Add evaluate function

examples/yolo/yolo_detect.cpp

@@ -482,7 +482,7 @@ void MatMul(cv::Mat img1, cv::Mat img2,int idx=0)
 		int img_index1 = 0;
 		int img_index2 = 0;
 		for (j = 0; j < width; j++) {
-      if(ptr2[img_index2]>20) {
+      if(ptr2[img_index2]>120) {
         ptr1[img_index1+idx] = 127 + ptr1[img_index1]/2;
       }
 			//ptr1[img_index1+idx] = (unsigned char) BOUND(ptr1[img_index1] + ptr2[img_index2] * 1.0,0,255);

include/caffe/layers/annotated_data_layer.hpp

@@ -44,6 +44,9 @@ class AnnotatedDataLayer : public BasePrefetchingDataLayer<Dtype> {
   bool single_class_; //for yolo segementation
   YoloSegLabel label_map_;
   int seg_label_maxima_;
+  int seg_scales_;
+  int seg_resize_width_;
+  int seg_resize_height_;
 };
 
 }  // namespace caffe

include/caffe/layers/segmentation_evaluate_layer.hpp

@@ -0,0 +1,77 @@
+/*
+* @Author: Eric612
+* @Date:   2019-03-11
+* @https://github.com/eric612/Caffe-YOLOv3-Windows
+* @https://github.com/eric612/MobileNet-YOLO
+* Avisonic , ELAN microelectronics
+*/
+#ifdef USE_OPENCV
+#include <opencv2/core/core.hpp>
+#include <opencv2/highgui/highgui.hpp>
+#include <opencv2/imgproc/imgproc.hpp>
+#endif  // USE_OPENCV
+#ifndef CAFFE_SEGMENTATION_EVALUATE_LAYER_HPP_
+#define CAFFE_SEGMENTATION_EVALUATE_LAYER_HPP_
+
+#include <utility>
+#include <vector>
+
+#include "caffe/blob.hpp"
+#include "caffe/layer.hpp"
+#include "caffe/proto/caffe.pb.h"
+
+namespace caffe {
+
+/**
+ * @brief Generate the detection evaluation based on DetectionOutputLayer and
+ * ground truth bounding box labels.
+ *
+ * Intended for use with MultiBox detection method.
+ *
+ * NOTE: does not implement Backwards operation.
+ */
+template <typename Dtype>
+class SegmentationEvaluateLayer : public Layer<Dtype> {
+ public:
+  explicit SegmentationEvaluateLayer(const LayerParameter& param)
+      : Layer<Dtype>(param) {}
+  virtual void LayerSetUp(const vector<Blob<Dtype>*>& bottom,
+      const vector<Blob<Dtype>*>& top);
+  virtual void Reshape(const vector<Blob<Dtype>*>& bottom,
+      const vector<Blob<Dtype>*>& top);
+
+  virtual inline const char* type() const { return "DetectionEvaluate"; }
+  virtual inline int ExactBottomBlobs() const { return 2; }
+  virtual inline int ExactNumTopBlobs() const { return 1; }
+
+ protected:
+  /**
+   * @brief Evaluate the detection output.
+   *
+   * @param bottom input Blob vector (exact 2)
+   *   -# @f$ (1 \times 1 \times N \times 7) @f$
+   *      N detection results.
+   *   -# @f$ (1 \times 1 \times M \times 7) @f$
+   *      M ground truth.
+   * @param top Blob vector (length 1)
+   *   -# @f$ (1 \times 1 \times N \times 4) @f$
+   *      N is the number of detections, and each row is:
+   *      [image_id, label, confidence, true_pos, false_pos]
+   */
+  virtual void Forward_cpu(const vector<Blob<Dtype>*>& bottom,
+      const vector<Blob<Dtype>*>& top);
+  /// @brief Not implemented
+  virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
+      const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom) {
+    NOT_IMPLEMENTED;
+  }
+  void visualization(const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top);
+  int num_classes_;
+  //std::vector<cv::Mat> seg_img_;
+  float threshold_;
+  int iter_;
+};
+
+}  // namespace caffe
+
+#endif  // CAFFE_SEGMENTATION_EVALUATE_LAYER_HPP_

include/caffe/solver.hpp

@@ -105,6 +105,7 @@ class Solver {
   void TestAll();
   void TestClassification(const int test_net_id = 0);
   void TestDetection(const int test_net_id = 0);
+  void TestDetectionSeg(const int test_net_id = 0);
   virtual void SnapshotSolverState(const string& model_filename) = 0;
   virtual void RestoreSolverStateFromHDF5(const string& state_file) = 0;
   virtual void RestoreSolverStateFromBinaryProto(const string& state_file) = 0;

models/cityscapes/mobilenet_yolov3_solver.prototxt

@@ -1,7 +1,7 @@
 train_net: "models/cityscapes/mobilenet_yolov3_train.prototxt"
-#test_net: "models/cityscapes/mobilenet_yolov3_test.prototxt"
-#test_iter: 2000
-#test_interval: 1000
+test_net: "models/cityscapes/mobilenet_yolov3_test.prototxt"
+test_iter: 500
+test_interval: 1000
 base_lr: 0.0005
 display: 10
 max_iter: 120000
@@ -20,6 +20,6 @@ stepvalue: 40000
 stepvalue: 60000
 iter_size: 16
 type: "RMSProp"
-eval_type: "detection"
+eval_type: "detection_segmentation"
 ap_version: "11point"
 show_per_class_result: true

models/cityscapes/mobilenet_yolov3_test.prototxt

@@ -4,6 +4,7 @@ layer {
   type: "AnnotatedData"
   top: "data"
   top: "label"
+  top: "seg_label"
   include {
     phase: TEST
   }
@@ -22,14 +23,17 @@ layer {
     }
   }
   data_param {
-    source: "examples/bus/bus_test_lmdb"
+    source: "examples/cityscapes/cityscapes_val_lmdb"
     batch_size: 1
     backend: LMDB
   }
   annotated_data_param {
+    single_class : false
+    #seg_resize_width : 2048
+    #seg_resize_height : 1024
     batch_sampler {
     }
-    label_map_file: "data/VOC0712/labelmap_voc.prototxt"
+    label_map_file:  "data/cityscapes/labelmap_seg.prototxt"
   }
 }
 
@@ -2911,24 +2915,23 @@ layer {
 	#10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
 
     biases: 4
-    biases: 9
+    biases: 7
     biases: 6
-    biases: 15
+    biases: 13
     biases: 8
-    biases: 22
-    biases: 12
-    biases: 31
+    biases: 21
+    biases: 18
     biases: 16
-    biases: 42
-    biases: 22
-    biases: 57
-    biases: 32
-    biases: 81
-    biases: 50
-    biases: 124
-    biases: 82
-    biases: 207 
-	
+    biases: 12
+    biases: 33
+    biases: 20
+    biases: 47
+    biases: 30
+    biases: 71
+    biases: 46
+    biases: 112
+    biases: 78
+    biases: 193    
     mask:6
     mask:7
     mask:8
@@ -2944,7 +2947,6 @@ layer {
     mask_group_num:3
   }
 }
-
 layer {
   name: "detection_eval"
   type: "DetectionEvaluate"
@@ -2960,3 +2962,179 @@ layer {
   }
 }
 
+layer {
+  name: "conv25/dw"
+  type: "DepthwiseConvolution"
+  bottom: "conv20/sum"
+  top: "conv25/dw"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  convolution_param {
+    num_output: 256
+    bias_term: false
+    pad: 1
+    kernel_size: 3
+    group: 256
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+  }
+}
+layer {
+  name: "conv25/dw/bn"
+  type: "BatchNorm"
+  bottom: "conv25/dw"
+  top: "conv25/dw"
+  param {
+    lr_mult: 0
+    decay_mult: 0
+  }
+  param {
+    lr_mult: 0
+    decay_mult: 0
+  }
+  param {
+    lr_mult: 0
+    decay_mult: 0
+  }
+}
+layer {
+  name: "conv25/dw/scale"
+  type: "Scale"
+  bottom: "conv25/dw"
+  top: "conv25/dw"
+  param {
+    lr_mult: 1
+    decay_mult: 0.0
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0.0
+  }
+  scale_param {
+    filler {
+      value: 1
+    }
+    bias_term: true
+    bias_filler {
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv25/dw/relu"
+  type: "ReLU"
+  bottom: "conv25/dw"
+  top: "conv25/dw"
+}
+layer {
+  name: "conv25"
+  type: "Convolution"
+  bottom: "conv25/dw"
+  top: "conv25"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  convolution_param {
+    num_output: 256 
+    bias_term: false
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+  }
+}
+layer {
+  name: "conv25/bn"
+  type: "BatchNorm"
+  bottom: "conv25"
+  top: "conv25"
+  param {
+    lr_mult: 0
+    decay_mult: 0
+  }
+  param {
+    lr_mult: 0
+    decay_mult: 0
+  }
+  param {
+    lr_mult: 0
+    decay_mult: 0
+  }
+}
+layer {
+  name: "conv25/scale"
+  type: "Scale"
+  bottom: "conv25"
+  top: "conv25"
+  param {
+    lr_mult: 1.0
+    decay_mult: 0.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  scale_param {
+    filler {
+      value: 1
+    }
+    bias_term: true
+    bias_filler {
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv25/relu"
+  type: "ReLU"
+  bottom: "conv25"
+  top: "conv25"
+}
+layer {
+  name: "conv26"
+  type: "Convolution"
+  bottom: "conv25"
+  top: "conv26"
+    param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 3 # channel = class 
+    kernel_size: 1
+    pad: 0
+    stride: 1
+    weight_filler {
+      type: "msra"
+    }
+	bias_filler {
+      value: 0
+    }
+  }
+}
+layer {
+  name: "sigmoid"
+  bottom: "conv26"
+  top: "sigmoid"
+  type: "Sigmoid"
+}
+layer {
+  name: "segmentation_eval"
+  type: "SegmentationEvaluate"
+  bottom: "sigmoid"
+  bottom: "seg_label"
+  top: "segmentation_eval"
+
+  segmentation_evaluate_param {
+    num_classes: 3
+  }
+}