposalParameter* ProposalParameter::New(::google::protobuf::Arena* arena) const { + ProposalParameter* n = new ProposalParameter; + if (arena != NULL) { + arena->Own(n); + } + return n; +} + +void ProposalParameter::Clear() { +// @@protoc_insertion_point(message_clear_start:opencv_caffe.ProposalParameter) + if (_has_bits_[0 / 32] & 231u) { + feat_stride_ = 16u; + base_size_ = 16u; + min_size_ = 16u; + pre_nms_topn_ = 6000u; + post_nms_topn_ = 300u; + nms_thresh_ = 0.7f; + } + ratio_.Clear(); + scale_.Clear(); + _has_bits_.Clear(); + if (_internal_metadata_.have_unknown_fields()) { + mutable_unknown_fields()->Clear(); + } +} + +bool ProposalParameter::MergePartialFromCodedStream( + ::google::protobuf::io::CodedInputStream* input) { +#define DO_(EXPRESSION) if (!GOOGLE_PREDICT_TRUE(EXPRESSION)) goto failure + ::google::protobuf::uint32 tag; + // @@protoc_insertion_point(parse_start:opencv_caffe.ProposalParameter) + for (;;) { + ::std::pair< ::google::protobuf::uint32, bool> p = input->ReadTagWithCutoff(127); + tag = p.first; + if (!p.second) goto handle_unusual; + switch (::google::protobuf::internal::WireFormatLite::GetTagFieldNumber(tag)) { + // optional uint32 feat_stride = 1 [default = 16]; + case 1: { + if (tag == 8) { + set_has_feat_stride(); + DO_((::google::protobuf::internal::WireFormatLite::ReadPrimitive< + ::google::protobuf::uint32, ::google::protobuf::internal::WireFormatLite::TYPE_UINT32>( + input, &feat_stride_))); + } else { + goto handle_unusual; + } + if (input->ExpectTag(16)) goto parse_base_size; + break; + } + + // optional uint32 base_size = 2 [default = 16]; + case 2: { + if (tag == 16) { + parse_base_size: + set_has_base_size(); + DO_((::google::protobuf::internal::WireFormatLite::ReadPrimitive< + ::google::protobuf::uint32, ::google::protobuf::internal::WireFormatLite::TYPE_UINT32>( + input, &base_size_))); + } else { + goto handle_unusual; + } + if (input->ExpectTag(24)) goto parse_min_size; + break; + } + + // optional uint32 min_size = 3 [default = 16]; + case 3: { + if (tag == 24) { + parse_min_size: + set_has_min_size(); + DO_((::google::protobuf::internal::WireFormatLite::ReadPrimitive< + ::google::protobuf::uint32, ::google::protobuf::internal::WireFormatLite::TYPE_UINT32>( + input, &min_size_))); + } else { + goto handle_unusual; + } + if (input->ExpectTag(37)) goto parse_ratio; + break; + } + + // repeated float ratio = 4; + case 4: { + if (tag == 37) { + parse_ratio: + DO_((::google::protobuf::internal::WireFormatLite::ReadRepeatedPrimitive< + float, ::google::protobuf::internal::WireFormatLite::TYPE_FLOAT>( + 1, 37, input, this->mutable_ratio()))); + } else if (tag == 34) { + DO_((::google::protobuf::internal::WireFormatLite::ReadPackedPrimitiveNoInline< + float, ::google::protobuf::internal::WireFormatLite::TYPE_FLOAT>( + input, this->mutable_ratio()))); + } else { + goto handle_unusual; + } + if (input->ExpectTag(37)) goto parse_ratio; + if (input->ExpectTag(45)) goto parse_scale; + break; + } + + // repeated float scale = 5; + case 5: { + if (tag == 45) { + parse_scale: + DO_((::google::protobuf::internal::WireFormatLite::ReadRepeatedPrimitive< + float, ::google::protobuf::internal::WireFormatLite::TYPE_FLOAT>( + 1, 45, input, this->mutable_scale()))); + } else if (tag == 42) { + DO_((::google::protobuf::internal::WireFormatLite::ReadPackedPrimitiveNoInline< + float, ::google::protobuf::internal::WireFormatLite::TYPE_FLOAT>( + input, this->mutable_scale()))); + } else { + goto handle_unusual; + } + if (input->ExpectTag(45)) goto parse_scale; + if (input->ExpectTag(48)) goto parse_pre_nms_topn; + break; + } + + // optional uint32 pre_nms_topn = 6 [default = 6000]; + case 6: { + if (tag == 48) { + parse_pre_nms_topn: + set_has_pre_nms_topn(); + DO_((::google::protobuf::internal::WireFormatLite::ReadPrimitive< + ::google::protobuf::uint32, ::google::protobuf::internal::WireFormatLite::TYPE_UINT32>( + input, &pre_nms_topn_))); + } else { + goto handle_unusual; + } + if (input->ExpectTag(56)) goto parse_post_nms_topn; + break; + } + + // optional uint32 post_nms_topn = 7 [default = 300]; + case 7: { + if (tag == 56) { + parse_post_nms_topn: + set_has_post_nms_topn(); + DO_((::google::protobuf::internal::WireFormatLite::ReadPrimitive< + ::google::protobuf::uint32, ::google::protobuf::internal::WireFormatLite::TYPE_UINT32>( + input, &post_nms_topn_))); + } else { + goto handle_unusual; + } + if (input->ExpectTag(69)) goto parse_nms_thresh; + break; + } + + // optional float nms_thresh = 8 [default = 0.7]; + case 8: { + if (tag == 69) { + parse_nms_thresh: + set_has_nms_thresh(); + DO_((::google::protobuf::internal::WireFormatLite::ReadPrimitive< + float, ::google::protobuf::internal::WireFormatLite::TYPE_FLOAT>( + input, &nms_thresh_))); + } else { + goto handle_unusual; + } + if (input->ExpectAtEnd()) goto success; + break; + } + + default: { + handle_unusual: + if (tag == 0 || + ::google::protobuf::internal::WireFormatLite::GetTagWireType(tag) == + ::google::protobuf::internal::WireFormatLite::WIRETYPE_END_GROUP) { + goto success; + } + DO_(::google::protobuf::internal::WireFormat::SkipField( + input, tag, mutable_unknown_fields())); + break; + } + } + } +success: + // @@protoc_insertion_point(parse_success:opencv_caffe.ProposalParameter) + return true; +failure: + // @@protoc_insertion_point(parse_failure:opencv_caffe.ProposalParameter) + return false; +#undef DO_ +} + +void ProposalParameter::SerializeWithCachedSizes( + ::google::protobuf::io::CodedOutputStream* output) const { + // @@protoc_insertion_point(serialize_start:opencv_caffe.ProposalParameter) + // optional uint32 feat_stride = 1 [default = 16]; + if (has_feat_stride()) { + ::google::protobuf::internal::WireFormatLite::WriteUInt32(1, this->feat_stride(), output); + } + + // optional uint32 base_size = 2 [default = 16]; + if (has_base_size()) { + ::google::protobuf::internal::WireFormatLite::WriteUInt32(2, this->base_size(), output); + } + + // optional uint32 min_size = 3 [default = 16]; + if (has_min_size()) { + ::google::protobuf::internal::WireFormatLite::WriteUInt32(3, this->min_size(), output); + } + + // repeated float ratio = 4; + for (int i = 0; i < this->ratio_size(); i++) { + ::google::protobuf::internal::WireFormatLite::WriteFloat( + 4, this->ratio(i), output); + } + + // repeated float scale = 5; + for (int i = 0; i < this->scale_size(); i++) { + ::google::protobuf::internal::WireFormatLite::WriteFloat( + 5, this->scale(i), output); + } + + // optional uint32 pre_nms_topn = 6 [default = 6000]; + if (has_pre_nms_topn()) { + ::google::protobuf::internal::WireFormatLite::WriteUInt32(6, this->pre_nms_topn(), output); + } + + // optional uint32 post_nms_topn = 7 [default = 300]; + if (has_post_nms_topn()) { + ::google::protobuf::internal::WireFormatLite::WriteUInt32(7, this->post_nms_topn(), output); + } + + // optional float nms_thresh = 8 [default = 0.7]; + if (has_nms_thresh()) { + ::google::protobuf::internal::WireFormatLite::WriteFloat(8, this->nms_thresh(), output); + } + + if (_internal_metadata_.have_unknown_fields()) { + ::google::protobuf::internal::WireFormat::SerializeUnknownFields( + unknown_fields(), output); + } + // @@protoc_insertion_point(serialize_end:opencv_caffe.ProposalParameter) +} + +::google::protobuf::uint8* ProposalParameter::InternalSerializeWithCachedSizesToArray( + bool deterministic, ::google::protobuf::uint8* target) const { + (void)deterministic; // Unused + // @@protoc_insertion_point(serialize_to_array_start:opencv_caffe.ProposalParameter) + // optional uint32 feat_stride = 1 [default = 16]; + if (has_feat_stride()) { + target = ::google::protobuf::internal::WireFormatLite::WriteUInt32ToArray(1, this->feat_stride(), target); + } + + // optional uint32 base_size = 2 [default = 16]; + if (has_base_size()) { + target = ::google::protobuf::internal::WireFormatLite::WriteUInt32ToArray(2, this->base_size(), target); + } + + // optional uint32 min_size = 3 [default = 16]; + if (has_min_size()) { + target = ::google::protobuf::internal::WireFormatLite::WriteUInt32ToArray(3, this->min_size(), target); + } + + // repeated float ratio = 4; + for (int i = 0; i < this->ratio_size(); i++) { + target = ::google::protobuf::internal::WireFormatLite:: + WriteFloatToArray(4, this->ratio(i), target); + } + + // repeated float scale = 5; + for (int i = 0; i < this->scale_size(); i++) { + target = ::google::protobuf::internal::WireFormatLite:: + WriteFloatToArray(5, this->scale(i), target); + } + + // optional uint32 pre_nms_topn = 6 [default = 6000]; + if (has_pre_nms_topn()) { + target = ::google::protobuf::internal::WireFormatLite::WriteUInt32ToArray(6, this->pre_nms_topn(), target); + } + + // optional uint32 post_nms_topn = 7 [default = 300]; + if (has_post_nms_topn()) { + target = ::google::protobuf::internal::WireFormatLite::WriteUInt32ToArray(7, this->post_nms_topn(), target); + } + + // optional float nms_thresh = 8 [default = 0.7]; + if (has_nms_thresh()) { + target = ::google::protobuf::internal::WireFormatLite::WriteFloatToArray(8, this->nms_thresh(), target); + } + + if (_internal_metadata_.have_unknown_fields()) { + target = ::google::protobuf::internal::WireFormat::SerializeUnknownFieldsToArray( + unknown_fields(), target); + } + // @@protoc_insertion_point(serialize_to_array_end:opencv_caffe.ProposalParameter) + return target; +} + +size_t ProposalParameter::ByteSizeLong() const { +// @@protoc_insertion_point(message_byte_size_start:opencv_caffe.ProposalParameter) + size_t total_size = 0; + + if (_has_bits_[0 / 32] & 231u) { + // optional uint32 feat_stride = 1 [default = 16]; + if (has_feat_stride()) { + total_size += 1 + + ::google::protobuf::internal::WireFormatLite::UInt32Size( + this->feat_stride()); + } + + // optional uint32 base_size = 2 [default = 16]; + if (has_base_size()) { + total_size += 1 + + ::google::protobuf::internal::WireFormatLite::UInt32Size( + this->base_size()); + } + + // optional uint32 min_size = 3 [default = 16]; + if (has_min_size()) { + total_size += 1 + + ::google::protobuf::internal::WireFormatLite::UInt32Size( + this->min_size()); + } + + // optional uint32 pre_nms_topn = 6 [default = 6000]; + if (has_pre_nms_topn()) { + total_size += 1 + + ::google::protobuf::internal::WireFormatLite::UInt32Size( + this->pre_nms_topn()); + } + + // optional uint32 post_nms_topn = 7 [default = 300]; + if (has_post_nms_topn()) { + total_size += 1 + + ::google::protobuf::internal::WireFormatLite::UInt32Size( + this->post_nms_topn()); + } + + // optional float nms_thresh = 8 [default = 0.7]; + if (has_nms_thresh()) { + total_size += 1 + 4; + } + + } + // repeated float ratio = 4; + { + size_t data_size = 0; + unsigned int count = this->ratio_size(); + data_size = 4UL * count; + total_size += 1 * + ::google::protobuf::internal::FromIntSize(this->ratio_size()); + total_size += data_size; + } + + // repeated float scale = 5; + { + size_t data_size = 0; + unsigned int count = this->scale_size(); + data_size = 4UL * count; + total_size += 1 * + ::google::protobuf::internal::FromIntSize(this->scale_size()); + total_size += data_size; + } + + if (_internal_metadata_.have_unknown_fields()) { + total_size += + ::google::protobuf::internal::WireFormat::ComputeUnknownFieldsSize( + unknown_fields()); + } + int cached_size = ::google::protobuf::internal::ToCachedSize(total_size); + GOOGLE_SAFE_CONCURRENT_WRITES_BEGIN(); + _cached_size_ = cached_size; + GOOGLE_SAFE_CONCURRENT_WRITES_END(); + return total_size; +} + +void ProposalParameter::MergeFrom(const ::google::protobuf::Message& from) { +// @@protoc_insertion_point(generalized_merge_from_start:opencv_caffe.ProposalParameter) + if (GOOGLE_PREDICT_FALSE(&from == this)) MergeFromFail(__LINE__); + const ProposalParameter* source = + ::google::protobuf::internal::DynamicCastToGenerated( + &from); + if (source == NULL) { + // @@protoc_insertion_point(generalized_merge_from_cast_fail:opencv_caffe.ProposalParameter) + ::google::protobuf::internal::ReflectionOps::Merge(from, this); + } else { + // @@protoc_insertion_point(generalized_merge_from_cast_success:opencv_caffe.ProposalParameter) + UnsafeMergeFrom(*source); + } +} + +void ProposalParameter::MergeFrom(const ProposalParameter& from) { +// @@protoc_insertion_point(class_specific_merge_from_start:opencv_caffe.ProposalParameter) + if (GOOGLE_PREDICT_TRUE(&from != this)) { + UnsafeMergeFrom(from); + } else { + MergeFromFail(__LINE__); + } +} + +void ProposalParameter::UnsafeMergeFrom(const ProposalParameter& from) { + GOOGLE_DCHECK(&from != this); + ratio_.UnsafeMergeFrom(from.ratio_); + scale_.UnsafeMergeFrom(from.scale_); + if (from._has_bits_[0 / 32] & (0xffu << (0 % 32))) { + if (from.has_feat_stride()) { + set_feat_stride(from.feat_stride()); + } + if (from.has_base_size()) { + set_base_size(from.base_size()); + } + if (from.has_min_size()) { + set_min_size(from.min_size()); + } + if (from.has_pre_nms_topn()) { + set_pre_nms_topn(from.pre_nms_topn()); + } + if (from.has_post_nms_topn()) { + set_post_nms_topn(from.post_nms_topn()); + } + if (from.has_nms_thresh()) { + set_nms_thresh(from.nms_thresh()); + } + } + if (from._internal_metadata_.have_unknown_fields()) { + ::google::protobuf::UnknownFieldSet::MergeToInternalMetdata( + from.unknown_fields(), &_internal_metadata_); + } +} + +void ProposalParameter::CopyFrom(const ::google::protobuf::Message& from) { +// @@protoc_insertion_point(generalized_copy_from_start:opencv_caffe.ProposalParameter) + if (&from == this) return; + Clear(); + MergeFrom(from); +} + +void ProposalParameter::CopyFrom(const ProposalParameter& from) { +// @@protoc_insertion_point(class_specific_copy_from_start:opencv_caffe.ProposalParameter) + if (&from == this) return; + Clear(); + UnsafeMergeFrom(from); +} + +bool ProposalParameter::IsInitialized() const { + + return true; +} + +void ProposalParameter::Swap(ProposalParameter* other) { + if (other == this) return; + InternalSwap(other); +} +void ProposalParameter::InternalSwap(ProposalParameter* other) { + std::swap(feat_stride_, other->feat_stride_); + std::swap(base_size_, other->base_size_); + std::swap(min_size_, other->min_size_); + ratio_.UnsafeArenaSwap(&other->ratio_); + scale_.UnsafeArenaSwap(&other->scale_); + std::swap(pre_nms_topn_, other->pre_nms_topn_); + std::swap(post_nms_topn_, other->post_nms_topn_); + std::swap(nms_thresh_, other->nms_thresh_); + std::swap(_has_bits_[0], other->_has_bits_[0]); + _internal_metadata_.Swap(&other->_internal_metadata_); + std::swap(_cached_size_, other->_cached_size_); +} + +::google::protobuf::Metadata ProposalParameter::GetMetadata() const { + protobuf_AssignDescriptorsOnce(); + ::google::protobuf::Metadata metadata; + metadata.descriptor = ProposalParameter_descriptor_; + metadata.reflection = ProposalParameter_reflection_; + return metadata; +} + +#if PROTOBUF_INLINE_NOT_IN_HEADERS +// ProposalParameter + +// optional uint32 feat_stride = 1 [default = 16]; +bool ProposalParameter::has_feat_stride() const { + return (_has_bits_[0] & 0x00000001u) != 0; +} +void ProposalParameter::set_has_feat_stride() { + _has_bits_[0] |= 0x00000001u; +} +void ProposalParameter::clear_has_feat_stride() { + _has_bits_[0] &= ~0x00000001u; +} +void ProposalParameter::clear_feat_stride() { + feat_stride_ = 16u; + clear_has_feat_stride(); +} +::google::protobuf::uint32 ProposalParameter::feat_stride() const { + // @@protoc_insertion_point(field_get:opencv_caffe.ProposalParameter.feat_stride) + return feat_stride_; +} +void ProposalParameter::set_feat_stride(::google::protobuf::uint32 value) { + set_has_feat_stride(); + feat_stride_ = value; + // @@protoc_insertion_point(field_set:opencv_caffe.ProposalParameter.feat_stride) +} + +// optional uint32 base_size = 2 [default = 16]; +bool ProposalParameter::has_base_size() const { + return (_has_bits_[0] & 0x00000002u) != 0; +} +void ProposalParameter::set_has_base_size() { + _has_bits_[0] |= 0x00000002u; +} +void ProposalParameter::clear_has_base_size() { + _has_bits_[0] &= ~0x00000002u; +} +void ProposalParameter::clear_base_size() { + base_size_ = 16u; + clear_has_base_size(); +} +::google::protobuf::uint32 ProposalParameter::base_size() const { + // @@protoc_insertion_point(field_get:opencv_caffe.ProposalParameter.base_size) + return base_size_; +} +void ProposalParameter::set_base_size(::google::protobuf::uint32 value) { + set_has_base_size(); + base_size_ = value; + // @@protoc_insertion_point(field_set:opencv_caffe.ProposalParameter.base_size) +} + +// optional uint32 min_size = 3 [default = 16]; +bool ProposalParameter::has_min_size() const { + return (_has_bits_[0] & 0x00000004u) != 0; +} +void ProposalParameter::set_has_min_size() { + _has_bits_[0] |= 0x00000004u; +} +void ProposalParameter::clear_has_min_size() { + _has_bits_[0] &= ~0x00000004u; +} +void ProposalParameter::clear_min_size() { + min_size_ = 16u; + clear_has_min_size(); +} +::google::protobuf::uint32 ProposalParameter::min_size() const { + // @@protoc_insertion_point(field_get:opencv_caffe.ProposalParameter.min_size) + return min_size_; +} +void ProposalParameter::set_min_size(::google::protobuf::uint32 value) { + set_has_min_size(); + min_size_ = value; + // @@protoc_insertion_point(field_set:opencv_caffe.ProposalParameter.min_size) +} + +// repeated float ratio = 4; +int ProposalParameter::ratio_size() const { + return ratio_.size(); +} +void ProposalParameter::clear_ratio() { + ratio_.Clear(); +} +float ProposalParameter::ratio(int index) const { + // @@protoc_insertion_point(field_get:opencv_caffe.ProposalParameter.ratio) + return ratio_.Get(index); +} +void ProposalParameter::set_ratio(int index, float value) { + ratio_.Set(index, value); + // @@protoc_insertion_point(field_set:opencv_caffe.ProposalParameter.ratio) +} +void ProposalParameter::add_ratio(float value) { + ratio_.Add(value); + // @@protoc_insertion_point(field_add:opencv_caffe.ProposalParameter.ratio) +} +const ::google::protobuf::RepeatedField< float >& +ProposalParameter::ratio() const { + // @@protoc_insertion_point(field_list:opencv_caffe.ProposalParameter.ratio) + return ratio_; +} +::google::protobuf::RepeatedField< float >* +ProposalParameter::mutable_ratio() { + // @@protoc_insertion_point(field_mutable_list:opencv_caffe.ProposalParameter.ratio) + return &ratio_; +} + +// repeated float scale = 5; +int ProposalParameter::scale_size() const { + return scale_.size(); +} +void ProposalParameter::clear_scale() { + scale_.Clear(); +} +float ProposalParameter::scale(int index) const { + // @@protoc_insertion_point(field_get:opencv_caffe.ProposalParameter.scale) + return scale_.Get(index); +} +void ProposalParameter::set_scale(int index, float value) { + scale_.Set(index, value); + // @@protoc_insertion_point(field_set:opencv_caffe.ProposalParameter.scale) +} +void ProposalParameter::add_scale(float value) { + scale_.Add(value); + // @@protoc_insertion_point(field_add:opencv_caffe.ProposalParameter.scale) +} +const ::google::protobuf::RepeatedField< float >& +ProposalParameter::scale() const { + // @@protoc_insertion_point(field_list:opencv_caffe.ProposalParameter.scale) + return scale_; +} +::google::protobuf::RepeatedField< float >* +ProposalParameter::mutable_scale() { + // @@protoc_insertion_point(field_mutable_list:opencv_caffe.ProposalParameter.scale) + return &scale_; +} + +// optional uint32 pre_nms_topn = 6 [default = 6000]; +bool ProposalParameter::has_pre_nms_topn() const { + return (_has_bits_[0] & 0x00000020u) != 0; +} +void ProposalParameter::set_has_pre_nms_topn() { + _has_bits_[0] |= 0x00000020u; +} +void ProposalParameter::clear_has_pre_nms_topn() { + _has_bits_[0] &= ~0x00000020u; +} +void ProposalParameter::clear_pre_nms_topn() { + pre_nms_topn_ = 6000u; + clear_has_pre_nms_topn(); +} +::google::protobuf::uint32 ProposalParameter::pre_nms_topn() const { + // @@protoc_insertion_point(field_get:opencv_caffe.ProposalParameter.pre_nms_topn) + return pre_nms_topn_; +} +void ProposalParameter::set_pre_nms_topn(::google::protobuf::uint32 value) { + set_has_pre_nms_topn(); + pre_nms_topn_ = value; + // @@protoc_insertion_point(field_set:opencv_caffe.ProposalParameter.pre_nms_topn) +} + +// optional uint32 post_nms_topn = 7 [default = 300]; +bool ProposalParameter::has_post_nms_topn() const { + return (_has_bits_[0] & 0x00000040u) != 0; +} +void ProposalParameter::set_has_post_nms_topn() { + _has_bits_[0] |= 0x00000040u; +} +void ProposalParameter::clear_has_post_nms_topn() { + _has_bits_[0] &= ~0x00000040u; +} +void ProposalParameter::clear_post_nms_topn() { + post_nms_topn_ = 300u; + clear_has_post_nms_topn(); +} +::google::protobuf::uint32 ProposalParameter::post_nms_topn() const { + // @@protoc_insertion_point(field_get:opencv_caffe.ProposalParameter.post_nms_topn) + return post_nms_topn_; +} +void ProposalParameter::set_post_nms_topn(::google::protobuf::uint32 value) { + set_has_post_nms_topn(); + post_nms_topn_ = value; + // @@protoc_insertion_point(field_set:opencv_caffe.ProposalParameter.post_nms_topn) +} + +// optional float nms_thresh = 8 [default = 0.7]; +bool ProposalParameter::has_nms_thresh() const { + return (_has_bits_[0] & 0x00000080u) != 0; +} +void ProposalParameter::set_has_nms_thresh() { + _has_bits_[0] |= 0x00000080u; +} +void ProposalParameter::clear_has_nms_thresh() { + _has_bits_[0] &= ~0x00000080u; +} +void ProposalParameter::clear_nms_thresh() { + nms_thresh_ = 0.7f; + clear_has_nms_thresh(); +} +float ProposalParameter::nms_thresh() const { + // @@protoc_insertion_point(field_get:opencv_caffe.ProposalParameter.nms_thresh) + return nms_thresh_; +} +void ProposalParameter::set_nms_thresh(float value) { + set_has_nms_thresh(); + nms_thresh_ = value; + // @@protoc_insertion_point(field_set:opencv_caffe.ProposalParameter.nms_thresh) +} + +inline const ProposalParameter* ProposalParameter::internal_default_instance() { + return &ProposalParameter_default_instance_.get(); +} +#endif // PROTOBUF_INLINE_NOT_IN_HEADERS + // @@protoc_insertion_point(namespace_scope) } // namespace opencv_caffe diff --git a/modules/dnn/misc/caffe/opencv-caffe.pb.h b/modules/dnn/misc/caffe/opencv-caffe.pb.h index 0ee607c..74b3532 100644 --- a/modules/dnn/misc/caffe/opencv-caffe.pb.h +++ b/modules/dnn/misc/caffe/opencv-caffe.pb.h @@ -86,6 +86,7 @@ class PermuteParameter; class PoolingParameter; class PowerParameter; class PriorBoxParameter; +class ProposalParameter; class PythonParameter; class ROIPoolingParameter; class ReLUParameter; @@ -4138,6 +4139,15 @@ class LayerParameter : public ::google::protobuf::Message /* @@protoc_insertion_ ::opencv_caffe::PriorBoxParameter* release_prior_box_param(); void set_allocated_prior_box_param(::opencv_caffe::PriorBoxParameter* prior_box_param); + // optional .opencv_caffe.ProposalParameter proposal_param = 201; + bool has_proposal_param() const; + void clear_proposal_param(); + static const int kProposalParamFieldNumber = 201; + const ::opencv_caffe::ProposalParameter& proposal_param() const; + ::opencv_caffe::ProposalParameter* mutable_proposal_param(); + ::opencv_caffe::ProposalParameter* release_proposal_param(); + void set_allocated_proposal_param(::opencv_caffe::ProposalParameter* proposal_param); + // optional .opencv_caffe.PythonParameter python_param = 130; bool has_python_param() const; void clear_python_param(); @@ -4355,6 +4365,8 @@ class LayerParameter : public ::google::protobuf::Message /* @@protoc_insertion_ inline void clear_has_prelu_param(); inline void set_has_prior_box_param(); inline void clear_has_prior_box_param(); + inline void set_has_proposal_param(); + inline void clear_has_proposal_param(); inline void set_has_python_param(); inline void clear_has_python_param(); inline void set_has_recurrent_param(); @@ -4435,6 +4447,7 @@ class LayerParameter : public ::google::protobuf::Message /* @@protoc_insertion_ ::opencv_caffe::PowerParameter* power_param_; ::opencv_caffe::PReLUParameter* prelu_param_; ::opencv_caffe::PriorBoxParameter* prior_box_param_; + ::opencv_caffe::ProposalParameter* proposal_param_; ::opencv_caffe::PythonParameter* python_param_; ::opencv_caffe::RecurrentParameter* recurrent_param_; ::opencv_caffe::ReductionParameter* reduction_param_; @@ -6483,15 +6496,25 @@ class DropoutParameter : public ::google::protobuf::Message /* @@protoc_insertio float dropout_ratio() const; void set_dropout_ratio(float value); + // optional bool scale_train = 2 [default = true]; + bool has_scale_train() const; + void clear_scale_train(); + static const int kScaleTrainFieldNumber = 2; + bool scale_train() const; + void set_scale_train(bool value); + // @@protoc_insertion_point(class_scope:opencv_caffe.DropoutParameter) private: inline void set_has_dropout_ratio(); inline void clear_has_dropout_ratio(); + inline void set_has_scale_train(); + inline void clear_has_scale_train(); ::google::protobuf::internal::InternalMetadataWithArena _internal_metadata_; ::google::protobuf::internal::HasBits<1> _has_bits_; mutable int _cached_size_; float dropout_ratio_; + bool scale_train_; friend void protobuf_InitDefaults_opencv_2dcaffe_2eproto_impl(); friend void protobuf_AddDesc_opencv_2dcaffe_2eproto_impl(); friend void protobuf_AssignDesc_opencv_2dcaffe_2eproto(); @@ -12914,6 +12937,180 @@ class ROIPoolingParameter : public ::google::protobuf::Message /* @@protoc_inser }; extern ::google::protobuf::internal::ExplicitlyConstructed ROIPoolingParameter_default_instance_; +// ------------------------------------------------------------------- + +class ProposalParameter : public ::google::protobuf::Message /* @@protoc_insertion_point(class_definition:opencv_caffe.ProposalParameter) */ { + public: + ProposalParameter(); + virtual ~ProposalParameter(); + + ProposalParameter(const ProposalParameter& from); + + inline ProposalParameter& operator=(const ProposalParameter& from) { + CopyFrom(from); + return *this; + } + + inline const ::google::protobuf::UnknownFieldSet& unknown_fields() const { + return _internal_metadata_.unknown_fields(); + } + + inline ::google::protobuf::UnknownFieldSet* mutable_unknown_fields() { + return _internal_metadata_.mutable_unknown_fields(); + } + + static const ::google::protobuf::Descriptor* descriptor(); + static const ProposalParameter& default_instance(); + + static const ProposalParameter* internal_default_instance(); + + void Swap(ProposalParameter* other); + + // implements Message ---------------------------------------------- + + inline ProposalParameter* New() const { return New(NULL); } + + ProposalParameter* New(::google::protobuf::Arena* arena) const; + void CopyFrom(const ::google::protobuf::Message& from); + void MergeFrom(const ::google::protobuf::Message& from); + void CopyFrom(const ProposalParameter& from); + void MergeFrom(const ProposalParameter& from); + void Clear(); + bool IsInitialized() const; + + size_t ByteSizeLong() const; + bool MergePartialFromCodedStream( + ::google::protobuf::io::CodedInputStream* input); + void SerializeWithCachedSizes( + ::google::protobuf::io::CodedOutputStream* output) const; + ::google::protobuf::uint8* InternalSerializeWithCachedSizesToArray( + bool deterministic, ::google::protobuf::uint8* output) const; + ::google::protobuf::uint8* SerializeWithCachedSizesToArray(::google::protobuf::uint8* output) const { + return InternalSerializeWithCachedSizesToArray(false, output); + } + int GetCachedSize() const { return _cached_size_; } + private: + void SharedCtor(); + void SharedDtor(); + void SetCachedSize(int size) const; + void InternalSwap(ProposalParameter* other); + void UnsafeMergeFrom(const ProposalParameter& from); + private: + inline ::google::protobuf::Arena* GetArenaNoVirtual() const { + return _internal_metadata_.arena(); + } + inline void* MaybeArenaPtr() const { + return _internal_metadata_.raw_arena_ptr(); + } + public: + + ::google::protobuf::Metadata GetMetadata() const; + + // nested types ---------------------------------------------------- + + // accessors ------------------------------------------------------- + + // optional uint32 feat_stride = 1 [default = 16]; + bool has_feat_stride() const; + void clear_feat_stride(); + static const int kFeatStrideFieldNumber = 1; + ::google::protobuf::uint32 feat_stride() const; + void set_feat_stride(::google::protobuf::uint32 value); + + // optional uint32 base_size = 2 [default = 16]; + bool has_base_size() const; + void clear_base_size(); + static const int kBaseSizeFieldNumber = 2; + ::google::protobuf::uint32 base_size() const; + void set_base_size(::google::protobuf::uint32 value); + + // optional uint32 min_size = 3 [default = 16]; + bool has_min_size() const; + void clear_min_size(); + static const int kMinSizeFieldNumber = 3; + ::google::protobuf::uint32 min_size() const; + void set_min_size(::google::protobuf::uint32 value); + + // repeated float ratio = 4; + int ratio_size() const; + void clear_ratio(); + static const int kRatioFieldNumber = 4; + float ratio(int index) const; + void set_ratio(int index, float value); + void add_ratio(float value); + const ::google::protobuf::RepeatedField< float >& + ratio() const; + ::google::protobuf::RepeatedField< float >* + mutable_ratio(); + + // repeated float scale = 5; + int scale_size() const; + void clear_scale(); + static const int kScaleFieldNumber = 5; + float scale(int index) const; + void set_scale(int index, float value); + void add_scale(float value); + const ::google::protobuf::RepeatedField< float >& + scale() const; + ::google::protobuf::RepeatedField< float >* + mutable_scale(); + + // optional uint32 pre_nms_topn = 6 [default = 6000]; + bool has_pre_nms_topn() const; + void clear_pre_nms_topn(); + static const int kPreNmsTopnFieldNumber = 6; + ::google::protobuf::uint32 pre_nms_topn() const; + void set_pre_nms_topn(::google::protobuf::uint32 value); + + // optional uint32 post_nms_topn = 7 [default = 300]; + bool has_post_nms_topn() const; + void clear_post_nms_topn(); + static const int kPostNmsTopnFieldNumber = 7; + ::google::protobuf::uint32 post_nms_topn() const; + void set_post_nms_topn(::google::protobuf::uint32 value); + + // optional float nms_thresh = 8 [default = 0.7]; + bool has_nms_thresh() const; + void clear_nms_thresh(); + static const int kNmsThreshFieldNumber = 8; + float nms_thresh() const; + void set_nms_thresh(float value); + + // @@protoc_insertion_point(class_scope:opencv_caffe.ProposalParameter) + private: + inline void set_has_feat_stride(); + inline void clear_has_feat_stride(); + inline void set_has_base_size(); + inline void clear_has_base_size(); + inline void set_has_min_size(); + inline void clear_has_min_size(); + inline void set_has_pre_nms_topn(); + inline void clear_has_pre_nms_topn(); + inline void set_has_post_nms_topn(); + inline void clear_has_post_nms_topn(); + inline void set_has_nms_thresh(); + inline void clear_has_nms_thresh(); + + ::google::protobuf::internal::InternalMetadataWithArena _internal_metadata_; + ::google::protobuf::internal::HasBits<1> _has_bits_; + mutable int _cached_size_; + ::google::protobuf::RepeatedField< float > ratio_; + ::google::protobuf::RepeatedField< float > scale_; + ::google::protobuf::uint32 feat_stride_; + ::google::protobuf::uint32 base_size_; + ::google::protobuf::uint32 min_size_; + ::google::protobuf::uint32 pre_nms_topn_; + ::google::protobuf::uint32 post_nms_topn_; + float nms_thresh_; + friend void protobuf_InitDefaults_opencv_2dcaffe_2eproto_impl(); + friend void protobuf_AddDesc_opencv_2dcaffe_2eproto_impl(); + friend void protobuf_AssignDesc_opencv_2dcaffe_2eproto(); + friend void protobuf_ShutdownFile_opencv_2dcaffe_2eproto(); + + void InitAsDefaultInstance(); +}; +extern ::google::protobuf::internal::ExplicitlyConstructed ProposalParameter_default_instance_; + // =================================================================== @@ -18921,15 +19118,60 @@ inline void LayerParameter::set_allocated_prior_box_param(::opencv_caffe::PriorB // @@protoc_insertion_point(field_set_allocated:opencv_caffe.LayerParameter.prior_box_param) } +// optional .opencv_caffe.ProposalParameter proposal_param = 201; +inline bool LayerParameter::has_proposal_param() const { + return (_has_bits_[1] & 0x00010000u) != 0; +} +inline void LayerParameter::set_has_proposal_param() { + _has_bits_[1] |= 0x00010000u; +} +inline void LayerParameter::clear_has_proposal_param() { + _has_bits_[1] &= ~0x00010000u; +} +inline void LayerParameter::clear_proposal_param() { + if (proposal_param_ != NULL) proposal_param_->::opencv_caffe::ProposalParameter::Clear(); + clear_has_proposal_param(); +} +inline const ::opencv_caffe::ProposalParameter& LayerParameter::proposal_param() const { + // @@protoc_insertion_point(field_get:opencv_caffe.LayerParameter.proposal_param) + return proposal_param_ != NULL ? *proposal_param_ + : *::opencv_caffe::ProposalParameter::internal_default_instance(); +} +inline ::opencv_caffe::ProposalParameter* LayerParameter::mutable_proposal_param() { + set_has_proposal_param(); + if (proposal_param_ == NULL) { + proposal_param_ = new ::opencv_caffe::ProposalParameter; + } + // @@protoc_insertion_point(field_mutable:opencv_caffe.LayerParameter.proposal_param) + return proposal_param_; +} +inline ::opencv_caffe::ProposalParameter* LayerParameter::release_proposal_param() { + // @@protoc_insertion_point(field_release:opencv_caffe.LayerParameter.proposal_param) + clear_has_proposal_param(); + ::opencv_caffe::ProposalParameter* temp = proposal_param_; + proposal_param_ = NULL; + return temp; +} +inline void LayerParameter::set_allocated_proposal_param(::opencv_caffe::ProposalParameter* proposal_param) { + delete proposal_param_; + proposal_param_ = proposal_param; + if (proposal_param) { + set_has_proposal_param(); + } else { + clear_has_proposal_param(); + } + // @@protoc_insertion_point(field_set_allocated:opencv_caffe.LayerParameter.proposal_param) +} + // optional .opencv_caffe.PythonParameter python_param = 130; inline bool LayerParameter::has_python_param() const { - return (_has_bits_[1] & 0x00010000u) != 0; + return (_has_bits_[1] & 0x00020000u) != 0; } inline void LayerParameter::set_has_python_param() { - _has_bits_[1] |= 0x00010000u; + _has_bits_[1] |= 0x00020000u; } inline void LayerParameter::clear_has_python_param() { - _has_bits_[1] &= ~0x00010000u; + _has_bits_[1] &= ~0x00020000u; } inline void LayerParameter::clear_python_param() { if (python_param_ != NULL) python_param_->::opencv_caffe::PythonParameter::Clear(); @@ -18968,13 +19210,13 @@ inline void LayerParameter::set_allocated_python_param(::opencv_caffe::PythonPar // optional .opencv_caffe.RecurrentParameter recurrent_param = 146; inline bool LayerParameter::has_recurrent_param() const { - return (_has_bits_[1] & 0x00020000u) != 0; + return (_has_bits_[1] & 0x00040000u) != 0; } inline void LayerParameter::set_has_recurrent_param() { - _has_bits_[1] |= 0x00020000u; + _has_bits_[1] |= 0x00040000u; } inline void LayerParameter::clear_has_recurrent_param() { - _has_bits_[1] &= ~0x00020000u; + _has_bits_[1] &= ~0x00040000u; } inline void LayerParameter::clear_recurrent_param() { if (recurrent_param_ != NULL) recurrent_param_->::opencv_caffe::RecurrentParameter::Clear(); @@ -19013,13 +19255,13 @@ inline void LayerParameter::set_allocated_recurrent_param(::opencv_caffe::Recurr // optional .opencv_caffe.ReductionParameter reduction_param = 136; inline bool LayerParameter::has_reduction_param() const { - return (_has_bits_[1] & 0x00040000u) != 0; + return (_has_bits_[1] & 0x00080000u) != 0; } inline void LayerParameter::set_has_reduction_param() { - _has_bits_[1] |= 0x00040000u; + _has_bits_[1] |= 0x00080000u; } inline void LayerParameter::clear_has_reduction_param() { - _has_bits_[1] &= ~0x00040000u; + _has_bits_[1] &= ~0x00080000u; } inline void LayerParameter::clear_reduction_param() { if (reduction_param_ != NULL) reduction_param_->::opencv_caffe::ReductionParameter::Clear(); @@ -19058,13 +19300,13 @@ inline void LayerParameter::set_allocated_reduction_param(::opencv_caffe::Reduct // optional .opencv_caffe.ReLUParameter relu_param = 123; inline bool LayerParameter::has_relu_param() const { - return (_has_bits_[1] & 0x00080000u) != 0; + return (_has_bits_[1] & 0x00100000u) != 0; } inline void LayerParameter::set_has_relu_param() { - _has_bits_[1] |= 0x00080000u; + _has_bits_[1] |= 0x00100000u; } inline void LayerParameter::clear_has_relu_param() { - _has_bits_[1] &= ~0x00080000u; + _has_bits_[1] &= ~0x00100000u; } inline void LayerParameter::clear_relu_param() { if (relu_param_ != NULL) relu_param_->::opencv_caffe::ReLUParameter::Clear(); @@ -19103,13 +19345,13 @@ inline void LayerParameter::set_allocated_relu_param(::opencv_caffe::ReLUParamet // optional .opencv_caffe.ReshapeParameter reshape_param = 133; inline bool LayerParameter::has_reshape_param() const { - return (_has_bits_[1] & 0x00100000u) != 0; + return (_has_bits_[1] & 0x00200000u) != 0; } inline void LayerParameter::set_has_reshape_param() { - _has_bits_[1] |= 0x00100000u; + _has_bits_[1] |= 0x00200000u; } inline void LayerParameter::clear_has_reshape_param() { - _has_bits_[1] &= ~0x00100000u; + _has_bits_[1] &= ~0x00200000u; } inline void LayerParameter::clear_reshape_param() { if (reshape_param_ != NULL) reshape_param_->::opencv_caffe::ReshapeParameter::Clear(); @@ -19148,13 +19390,13 @@ inline void LayerParameter::set_allocated_reshape_param(::opencv_caffe::ReshapeP // optional .opencv_caffe.ROIPoolingParameter roi_pooling_param = 8266711; inline bool LayerParameter::has_roi_pooling_param() const { - return (_has_bits_[1] & 0x00200000u) != 0; + return (_has_bits_[1] & 0x00400000u) != 0; } inline void LayerParameter::set_has_roi_pooling_param() { - _has_bits_[1] |= 0x00200000u; + _has_bits_[1] |= 0x00400000u; } inline void LayerParameter::clear_has_roi_pooling_param() { - _has_bits_[1] &= ~0x00200000u; + _has_bits_[1] &= ~0x00400000u; } inline void LayerParameter::clear_roi_pooling_param() { if (roi_pooling_param_ != NULL) roi_pooling_param_->::opencv_caffe::ROIPoolingParameter::Clear(); @@ -19193,13 +19435,13 @@ inline void LayerParameter::set_allocated_roi_pooling_param(::opencv_caffe::ROIP // optional .opencv_caffe.ScaleParameter scale_param = 142; inline bool LayerParameter::has_scale_param() const { - return (_has_bits_[1] & 0x00400000u) != 0; + return (_has_bits_[1] & 0x00800000u) != 0; } inline void LayerParameter::set_has_scale_param() { - _has_bits_[1] |= 0x00400000u; + _has_bits_[1] |= 0x00800000u; } inline void LayerParameter::clear_has_scale_param() { - _has_bits_[1] &= ~0x00400000u; + _has_bits_[1] &= ~0x00800000u; } inline void LayerParameter::clear_scale_param() { if (scale_param_ != NULL) scale_param_->::opencv_caffe::ScaleParameter::Clear(); @@ -19238,13 +19480,13 @@ inline void LayerParameter::set_allocated_scale_param(::opencv_caffe::ScaleParam // optional .opencv_caffe.SigmoidParameter sigmoid_param = 124; inline bool LayerParameter::has_sigmoid_param() const { - return (_has_bits_[1] & 0x00800000u) != 0; + return (_has_bits_[1] & 0x01000000u) != 0; } inline void LayerParameter::set_has_sigmoid_param() { - _has_bits_[1] |= 0x00800000u; + _has_bits_[1] |= 0x01000000u; } inline void LayerParameter::clear_has_sigmoid_param() { - _has_bits_[1] &= ~0x00800000u; + _has_bits_[1] &= ~0x01000000u; } inline void LayerParameter::clear_sigmoid_param() { if (sigmoid_param_ != NULL) sigmoid_param_->::opencv_caffe::SigmoidParameter::Clear(); @@ -19283,13 +19525,13 @@ inline void LayerParameter::set_allocated_sigmoid_param(::opencv_caffe::SigmoidP // optional .opencv_caffe.SoftmaxParameter softmax_param = 125; inline bool LayerParameter::has_softmax_param() const { - return (_has_bits_[1] & 0x01000000u) != 0; + return (_has_bits_[1] & 0x02000000u) != 0; } inline void LayerParameter::set_has_softmax_param() { - _has_bits_[1] |= 0x01000000u; + _has_bits_[1] |= 0x02000000u; } inline void LayerParameter::clear_has_softmax_param() { - _has_bits_[1] &= ~0x01000000u; + _has_bits_[1] &= ~0x02000000u; } inline void LayerParameter::clear_softmax_param() { if (softmax_param_ != NULL) softmax_param_->::opencv_caffe::SoftmaxParameter::Clear(); @@ -19328,13 +19570,13 @@ inline void LayerParameter::set_allocated_softmax_param(::opencv_caffe::SoftmaxP // optional .opencv_caffe.SPPParameter spp_param = 132; inline bool LayerParameter::has_spp_param() const { - return (_has_bits_[1] & 0x02000000u) != 0; + return (_has_bits_[1] & 0x04000000u) != 0; } inline void LayerParameter::set_has_spp_param() { - _has_bits_[1] |= 0x02000000u; + _has_bits_[1] |= 0x04000000u; } inline void LayerParameter::clear_has_spp_param() { - _has_bits_[1] &= ~0x02000000u; + _has_bits_[1] &= ~0x04000000u; } inline void LayerParameter::clear_spp_param() { if (spp_param_ != NULL) spp_param_->::opencv_caffe::SPPParameter::Clear(); @@ -19373,13 +19615,13 @@ inline void LayerParameter::set_allocated_spp_param(::opencv_caffe::SPPParameter // optional .opencv_caffe.SliceParameter slice_param = 126; inline bool LayerParameter::has_slice_param() const { - return (_has_bits_[1] & 0x04000000u) != 0; + return (_has_bits_[1] & 0x08000000u) != 0; } inline void LayerParameter::set_has_slice_param() { - _has_bits_[1] |= 0x04000000u; + _has_bits_[1] |= 0x08000000u; } inline void LayerParameter::clear_has_slice_param() { - _has_bits_[1] &= ~0x04000000u; + _has_bits_[1] &= ~0x08000000u; } inline void LayerParameter::clear_slice_param() { if (slice_param_ != NULL) slice_param_->::opencv_caffe::SliceParameter::Clear(); @@ -19418,13 +19660,13 @@ inline void LayerParameter::set_allocated_slice_param(::opencv_caffe::SliceParam // optional .opencv_caffe.TanHParameter tanh_param = 127; inline bool LayerParameter::has_tanh_param() const { - return (_has_bits_[1] & 0x08000000u) != 0; + return (_has_bits_[1] & 0x10000000u) != 0; } inline void LayerParameter::set_has_tanh_param() { - _has_bits_[1] |= 0x08000000u; + _has_bits_[1] |= 0x10000000u; } inline void LayerParameter::clear_has_tanh_param() { - _has_bits_[1] &= ~0x08000000u; + _has_bits_[1] &= ~0x10000000u; } inline void LayerParameter::clear_tanh_param() { if (tanh_param_ != NULL) tanh_param_->::opencv_caffe::TanHParameter::Clear(); @@ -19463,13 +19705,13 @@ inline void LayerParameter::set_allocated_tanh_param(::opencv_caffe::TanHParamet // optional .opencv_caffe.ThresholdParameter threshold_param = 128; inline bool LayerParameter::has_threshold_param() const { - return (_has_bits_[1] & 0x10000000u) != 0; + return (_has_bits_[1] & 0x20000000u) != 0; } inline void LayerParameter::set_has_threshold_param() { - _has_bits_[1] |= 0x10000000u; + _has_bits_[1] |= 0x20000000u; } inline void LayerParameter::clear_has_threshold_param() { - _has_bits_[1] &= ~0x10000000u; + _has_bits_[1] &= ~0x20000000u; } inline void LayerParameter::clear_threshold_param() { if (threshold_param_ != NULL) threshold_param_->::opencv_caffe::ThresholdParameter::Clear(); @@ -19508,13 +19750,13 @@ inline void LayerParameter::set_allocated_threshold_param(::opencv_caffe::Thresh // optional .opencv_caffe.TileParameter tile_param = 138; inline bool LayerParameter::has_tile_param() const { - return (_has_bits_[1] & 0x20000000u) != 0; + return (_has_bits_[1] & 0x40000000u) != 0; } inline void LayerParameter::set_has_tile_param() { - _has_bits_[1] |= 0x20000000u; + _has_bits_[1] |= 0x40000000u; } inline void LayerParameter::clear_has_tile_param() { - _has_bits_[1] &= ~0x20000000u; + _has_bits_[1] &= ~0x40000000u; } inline void LayerParameter::clear_tile_param() { if (tile_param_ != NULL) tile_param_->::opencv_caffe::TileParameter::Clear(); @@ -19553,13 +19795,13 @@ inline void LayerParameter::set_allocated_tile_param(::opencv_caffe::TileParamet // optional .opencv_caffe.WindowDataParameter window_data_param = 129; inline bool LayerParameter::has_window_data_param() const { - return (_has_bits_[1] & 0x40000000u) != 0; + return (_has_bits_[1] & 0x80000000u) != 0; } inline void LayerParameter::set_has_window_data_param() { - _has_bits_[1] |= 0x40000000u; + _has_bits_[1] |= 0x80000000u; } inline void LayerParameter::clear_has_window_data_param() { - _has_bits_[1] &= ~0x40000000u; + _has_bits_[1] &= ~0x80000000u; } inline void LayerParameter::clear_window_data_param() { if (window_data_param_ != NULL) window_data_param_->::opencv_caffe::WindowDataParameter::Clear(); @@ -21620,6 +21862,30 @@ inline void DropoutParameter::set_dropout_ratio(float value) { // @@protoc_insertion_point(field_set:opencv_caffe.DropoutParameter.dropout_ratio) } +// optional bool scale_train = 2 [default = true]; +inline bool DropoutParameter::has_scale_train() const { + return (_has_bits_[0] & 0x00000002u) != 0; +} +inline void DropoutParameter::set_has_scale_train() { + _has_bits_[0] |= 0x00000002u; +} +inline void DropoutParameter::clear_has_scale_train() { + _has_bits_[0] &= ~0x00000002u; +} +inline void DropoutParameter::clear_scale_train() { + scale_train_ = true; + clear_has_scale_train(); +} +inline bool DropoutParameter::scale_train() const { + // @@protoc_insertion_point(field_get:opencv_caffe.DropoutParameter.scale_train) + return scale_train_; +} +inline void DropoutParameter::set_scale_train(bool value) { + set_has_scale_train(); + scale_train_ = value; + // @@protoc_insertion_point(field_set:opencv_caffe.DropoutParameter.scale_train) +} + inline const DropoutParameter* DropoutParameter::internal_default_instance() { return &DropoutParameter_default_instance_.get(); } @@ -28915,6 +29181,217 @@ inline void ROIPoolingParameter::set_spatial_scale(float value) { inline const ROIPoolingParameter* ROIPoolingParameter::internal_default_instance() { return &ROIPoolingParameter_default_instance_.get(); } +// ------------------------------------------------------------------- + +// ProposalParameter + +// optional uint32 feat_stride = 1 [default = 16]; +inline bool ProposalParameter::has_feat_stride() const { + return (_has_bits_[0] & 0x00000001u) != 0; +} +inline void ProposalParameter::set_has_feat_stride() { + _has_bits_[0] |= 0x00000001u; +} +inline void ProposalParameter::clear_has_feat_stride() { + _has_bits_[0] &= ~0x00000001u; +} +inline void ProposalParameter::clear_feat_stride() { + feat_stride_ = 16u; + clear_has_feat_stride(); +} +inline ::google::protobuf::uint32 ProposalParameter::feat_stride() const { + // @@protoc_insertion_point(field_get:opencv_caffe.ProposalParameter.feat_stride) + return feat_stride_; +} +inline void ProposalParameter::set_feat_stride(::google::protobuf::uint32 value) { + set_has_feat_stride(); + feat_stride_ = value; + // @@protoc_insertion_point(field_set:opencv_caffe.ProposalParameter.feat_stride) +} + +// optional uint32 base_size = 2 [default = 16]; +inline bool ProposalParameter::has_base_size() const { + return (_has_bits_[0] & 0x00000002u) != 0; +} +inline void ProposalParameter::set_has_base_size() { + _has_bits_[0] |= 0x00000002u; +} +inline void ProposalParameter::clear_has_base_size() { + _has_bits_[0] &= ~0x00000002u; +} +inline void ProposalParameter::clear_base_size() { + base_size_ = 16u; + clear_has_base_size(); +} +inline ::google::protobuf::uint32 ProposalParameter::base_size() const { + // @@protoc_insertion_point(field_get:opencv_caffe.ProposalParameter.base_size) + return base_size_; +} +inline void ProposalParameter::set_base_size(::google::protobuf::uint32 value) { + set_has_base_size(); + base_size_ = value; + // @@protoc_insertion_point(field_set:opencv_caffe.ProposalParameter.base_size) +} + +// optional uint32 min_size = 3 [default = 16]; +inline bool ProposalParameter::has_min_size() const { + return (_has_bits_[0] & 0x00000004u) != 0; +} +inline void ProposalParameter::set_has_min_size() { + _has_bits_[0] |= 0x00000004u; +} +inline void ProposalParameter::clear_has_min_size() { + _has_bits_[0] &= ~0x00000004u; +} +inline void ProposalParameter::clear_min_size() { + min_size_ = 16u; + clear_has_min_size(); +} +inline ::google::protobuf::uint32 ProposalParameter::min_size() const { + // @@protoc_insertion_point(field_get:opencv_caffe.ProposalParameter.min_size) + return min_size_; +} +inline void ProposalParameter::set_min_size(::google::protobuf::uint32 value) { + set_has_min_size(); + min_size_ = value; + // @@protoc_insertion_point(field_set:opencv_caffe.ProposalParameter.min_size) +} + +// repeated float ratio = 4; +inline int ProposalParameter::ratio_size() const { + return ratio_.size(); +} +inline void ProposalParameter::clear_ratio() { + ratio_.Clear(); +} +inline float ProposalParameter::ratio(int index) const { + // @@protoc_insertion_point(field_get:opencv_caffe.ProposalParameter.ratio) + return ratio_.Get(index); +} +inline void ProposalParameter::set_ratio(int index, float value) { + ratio_.Set(index, value); + // @@protoc_insertion_point(field_set:opencv_caffe.ProposalParameter.ratio) +} +inline void ProposalParameter::add_ratio(float value) { + ratio_.Add(value); + // @@protoc_insertion_point(field_add:opencv_caffe.ProposalParameter.ratio) +} +inline const ::google::protobuf::RepeatedField< float >& +ProposalParameter::ratio() const { + // @@protoc_insertion_point(field_list:opencv_caffe.ProposalParameter.ratio) + return ratio_; +} +inline ::google::protobuf::RepeatedField< float >* +ProposalParameter::mutable_ratio() { + // @@protoc_insertion_point(field_mutable_list:opencv_caffe.ProposalParameter.ratio) + return &ratio_; +} + +// repeated float scale = 5; +inline int ProposalParameter::scale_size() const { + return scale_.size(); +} +inline void ProposalParameter::clear_scale() { + scale_.Clear(); +} +inline float ProposalParameter::scale(int index) const { + // @@protoc_insertion_point(field_get:opencv_caffe.ProposalParameter.scale) + return scale_.Get(index); +} +inline void ProposalParameter::set_scale(int index, float value) { + scale_.Set(index, value); + // @@protoc_insertion_point(field_set:opencv_caffe.ProposalParameter.scale) +} +inline void ProposalParameter::add_scale(float value) { + scale_.Add(value); + // @@protoc_insertion_point(field_add:opencv_caffe.ProposalParameter.scale) +} +inline const ::google::protobuf::RepeatedField< float >& +ProposalParameter::scale() const { + // @@protoc_insertion_point(field_list:opencv_caffe.ProposalParameter.scale) + return scale_; +} +inline ::google::protobuf::RepeatedField< float >* +ProposalParameter::mutable_scale() { + // @@protoc_insertion_point(field_mutable_list:opencv_caffe.ProposalParameter.scale) + return &scale_; +} + +// optional uint32 pre_nms_topn = 6 [default = 6000]; +inline bool ProposalParameter::has_pre_nms_topn() const { + return (_has_bits_[0] & 0x00000020u) != 0; +} +inline void ProposalParameter::set_has_pre_nms_topn() { + _has_bits_[0] |= 0x00000020u; +} +inline void ProposalParameter::clear_has_pre_nms_topn() { + _has_bits_[0] &= ~0x00000020u; +} +inline void ProposalParameter::clear_pre_nms_topn() { + pre_nms_topn_ = 6000u; + clear_has_pre_nms_topn(); +} +inline ::google::protobuf::uint32 ProposalParameter::pre_nms_topn() const { + // @@protoc_insertion_point(field_get:opencv_caffe.ProposalParameter.pre_nms_topn) + return pre_nms_topn_; +} +inline void ProposalParameter::set_pre_nms_topn(::google::protobuf::uint32 value) { + set_has_pre_nms_topn(); + pre_nms_topn_ = value; + // @@protoc_insertion_point(field_set:opencv_caffe.ProposalParameter.pre_nms_topn) +} + +// optional uint32 post_nms_topn = 7 [default = 300]; +inline bool ProposalParameter::has_post_nms_topn() const { + return (_has_bits_[0] & 0x00000040u) != 0; +} +inline void ProposalParameter::set_has_post_nms_topn() { + _has_bits_[0] |= 0x00000040u; +} +inline void ProposalParameter::clear_has_post_nms_topn() { + _has_bits_[0] &= ~0x00000040u; +} +inline void ProposalParameter::clear_post_nms_topn() { + post_nms_topn_ = 300u; + clear_has_post_nms_topn(); +} +inline ::google::protobuf::uint32 ProposalParameter::post_nms_topn() const { + // @@protoc_insertion_point(field_get:opencv_caffe.ProposalParameter.post_nms_topn) + return post_nms_topn_; +} +inline void ProposalParameter::set_post_nms_topn(::google::protobuf::uint32 value) { + set_has_post_nms_topn(); + post_nms_topn_ = value; + // @@protoc_insertion_point(field_set:opencv_caffe.ProposalParameter.post_nms_topn) +} + +// optional float nms_thresh = 8 [default = 0.7]; +inline bool ProposalParameter::has_nms_thresh() const { + return (_has_bits_[0] & 0x00000080u) != 0; +} +inline void ProposalParameter::set_has_nms_thresh() { + _has_bits_[0] |= 0x00000080u; +} +inline void ProposalParameter::clear_has_nms_thresh() { + _has_bits_[0] &= ~0x00000080u; +} +inline void ProposalParameter::clear_nms_thresh() { + nms_thresh_ = 0.7f; + clear_has_nms_thresh(); +} +inline float ProposalParameter::nms_thresh() const { + // @@protoc_insertion_point(field_get:opencv_caffe.ProposalParameter.nms_thresh) + return nms_thresh_; +} +inline void ProposalParameter::set_nms_thresh(float value) { + set_has_nms_thresh(); + nms_thresh_ = value; + // @@protoc_insertion_point(field_set:opencv_caffe.ProposalParameter.nms_thresh) +} + +inline const ProposalParameter* ProposalParameter::internal_default_instance() { + return &ProposalParameter_default_instance_.get(); +} #endif // !PROTOBUF_INLINE_NOT_IN_HEADERS // ------------------------------------------------------------------- @@ -29052,6 +29529,8 @@ inline const ROIPoolingParameter* ROIPoolingParameter::internal_default_instance // ------------------------------------------------------------------- +// ------------------------------------------------------------------- + // @@protoc_insertion_point(namespace_scope) diff --git a/modules/dnn/src/caffe/opencv-caffe.proto b/modules/dnn/src/caffe/opencv-caffe.proto index 841f24f..8fde102 100644 --- a/modules/dnn/src/caffe/opencv-caffe.proto +++ b/modules/dnn/src/caffe/opencv-caffe.proto @@ -547,6 +547,7 @@ message LayerParameter { optional PowerParameter power_param = 122; optional PReLUParameter prelu_param = 131; optional PriorBoxParameter prior_box_param = 150; + optional ProposalParameter proposal_param = 201; optional PythonParameter python_param = 130; optional RecurrentParameter recurrent_param = 146; optional ReductionParameter reduction_param = 136; @@ -854,6 +855,9 @@ message SaveOutputParameter { message DropoutParameter { optional float dropout_ratio = 1 [default = 0.5]; // dropout ratio + // Faster-RCNN framework's parameter. + // source: https://github.com/rbgirshick/caffe-fast-rcnn/tree/faster-rcnn + optional bool scale_train = 2 [default = true]; // scale train or test phase } // DummyDataLayer fills any number of arbitrarily shaped blobs with random @@ -1618,3 +1622,14 @@ message ROIPoolingParameter { // input scale to the scale used when pooling optional float spatial_scale = 3 [default = 1]; } + +message ProposalParameter { + optional uint32 feat_stride = 1 [default = 16]; + optional uint32 base_size = 2 [default = 16]; + optional uint32 min_size = 3 [default = 16]; + repeated float ratio = 4; + repeated float scale = 5; + optional uint32 pre_nms_topn = 6 [default = 6000]; + optional uint32 post_nms_topn = 7 [default = 300]; + optional float nms_thresh = 8 [default = 0.7]; +} diff --git a/modules/dnn/src/init.cpp b/modules/dnn/src/init.cpp index 3e78435..ba1a10d 100644 --- a/modules/dnn/src/init.cpp +++ b/modules/dnn/src/init.cpp @@ -122,6 +122,7 @@ void initializeLayerFactory() CV_DNN_REGISTER_LAYER_CLASS(Normalize, NormalizeBBoxLayer); CV_DNN_REGISTER_LAYER_CLASS(Shift, ShiftLayer); CV_DNN_REGISTER_LAYER_CLASS(Padding, PaddingLayer); + CV_DNN_REGISTER_LAYER_CLASS(Proposal, ProposalLayer); CV_DNN_REGISTER_LAYER_CLASS(Scale, ScaleLayer); CV_DNN_REGISTER_LAYER_CLASS(LSTM, LSTMLayer); diff --git a/modules/dnn/src/layers/blank_layer.cpp b/modules/dnn/src/layers/blank_layer.cpp index 5e6ca22..af2bfeb 100644 --- a/modules/dnn/src/layers/blank_layer.cpp +++ b/modules/dnn/src/layers/blank_layer.cpp @@ -92,9 +92,25 @@ public: } }; -Ptr BlankLayer::create(const LayerParams& params) +Ptr BlankLayer::create(const LayerParams& params) { - return Ptr(new BlankLayerImpl(params)); + // In case of Caffe's Dropout layer from Faster-RCNN framework, + // https://github.com/rbgirshick/caffe-fast-rcnn/tree/faster-rcnn + // return Power layer. + if (!params.get("scale_train", true)) + { + float scale = 1 - params.get("dropout_ratio", 0.5f); + CV_Assert(scale > 0); + + LayerParams powerParams; + powerParams.name = params.name; + powerParams.type = "Power"; + powerParams.set("scale", scale); + + return PowerLayer::create(powerParams); + } + else + return Ptr(new BlankLayerImpl(params)); } } diff --git a/modules/dnn/src/layers/detection_output_layer.cpp b/modules/dnn/src/layers/detection_output_layer.cpp index 5f75eff..e1ca59b 100644 --- a/modules/dnn/src/layers/detection_output_layer.cpp +++ b/modules/dnn/src/layers/detection_output_layer.cpp @@ -85,6 +85,8 @@ static inline bool SortScorePairDescend(const std::pair& pair1, static inline float caffe_box_overlap(const util::NormalizedBBox& a, const util::NormalizedBBox& b); +static inline float caffe_norm_box_overlap(const util::NormalizedBBox& a, const util::NormalizedBBox& b); + } // namespace class DetectionOutputLayerImpl : public DetectionOutputLayer @@ -106,6 +108,9 @@ public: int _topK; // Whenever predicted bounding boxes are respresented in YXHW instead of XYWH layout. bool _locPredTransposed; + // It's true whenever predicted bounding boxes and proposals are normalized to [0, 1]. + bool _bboxesNormalized; + bool _clip; enum { _numAxes = 4 }; static const std::string _layerName; @@ -172,6 +177,8 @@ public: _confidenceThreshold = getParameter(params, "confidence_threshold", 0, false, -FLT_MAX); _topK = getParameter(params, "top_k", 0, false, -1); _locPredTransposed = getParameter(params, "loc_pred_transposed", 0, false, false); + _bboxesNormalized = getParameter(params, "normalized_bbox", 0, false, true); + _clip = getParameter(params, "clip", 0, false, false); getCodeType(params); @@ -182,20 +189,12 @@ public: setParamsFrom(params); } - void checkInputs(const std::vector &inputs) - { - for (size_t i = 1; i < inputs.size(); i++) - { - CV_Assert(inputs[i]->size == inputs[0]->size); - } - } - bool getMemoryShapes(const std::vector &inputs, const int requiredOutputs, std::vector &outputs, std::vector &internals) const { - CV_Assert(inputs.size() > 0); + CV_Assert(inputs.size() >= 3); CV_Assert(inputs[0][0] == inputs[1][0]); int numPriors = inputs[2][2] / 4; @@ -398,12 +397,28 @@ public: // Retrieve all prior bboxes std::vector priorBBoxes; std::vector > priorVariances; - GetPriorBBoxes(priorData, numPriors, priorBBoxes, priorVariances); + GetPriorBBoxes(priorData, numPriors, _bboxesNormalized, priorBBoxes, priorVariances); // Decode all loc predictions to bboxes + util::NormalizedBBox clipBounds; + if (_clip) + { + CV_Assert(_bboxesNormalized || inputs.size() >= 4); + clipBounds.xmin = clipBounds.ymin = 0.0f; + if (_bboxesNormalized) + clipBounds.xmax = clipBounds.ymax = 1.0f; + else + { + // Input image sizes; + CV_Assert(inputs[3]->dims == 4); + clipBounds.xmax = inputs[3]->size[3] - 1; + clipBounds.ymax = inputs[3]->size[2] - 1; + } + } DecodeBBoxesAll(allLocationPredictions, priorBBoxes, priorVariances, num, _shareLocation, _numLocClasses, _backgroundLabelId, - _codeType, _varianceEncodedInTarget, false, allDecodedBBoxes); + _codeType, _varianceEncodedInTarget, _clip, clipBounds, + _bboxesNormalized, allDecodedBBoxes); } size_t numKept = 0; @@ -489,8 +504,12 @@ public: LabelBBox::const_iterator label_bboxes = decodeBBoxes.find(label); if (label_bboxes == decodeBBoxes.end()) CV_ErrorNoReturn_(cv::Error::StsError, ("Could not find location predictions for label %d", label)); - NMSFast_(label_bboxes->second, scores, _confidenceThreshold, _nmsThreshold, 1.0, _topK, - indices[c], util::caffe_box_overlap); + if (_bboxesNormalized) + NMSFast_(label_bboxes->second, scores, _confidenceThreshold, _nmsThreshold, 1.0, _topK, + indices[c], util::caffe_norm_box_overlap); + else + NMSFast_(label_bboxes->second, scores, _confidenceThreshold, _nmsThreshold, 1.0, _topK, + indices[c], util::caffe_box_overlap); numDetections += indices[c].size(); } if (_keepTopK > -1 && numDetections > (size_t)_keepTopK) @@ -539,8 +558,7 @@ public: // ************************************************************** // Compute bbox size - template - static float BBoxSize(const util::NormalizedBBox& bbox) + static float BBoxSize(const util::NormalizedBBox& bbox, bool normalized) { if (bbox.xmax < bbox.xmin || bbox.ymax < bbox.ymin) { @@ -575,7 +593,8 @@ public: static void DecodeBBox( const util::NormalizedBBox& prior_bbox, const std::vector& prior_variance, const cv::String& code_type, - const bool clip_bbox, const util::NormalizedBBox& bbox, + const bool clip_bbox, const util::NormalizedBBox& clip_bounds, + const bool normalized_bbox, const util::NormalizedBBox& bbox, util::NormalizedBBox& decode_bbox) { float bbox_xmin = variance_encoded_in_target ? bbox.xmin : prior_variance[0] * bbox.xmin; @@ -592,11 +611,16 @@ public: else if (code_type == "CENTER_SIZE") { float prior_width = prior_bbox.xmax - prior_bbox.xmin; - CV_Assert(prior_width > 0); float prior_height = prior_bbox.ymax - prior_bbox.ymin; + if (!normalized_bbox) + { + prior_width += 1.0f; + prior_height += 1.0f; + } + CV_Assert(prior_width > 0); CV_Assert(prior_height > 0); - float prior_center_x = (prior_bbox.xmin + prior_bbox.xmax) * .5; - float prior_center_y = (prior_bbox.ymin + prior_bbox.ymax) * .5; + float prior_center_x = prior_bbox.xmin + prior_width * .5; + float prior_center_y = prior_bbox.ymin + prior_height * .5; float decode_bbox_center_x, decode_bbox_center_y; float decode_bbox_width, decode_bbox_height; @@ -614,14 +638,14 @@ public: if (clip_bbox) { - // Clip the util::NormalizedBBox such that the range for each corner is [0, 1] - decode_bbox.xmin = std::max(std::min(decode_bbox.xmin, 1.f), 0.f); - decode_bbox.ymin = std::max(std::min(decode_bbox.ymin, 1.f), 0.f); - decode_bbox.xmax = std::max(std::min(decode_bbox.xmax, 1.f), 0.f); - decode_bbox.ymax = std::max(std::min(decode_bbox.ymax, 1.f), 0.f); + // Clip the util::NormalizedBBox. + decode_bbox.xmin = std::max(std::min(decode_bbox.xmin, clip_bounds.xmax), clip_bounds.xmin); + decode_bbox.ymin = std::max(std::min(decode_bbox.ymin, clip_bounds.ymax), clip_bounds.ymin); + decode_bbox.xmax = std::max(std::min(decode_bbox.xmax, clip_bounds.xmax), clip_bounds.xmin); + decode_bbox.ymax = std::max(std::min(decode_bbox.ymax, clip_bounds.ymax), clip_bounds.ymin); } decode_bbox.clear_size(); - decode_bbox.set_size(BBoxSize(decode_bbox)); + decode_bbox.set_size(BBoxSize(decode_bbox, normalized_bbox)); } // Decode a set of bboxes according to a set of prior bboxes @@ -629,7 +653,8 @@ public: const std::vector& prior_bboxes, const std::vector >& prior_variances, const cv::String& code_type, const bool variance_encoded_in_target, - const bool clip_bbox, const std::vector& bboxes, + const bool clip_bbox, const util::NormalizedBBox& clip_bounds, + const bool normalized_bbox, const std::vector& bboxes, std::vector& decode_bboxes) { CV_Assert(prior_bboxes.size() == prior_variances.size()); @@ -641,13 +666,15 @@ public: { for (int i = 0; i < num_bboxes; ++i) DecodeBBox(prior_bboxes[i], prior_variances[i], code_type, - clip_bbox, bboxes[i], decode_bboxes[i]); + clip_bbox, clip_bounds, normalized_bbox, + bboxes[i], decode_bboxes[i]); } else { for (int i = 0; i < num_bboxes; ++i) DecodeBBox(prior_bboxes[i], prior_variances[i], code_type, - clip_bbox, bboxes[i], decode_bboxes[i]); + clip_bbox, clip_bounds, normalized_bbox, + bboxes[i], decode_bboxes[i]); } } @@ -658,7 +685,8 @@ public: const int num, const bool share_location, const int num_loc_classes, const int background_label_id, const cv::String& code_type, const bool variance_encoded_in_target, - const bool clip, std::vector& all_decode_bboxes) + const bool clip, const util::NormalizedBBox& clip_bounds, + const bool normalized_bbox, std::vector& all_decode_bboxes) { CV_Assert(all_loc_preds.size() == num); all_decode_bboxes.clear(); @@ -677,8 +705,8 @@ public: if (label_loc_preds == loc_preds.end()) CV_ErrorNoReturn_(cv::Error::StsError, ("Could not find location predictions for label %d", label)); DecodeBBoxes(prior_bboxes, prior_variances, - code_type, variance_encoded_in_target, clip, - label_loc_preds->second, decode_bboxes[label]); + code_type, variance_encoded_in_target, clip, clip_bounds, + normalized_bbox, label_loc_preds->second, decode_bboxes[label]); } } } @@ -689,7 +717,7 @@ public: // prior_bboxes: stores all the prior bboxes in the format of util::NormalizedBBox. // prior_variances: stores all the variances needed by prior bboxes. static void GetPriorBBoxes(const float* priorData, const int& numPriors, - std::vector& priorBBoxes, + bool normalized_bbox, std::vector& priorBBoxes, std::vector >& priorVariances) { priorBBoxes.clear(); priorBBoxes.resize(numPriors); @@ -702,7 +730,7 @@ public: bbox.ymin = priorData[startIdx + 1]; bbox.xmax = priorData[startIdx + 2]; bbox.ymax = priorData[startIdx + 3]; - bbox.set_size(BBoxSize(bbox)); + bbox.set_size(BBoxSize(bbox, normalized_bbox)); } for (int i = 0; i < numPriors; ++i) @@ -805,36 +833,16 @@ public: const util::NormalizedBBox& bbox2) { util::NormalizedBBox intersect_bbox; - if (bbox2.xmin > bbox1.xmax || bbox2.xmax < bbox1.xmin || - bbox2.ymin > bbox1.ymax || bbox2.ymax < bbox1.ymin) - { - // Return [0, 0, 0, 0] if there is no intersection. - intersect_bbox.xmin = 0; - intersect_bbox.ymin = 0; - intersect_bbox.xmax = 0; - intersect_bbox.ymax = 0; - } - else - { - intersect_bbox.xmin = std::max(bbox1.xmin, bbox2.xmin); - intersect_bbox.ymin = std::max(bbox1.ymin, bbox2.ymin); - intersect_bbox.xmax = std::min(bbox1.xmax, bbox2.xmax); - intersect_bbox.ymax = std::min(bbox1.ymax, bbox2.ymax); - } + intersect_bbox.xmin = std::max(bbox1.xmin, bbox2.xmin); + intersect_bbox.ymin = std::max(bbox1.ymin, bbox2.ymin); + intersect_bbox.xmax = std::min(bbox1.xmax, bbox2.xmax); + intersect_bbox.ymax = std::min(bbox1.ymax, bbox2.ymax); - float intersect_width, intersect_height; - intersect_width = intersect_bbox.xmax - intersect_bbox.xmin; - intersect_height = intersect_bbox.ymax - intersect_bbox.ymin; - if (intersect_width > 0 && intersect_height > 0) + float intersect_size = BBoxSize(intersect_bbox, normalized); + if (intersect_size > 0) { - if (!normalized) - { - intersect_width++; - intersect_height++; - } - float intersect_size = intersect_width * intersect_height; - float bbox1_size = BBoxSize(bbox1); - float bbox2_size = BBoxSize(bbox2); + float bbox1_size = BBoxSize(bbox1, normalized); + float bbox2_size = BBoxSize(bbox2, normalized); return intersect_size / (bbox1_size + bbox2_size - intersect_size); } else @@ -846,6 +854,11 @@ public: float util::caffe_box_overlap(const util::NormalizedBBox& a, const util::NormalizedBBox& b) { + return DetectionOutputLayerImpl::JaccardOverlap(a, b); +} + +float util::caffe_norm_box_overlap(const util::NormalizedBBox& a, const util::NormalizedBBox& b) +{ return DetectionOutputLayerImpl::JaccardOverlap(a, b); } diff --git a/modules/dnn/src/layers/pooling_layer.cpp b/modules/dnn/src/layers/pooling_layer.cpp index 51a2ea2..0574458 100644 --- a/modules/dnn/src/layers/pooling_layer.cpp +++ b/modules/dnn/src/layers/pooling_layer.cpp @@ -88,6 +88,7 @@ public: else if (params.has("pooled_w") || params.has("pooled_h") || params.has("spatial_scale")) { type = ROI; + computeMaxIdx = false; } setParamsFrom(params); ceilMode = params.get("ceil_mode", true); @@ -294,24 +295,17 @@ public: int ystart, yend; const float *srcData; - int xstartROI = 0; - float roiRatio = 0; if (poolingType == ROI) { const float *roisData = rois->ptr(n); int ystartROI = scaleAndRoundRoi(roisData[2], spatialScale); int yendROI = scaleAndRoundRoi(roisData[4], spatialScale); int roiHeight = std::max(yendROI - ystartROI + 1, 1); - roiRatio = (float)roiHeight / height; + float roiRatio = (float)roiHeight / height; ystart = ystartROI + y0 * roiRatio; yend = ystartROI + std::ceil((y0 + 1) * roiRatio); - xstartROI = scaleAndRoundRoi(roisData[1], spatialScale); - int xendROI = scaleAndRoundRoi(roisData[3], spatialScale); - int roiWidth = std::max(xendROI - xstartROI + 1, 1); - roiRatio = (float)roiWidth / width; - CV_Assert(roisData[0] < src->size[0]); srcData = src->ptr(roisData[0], c); } @@ -331,22 +325,12 @@ public: ofs0 += delta; int x1 = x0 + delta; - if( poolingType == MAX || poolingType == ROI) + if( poolingType == MAX) for( ; x0 < x1; x0++ ) { - int xstart, xend; - if (poolingType == ROI) - { - xstart = xstartROI + x0 * roiRatio; - xend = xstartROI + std::ceil((x0 + 1) * roiRatio); - } - else - { - xstart = x0 * stride_w - pad_w; - xend = xstart + kernel_w; - } + int xstart = x0 * stride_w - pad_w; + int xend = min(xstart + kernel_w, inp_width); xstart = max(xstart, 0); - xend = min(xend, inp_width); if (xstart >= xend || ystart >= yend) { dstData[x0] = 0; @@ -493,7 +477,7 @@ public: } } } - else + else if (poolingType == AVE) { for( ; x0 < x1; x0++ ) { @@ -543,6 +527,37 @@ public: } } } + else // ROI + { + const float *roisData = rois->ptr(n); + int xstartROI = scaleAndRoundRoi(roisData[1], spatialScale); + int xendROI = scaleAndRoundRoi(roisData[3], spatialScale); + int roiWidth = std::max(xendROI - xstartROI + 1, 1); + float roiRatio = (float)roiWidth / width; + for( ; x0 < x1; x0++ ) + { + int xstart = xstartROI + x0 * roiRatio; + int xend = xstartROI + std::ceil((x0 + 1) * roiRatio); + xstart = max(xstart, 0); + xend = min(xend, inp_width); + if (xstart >= xend || ystart >= yend) + { + dstData[x0] = 0; + if (compMaxIdx && dstMaskData) + dstMaskData[x0] = -1; + continue; + } + float max_val = -FLT_MAX; + for (int y = ystart; y < yend; ++y) + for (int x = xstart; x < xend; ++x) + { + const int index = y * inp_width + x; + float val = srcData[index]; + max_val = std::max(max_val, val); + } + dstData[x0] = max_val; + } + } } } }; diff --git a/modules/dnn/src/layers/prior_box_layer.cpp b/modules/dnn/src/layers/prior_box_layer.cpp index 89f37da..5fc852a 100644 --- a/modules/dnn/src/layers/prior_box_layer.cpp +++ b/modules/dnn/src/layers/prior_box_layer.cpp @@ -183,6 +183,7 @@ public: _minSize = getParameter(params, "min_size", 0, false, 0); _flip = getParameter(params, "flip", 0, false, true); _clip = getParameter(params, "clip", 0, false, true); + _bboxesNormalized = getParameter(params, "normalized_bbox", 0, false, true); _scales.clear(); _aspectRatios.clear(); @@ -251,7 +252,7 @@ public: std::vector &outputs, std::vector &internals) const { - CV_Assert(inputs.size() == 2); + CV_Assert(!inputs.empty()); int layerHeight = inputs[0][2]; int layerWidth = inputs[0][3]; @@ -282,6 +283,8 @@ public: CV_TRACE_FUNCTION(); CV_TRACE_ARG_VALUE(name, "name", name.c_str()); + CV_Assert(inputs.size() == 2); + size_t real_numPriors = _numPriors / pow(2, _offsetsX.size() - 1); if (_scales.empty()) _scales.resize(real_numPriors, 1.0f); @@ -323,7 +326,8 @@ public: { float center_x = (w + _offsetsX[i]) * stepX; float center_y = (h + _offsetsY[i]) * stepY; - outputPtr = addPrior(center_x, center_y, _boxWidth, _boxHeight, _imageWidth, _imageHeight, outputPtr); + outputPtr = addPrior(center_x, center_y, _boxWidth, _boxHeight, _imageWidth, + _imageHeight, _bboxesNormalized, outputPtr); } if (_maxSize > 0) { @@ -333,7 +337,8 @@ public: { float center_x = (w + _offsetsX[i]) * stepX; float center_y = (h + _offsetsY[i]) * stepY; - outputPtr = addPrior(center_x, center_y, _boxWidth, _boxHeight, _imageWidth, _imageHeight, outputPtr); + outputPtr = addPrior(center_x, center_y, _boxWidth, _boxHeight, _imageWidth, + _imageHeight, _bboxesNormalized, outputPtr); } } @@ -349,7 +354,8 @@ public: { float center_x = (w + _offsetsX[i]) * stepX; float center_y = (h + _offsetsY[i]) * stepY; - outputPtr = addPrior(center_x, center_y, _boxWidth, _boxHeight, _imageWidth, _imageHeight, outputPtr); + outputPtr = addPrior(center_x, center_y, _boxWidth, _boxHeight, _imageWidth, + _imageHeight, _bboxesNormalized, outputPtr); } } @@ -363,7 +369,8 @@ public: { float center_x = (w + _offsetsX[j]) * stepX; float center_y = (h + _offsetsY[j]) * stepY; - outputPtr = addPrior(center_x, center_y, _boxWidth, _boxHeight, _imageWidth, _imageHeight, outputPtr); + outputPtr = addPrior(center_x, center_y, _boxWidth, _boxHeight, _imageWidth, + _imageHeight, _bboxesNormalized, outputPtr); } } } @@ -437,6 +444,7 @@ private: bool _flip; bool _clip; bool _explicitSizes; + bool _bboxesNormalized; size_t _numPriors; @@ -444,12 +452,22 @@ private: static const std::string _layerName; static float* addPrior(float center_x, float center_y, float width, float height, - float imgWidth, float imgHeight, float* dst) + float imgWidth, float imgHeight, bool normalized, float* dst) { - dst[0] = (center_x - width * 0.5f) / imgWidth; // xmin - dst[1] = (center_y - height * 0.5f) / imgHeight; // ymin - dst[2] = (center_x + width * 0.5f) / imgWidth; // xmax - dst[3] = (center_y + height * 0.5f) / imgHeight; // ymax + if (normalized) + { + dst[0] = (center_x - width * 0.5f) / imgWidth; // xmin + dst[1] = (center_y - height * 0.5f) / imgHeight; // ymin + dst[2] = (center_x + width * 0.5f) / imgWidth; // xmax + dst[3] = (center_y + height * 0.5f) / imgHeight; // ymax + } + else + { + dst[0] = center_x - width * 0.5f; // xmin + dst[1] = center_y - height * 0.5f; // ymin + dst[2] = center_x + width * 0.5f - 1.0f; // xmax + dst[3] = center_y + height * 0.5f - 1.0f; // ymax + } return dst + 4; } }; diff --git a/modules/dnn/src/layers/proposal_layer.cpp b/modules/dnn/src/layers/proposal_layer.cpp new file mode 100644 index 0000000..8da4c47 --- /dev/null +++ b/modules/dnn/src/layers/proposal_layer.cpp @@ -0,0 +1,245 @@ +// 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) 2017, Intel Corporation, all rights reserved. +// Third party copyrights are property of their respective owners. +#include "../precomp.hpp" +#include "layers_common.hpp" + +namespace cv { namespace dnn { + +class ProposalLayerImpl : public ProposalLayer +{ +public: + ProposalLayerImpl(const LayerParams& params) + { + setParamsFrom(params); + + uint32_t featStride = params.get("feat_stride", 16); + uint32_t baseSize = params.get("base_size", 16); + // uint32_t minSize = params.get("min_size", 16); + uint32_t keepTopBeforeNMS = params.get("pre_nms_topn", 6000); + keepTopAfterNMS = params.get("post_nms_topn", 300); + float nmsThreshold = params.get("nms_thresh", 0.7); + DictValue ratios = params.get("ratio"); + DictValue scales = params.get("scale"); + + { + LayerParams lp; + lp.set("step", featStride); + lp.set("flip", false); + lp.set("clip", false); + lp.set("normalized_bbox", false); + + // Unused values. + float variance[] = {0.1f, 0.1f, 0.2f, 0.2f}; + lp.set("variance", DictValue::arrayReal(&variance[0], 4)); + + // Compute widths and heights explicitly. + std::vector widths, heights; + widths.reserve(ratios.size() * scales.size()); + heights.reserve(ratios.size() * scales.size()); + for (int i = 0; i < ratios.size(); ++i) + { + float ratio = ratios.get(i); + for (int j = 0; j < scales.size(); ++j) + { + float scale = scales.get(j); + float width = std::floor(baseSize / sqrt(ratio) + 0.5f); + float height = std::floor(width * ratio + 0.5f); + widths.push_back(scale * width); + heights.push_back(scale * height); + } + } + lp.set("width", DictValue::arrayReal(&widths[0], widths.size())); + lp.set("height", DictValue::arrayReal(&heights[0], heights.size())); + + priorBoxLayer = PriorBoxLayer::create(lp); + } + { + int order[] = {0, 2, 3, 1}; + LayerParams lp; + lp.set("order", DictValue::arrayInt(&order[0], 4)); + + deltasPermute = PermuteLayer::create(lp); + scoresPermute = PermuteLayer::create(lp); + } + { + LayerParams lp; + lp.set("code_type", "CENTER_SIZE"); + lp.set("num_classes", 1); + lp.set("share_location", true); + lp.set("background_label_id", 1); // We won't pass background scores so set it out of range [0, num_classes) + lp.set("variance_encoded_in_target", true); + lp.set("keep_top_k", keepTopAfterNMS); + lp.set("top_k", keepTopBeforeNMS); + lp.set("nms_threshold", nmsThreshold); + lp.set("normalized_bbox", false); + lp.set("clip", true); + + detectionOutputLayer = DetectionOutputLayer::create(lp); + } + } + + bool getMemoryShapes(const std::vector &inputs, + const int requiredOutputs, + std::vector &outputs, + std::vector &internals) const + { + // We need to allocate the following blobs: + // - output priors from PriorBoxLayer + // - permuted priors + // - permuted scores + CV_Assert(inputs.size() == 3); + + const MatShape& scores = inputs[0]; + const MatShape& bboxDeltas = inputs[1]; + + std::vector layerInputs, layerOutputs, layerInternals; + + // Prior boxes layer. + layerInputs.assign(1, scores); + priorBoxLayer->getMemoryShapes(layerInputs, 1, layerOutputs, layerInternals); + CV_Assert(layerOutputs.size() == 1); + CV_Assert(layerInternals.empty()); + internals.push_back(layerOutputs[0]); + + // Scores permute layer. + CV_Assert(scores.size() == 4); + MatShape objectScores = scores; + CV_Assert((scores[1] & 1) == 0); // Number of channels is even. + objectScores[1] /= 2; + layerInputs.assign(1, objectScores); + scoresPermute->getMemoryShapes(layerInputs, 1, layerOutputs, layerInternals); + CV_Assert(layerOutputs.size() == 1); + CV_Assert(layerInternals.empty()); + internals.push_back(layerOutputs[0]); + + // BBox predictions permute layer. + layerInputs.assign(1, bboxDeltas); + deltasPermute->getMemoryShapes(layerInputs, 1, layerOutputs, layerInternals); + CV_Assert(layerOutputs.size() == 1); + CV_Assert(layerInternals.empty()); + internals.push_back(layerOutputs[0]); + + outputs.resize(1, shape(keepTopAfterNMS, 5)); + return false; + } + + void finalize(const std::vector &inputs, std::vector &outputs) + { + std::vector layerInputs; + std::vector layerOutputs; + + // Scores permute layer. + Mat scores = getObjectScores(*inputs[0]); + layerInputs.assign(1, &scores); + layerOutputs.assign(1, Mat(shape(scores.size[0], scores.size[2], + scores.size[3], scores.size[1]), CV_32FC1)); + scoresPermute->finalize(layerInputs, layerOutputs); + + // BBox predictions permute layer. + Mat* bboxDeltas = inputs[1]; + CV_Assert(bboxDeltas->dims == 4); + layerInputs.assign(1, bboxDeltas); + layerOutputs.assign(1, Mat(shape(bboxDeltas->size[0], bboxDeltas->size[2], + bboxDeltas->size[3], bboxDeltas->size[1]), CV_32FC1)); + deltasPermute->finalize(layerInputs, layerOutputs); + } + + void forward(InputArrayOfArrays inputs_arr, OutputArrayOfArrays outputs_arr, OutputArrayOfArrays internals_arr) + { + CV_TRACE_FUNCTION(); + CV_TRACE_ARG_VALUE(name, "name", name.c_str()); + + Layer::forward_fallback(inputs_arr, outputs_arr, internals_arr); + } + + void forward(std::vector &inputs, std::vector &outputs, std::vector &internals) + { + CV_TRACE_FUNCTION(); + CV_TRACE_ARG_VALUE(name, "name", name.c_str()); + + CV_Assert(inputs.size() == 3); + CV_Assert(internals.size() == 3); + const Mat& scores = *inputs[0]; + const Mat& bboxDeltas = *inputs[1]; + const Mat& imInfo = *inputs[2]; + Mat& priorBoxes = internals[0]; + Mat& permuttedScores = internals[1]; + Mat& permuttedDeltas = internals[2]; + + CV_Assert(imInfo.total() >= 2); + // We've chosen the smallest data type because we need just a shape from it. + fakeImageBlob.create(shape(1, 1, imInfo.at(0), imInfo.at(1)), CV_8UC1); + + // Generate prior boxes. + std::vector layerInputs(2), layerOutputs(1, priorBoxes); + layerInputs[0] = scores; + layerInputs[1] = fakeImageBlob; + priorBoxLayer->forward(layerInputs, layerOutputs, internals); + + // Permute scores. + layerInputs.assign(1, getObjectScores(scores)); + layerOutputs.assign(1, permuttedScores); + scoresPermute->forward(layerInputs, layerOutputs, internals); + + // Permute deltas. + layerInputs.assign(1, bboxDeltas); + layerOutputs.assign(1, permuttedDeltas); + deltasPermute->forward(layerInputs, layerOutputs, internals); + + // Sort predictions by scores and apply NMS. DetectionOutputLayer allocates + // output internally because of different number of objects after NMS. + layerInputs.resize(4); + layerInputs[0] = permuttedDeltas; + layerInputs[1] = permuttedScores; + layerInputs[2] = priorBoxes; + layerInputs[3] = fakeImageBlob; + + layerOutputs[0] = Mat(); + detectionOutputLayer->forward(layerInputs, layerOutputs, internals); + + // DetectionOutputLayer produces 1x1xNx7 output where N might be less or + // equal to keepTopAfterNMS. We fill the rest by zeros. + const int numDets = layerOutputs[0].total() / 7; + CV_Assert(numDets <= keepTopAfterNMS); + + Mat src = layerOutputs[0].reshape(1, numDets).colRange(3, 7); + Mat dst = outputs[0].rowRange(0, numDets); + src.copyTo(dst.colRange(1, 5)); + dst.col(0).setTo(0); // First column are batch ids. Keep it zeros too. + + if (numDets < keepTopAfterNMS) + outputs[0].rowRange(numDets, keepTopAfterNMS).setTo(0); + } + +private: + // A first half of channels are background scores. We need only a second one. + static Mat getObjectScores(const Mat& m) + { + CV_Assert(m.dims == 4); + CV_Assert(m.size[0] == 1); + int channels = m.size[1]; + CV_Assert((channels & 1) == 0); + return slice(m, Range::all(), Range(channels / 2, channels)); + } + + Ptr priorBoxLayer; + Ptr detectionOutputLayer; + + Ptr deltasPermute; + Ptr scoresPermute; + uint32_t keepTopAfterNMS; + Mat fakeImageBlob; +}; + + +Ptr ProposalLayer::create(const LayerParams& params) +{ + return Ptr(new ProposalLayerImpl(params)); +} + +} // namespace dnn +} // namespace cv diff --git a/modules/dnn/test/test_layers.cpp b/modules/dnn/test/test_layers.cpp index 029e241..670ccc2 100644 --- a/modules/dnn/test/test_layers.cpp +++ b/modules/dnn/test/test_layers.cpp @@ -576,4 +576,27 @@ TEST(Layer_Test_ROIPooling, Accuracy) normAssert(out, ref); } +TEST(Layer_Test_FasterRCNN_Proposal, Accuracy) +{ + Net net = readNetFromCaffe(_tf("net_faster_rcnn_proposal.prototxt")); + + Mat scores = blobFromNPY(_tf("net_faster_rcnn_proposal.scores.npy")); + Mat deltas = blobFromNPY(_tf("net_faster_rcnn_proposal.deltas.npy")); + Mat imInfo = (Mat_(1, 3) << 600, 800, 1.6f); + Mat ref = blobFromNPY(_tf("net_faster_rcnn_proposal.npy")); + + net.setInput(scores, "rpn_cls_prob_reshape"); + net.setInput(deltas, "rpn_bbox_pred"); + net.setInput(imInfo, "im_info"); + + Mat out = net.forward(); + + const int numDets = ref.size[0]; + EXPECT_LE(numDets, out.size[0]); + normAssert(out.rowRange(0, numDets), ref); + + if (numDets < out.size[0]) + EXPECT_EQ(countNonZero(out.rowRange(numDets, out.size[0])), 0); +} + } diff --git a/samples/dnn/faster_rcnn.cpp b/samples/dnn/faster_rcnn.cpp new file mode 100644 index 0000000..67193d96 --- /dev/null +++ b/samples/dnn/faster_rcnn.cpp @@ -0,0 +1,148 @@ +// Faster-RCNN models use custom layer called 'Proposal' written in Python. To +// map it into OpenCV's layer replace a layer node with [type: 'Python'] to the +// following definition: +// layer { +// name: 'proposal' +// type: 'Proposal' +// bottom: 'rpn_cls_prob_reshape' +// bottom: 'rpn_bbox_pred' +// bottom: 'im_info' +// top: 'rois' +// proposal_param { +// ratio: 0.5 +// ratio: 1.0 +// ratio: 2.0 +// scale: 8 +// scale: 16 +// scale: 32 +// } +// } +#include + +#include +#include +#include +#include + +using namespace cv; +using namespace dnn; + +const char* about = "This sample is used to run Faster-RCNN object detection " + "models from https://github.com/rbgirshick/py-faster-rcnn with OpenCV."; + +const char* keys = + "{ help h | | print help message }" + "{ proto p | | path to .prototxt }" + "{ model m | | path to .caffemodel }" + "{ image i | | path to input image }" + "{ conf c | 0.8 | minimal confidence }"; + +const char* classNames[] = { + "__background__", + "aeroplane", "bicycle", "bird", "boat", + "bottle", "bus", "car", "cat", "chair", + "cow", "diningtable", "dog", "horse", + "motorbike", "person", "pottedplant", + "sheep", "sofa", "train", "tvmonitor" +}; + +static const int kInpWidth = 800; +static const int kInpHeight = 600; + +int main(int argc, char** argv) +{ + // Parse command line arguments. + CommandLineParser parser(argc, argv, keys); + if (argc == 1 || parser.has("help")) + { + std::cout << about << std::endl; + return 0; + } + + String protoPath = parser.get("proto"); + String modelPath = parser.get("model"); + String imagePath = parser.get("image"); + float confThreshold = parser.get("conf"); + CV_Assert(!protoPath.empty(), !modelPath.empty(), !imagePath.empty()); + + // Load a model. + Net net = readNetFromCaffe(protoPath, modelPath); + + // Create a preprocessing layer that does final bounding boxes applying predicted + // deltas to objects locations proposals and doing non-maximum suppression over it. + LayerParams lp; + lp.set("code_type", "CENTER_SIZE"); // An every bounding box is [xmin, ymin, xmax, ymax] + lp.set("num_classes", 21); + lp.set("share_location", (int)false); // Separate predictions for different classes. + lp.set("background_label_id", 0); + lp.set("variance_encoded_in_target", (int)true); + lp.set("keep_top_k", 100); + lp.set("nms_threshold", 0.3); + lp.set("normalized_bbox", (int)false); + Ptr detectionOutputLayer = DetectionOutputLayer::create(lp); + + Mat img = imread(imagePath); + resize(img, img, Size(kInpWidth, kInpHeight)); + Mat blob = blobFromImage(img, 1.0, Size(), Scalar(102.9801, 115.9465, 122.7717), false, false); + Mat imInfo = (Mat_(1, 3) << img.rows, img.cols, 1.6f); + + net.setInput(blob, "data"); + net.setInput(imInfo, "im_info"); + + std::vector outs; + std::vector outNames(3); + outNames[0] = "proposal"; + outNames[1] = "bbox_pred"; + outNames[2] = "cls_prob"; + net.forward(outs, outNames); + + Mat proposals = outs[0].colRange(1, 5).clone(); // Only last 4 columns. + Mat& deltas = outs[1]; + Mat& scores = outs[2]; + + // Reshape proposals from Nx4 to 1x1xN*4 + std::vector shape(3, 1); + shape[2] = (int)proposals.total(); + proposals = proposals.reshape(1, shape); + + // Run postprocessing layer. + std::vector layerInputs(3), layerOutputs(1), layerInternals; + layerInputs[0] = deltas.reshape(1, 1); + layerInputs[1] = scores.reshape(1, 1); + layerInputs[2] = proposals; + detectionOutputLayer->forward(layerInputs, layerOutputs, layerInternals); + + // Draw detections. + Mat detections = layerOutputs[0]; + const float* data = (float*)detections.data; + for (size_t i = 0; i < detections.total(); i += 7) + { + // An every detection is a vector [id, classId, confidence, left, top, right, bottom] + float confidence = data[i + 2]; + if (confidence > confThreshold) + { + int classId = (int)data[i + 1]; + int left = max(0, min((int)data[i + 3], img.cols - 1)); + int top = max(0, min((int)data[i + 4], img.rows - 1)); + int right = max(0, min((int)data[i + 5], img.cols - 1)); + int bottom = max(0, min((int)data[i + 6], img.rows - 1)); + + // Draw a bounding box. + rectangle(img, Point(left, top), Point(right, bottom), Scalar(0, 255, 0)); + + // Put a label with a class name and confidence. + String label = cv::format("%s, %.3f", classNames[classId], confidence); + int baseLine; + Size labelSize = cv::getTextSize(label, FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine); + + top = max(top, labelSize.height); + rectangle(img, Point(left, top - labelSize.height), + Point(left + labelSize.width, top + baseLine), + Scalar(255, 255, 255), FILLED); + putText(img, label, Point(left, top), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 0, 0)); + } + } + imshow("frame", img); + waitKey(); + return 0; +}