diff --git a/algorithm/mot/sv_mot.cpp b/algorithm/mot/sv_mot.cpp
index 73701c3..4e26283 100644
--- a/algorithm/mot/sv_mot.cpp
+++ b/algorithm/mot/sv_mot.cpp
@@ -195,7 +195,7 @@ void SORT::update(TargetsInFrame& tgts)
             tracklet.age = 0;
             tracklet.hits = 1;
             tracklet.misses = 0;
-            tracklet.frame_id=tgts.frame_id;
+            tracklet.frame_id = tgts.frame_id;
             tracklet.tentative = true;
             // initate the motion
             pair<Matrix<double, 8, 1>, Matrix<double, 8, 8> > motion = kf.initiate(tracklet.bbox);
@@ -245,13 +245,13 @@ void SORT::update(TargetsInFrame& tgts)
             int detectionIndex = match.second;
             if (trackletIndex >= 0 && detectionIndex >= 0)
             {
-                if (iouMatrix[match.first][match.second] >= _iou_threshold)//iou_thrshold
+                if (iouMatrix[match.first][match.second] >= _iou_threshold)  // iou_thrshold
                 {
                     sv::Box box;
                     tgts.targets[detectionIndex].getBox(box);
                     this->_tracklets[trackletIndex].age = 0;
                     this->_tracklets[trackletIndex].hits++;
-                    this->_tracklets[trackletIndex].frame_id=tgts.frame_id;
+                    this->_tracklets[trackletIndex].frame_id = tgts.frame_id;
                     this->_tracklets[trackletIndex].bbox << box.x1, box.y1, box.x2-box.x1, box.y2-box.y1;
 
                     auto[mean, covariance] = kf.update(this->_tracklets[trackletIndex].mean, this->_tracklets[trackletIndex].covariance, box);
@@ -264,7 +264,7 @@ void SORT::update(TargetsInFrame& tgts)
             }
         }
         // create new tracklets for unmatched detections
-        for (int i = 0; i < tgts.targets.size(); i++)
+        for (int i=0; i<tgts.targets.size(); i++)
         { 
             if (match_det[i] == -1)
             {
@@ -277,7 +277,7 @@ void SORT::update(TargetsInFrame& tgts)
                 tracklet.age = 0;
                 tracklet.hits = 1;
                 tracklet.misses = 0;
-                tracklet.frame_id=tgts.frame_id;
+                tracklet.frame_id = tgts.frame_id;
                 tracklet.tentative = true;
                 
                 auto[new_mean, new_covariance] = kf.initiate(tracklet.bbox);
@@ -295,7 +295,7 @@ void SORT::update(TargetsInFrame& tgts)
             {
                 tracklet.tentative = false;
             }
-            if ((tgts.frame_id-tracklet.frame_id <= _max_age) || (!tracklet.tentative && tracklet.frame_id==tgts.frame_id))
+            if ((tgts.frame_id-tracklet.frame_id <= _max_age) || (!tracklet.tentative && tracklet.frame_id == tgts.frame_id))
             {
                 _new_tracklets.push_back(tracklet);
             } 
diff --git a/include/sv_mot.h b/include/sv_mot.h
index 54964bf..9ed81df 100644
--- a/include/sv_mot.h
+++ b/include/sv_mot.h
@@ -51,11 +51,11 @@ struct Tracklet
 /* data */
 public:
     Eigen::Vector4d bbox;  // double x, y, w, h;
-    int id=0;
+    int id = 0;
     int age;
     int hits;
     int misses;
-    int frame_id=0;
+    int frame_id = 0;
     bool tentative;
     std::vector<double> features;
     Eigen::Matrix<double, 8, 1> mean;
diff --git a/samples/test/eval_mAP_on_coco_val/coco_eval.py b/samples/test/eval_mAP_on_coco_val/coco_eval.py
index 39de0ed..cf13271 100644
--- a/samples/test/eval_mAP_on_coco_val/coco_eval.py
+++ b/samples/test/eval_mAP_on_coco_val/coco_eval.py
@@ -11,19 +11,19 @@ if __name__ == '__main__':
     # use COCO API to load forecast results and annotations
     cocoGt = COCO(anno_json)
     with open(pred_json,'r') as file:
-      data = json.load(file)
+        data = json.load(file)
     
     # align anno_json with pred_json category_id
     gtCatDicts = {}
     for anns in range(len(cocoGt.getCatIds())):
-      gtCatDicts[anns] = cocoGt.getCatIds()[anns]
+        gtCatDicts[anns] = cocoGt.getCatIds()[anns]
 
     pdCatIds=list(set([d['category_id'] for d in data]))
 
     if not set(pdCatIds).issubset(set(cocoGt.getCatIds())):
         for ins in data:
-           temp = int(gtCatDicts[ins['category_id']])
-           ins['category_id'] = temp
+            temp = int(gtCatDicts[ins['category_id']])
+            ins['category_id'] = temp
 
     # load prediction results
     cocoDt = cocoGt.loadRes(data)
diff --git a/samples/test/eval_mAP_on_coco_val/eval_mAP_on_coco_val.cpp b/samples/test/eval_mAP_on_coco_val/eval_mAP_on_coco_val.cpp
index 12f6339..426fc0e 100644
--- a/samples/test/eval_mAP_on_coco_val/eval_mAP_on_coco_val.cpp
+++ b/samples/test/eval_mAP_on_coco_val/eval_mAP_on_coco_val.cpp
@@ -8,17 +8,21 @@ using namespace cv;
 
 //extract name
 std::string GetImageFileName(const std::string& imagePath) {
-    size_t lastSlash = imagePath.find_last_of("/\\");
-    if (lastSlash == std::string::npos) {
-        return imagePath;
-    } else {
-        std::string fileName = imagePath.substr(lastSlash + 1);
-        size_t lastDot = fileName.find_last_of(".");
-        if (lastDot != std::string::npos) {
-            return fileName.substr(0, lastDot);
-        }
-        return fileName;
+  size_t lastSlash = imagePath.find_last_of("/\\");
+  if (lastSlash == std::string::npos)
+  {
+    return imagePath;
+  }
+  else
+  {
+    std::string fileName = imagePath.substr(lastSlash + 1);
+    size_t lastDot = fileName.find_last_of(".");
+    if (lastDot != std::string::npos)
+    {
+      return fileName.substr(0, lastDot);
     }
+    return fileName;
+  }
 }
 
 
@@ -60,8 +64,8 @@ int main(int argc, char *argv[])
   }
 
 
-  for (int i = 0; i < val_image.size(); i++) {
-
+  for (int i = 0; i < val_image.size(); i++)
+  {
     //create pred file
     std::string val_image_name = GetImageFileName(val_image[i]);
     std::string filename = folder+"/"+ val_image_name + ".txt";
@@ -84,11 +88,12 @@ int main(int argc, char *argv[])
     // reslusts
     for (int j = 0; j < tgts.targets.size(); j++)
     {
-        sv::Box b;
-        tgts.targets[j].getBox(b);
-        file<<tgts.targets[j].category_id<<" "<<(float)(b.x1+b.x2)/(2*cols)<<" "<<(float)(b.y1+b.y2)/(2*rows)<<" "<<(float)(b.x2-b.x1)/cols<<" "<<(float)(b.y2-b.y1)/rows<<" "<<(float)tgts.targets[j].score<<"\n";
-    }
-    file.close();  
+      sv::Box b;
+      tgts.targets[j].getBox(b);
+      file << tgts.targets[j].category_id << " " << (float)(b.x1+b.x2) / (2*cols) << " " << (float)(b.y1+b.y2) / (2*rows) << \
+        " " << (float)(b.x2-b.x1) / cols << " " << (float)(b.y2-b.y1) / rows << " " << (float)tgts.targets[j].score << "\n";
     }
+    file.close();
+  }
   return 0;
 }
diff --git a/samples/test/eval_mAP_on_coco_val/pd2cocojson.py b/samples/test/eval_mAP_on_coco_val/pd2cocojson.py
index cd0f1e7..db62a88 100644
--- a/samples/test/eval_mAP_on_coco_val/pd2cocojson.py
+++ b/samples/test/eval_mAP_on_coco_val/pd2cocojson.py
@@ -4,11 +4,11 @@ import os
 import cv2
 
 # revert prediction results to coco_json 
-path = os.path.abspath(os.path.join(os.getcwd(),"../../.."))
+path = os.path.abspath(os.path.join(os.getcwd(), "../../.."))
 
 # all files dir
-images_path = path+'/val2017/val2017'
-preds_path = path+'/val2017/preds'
+images_path = path + '/val2017/val2017'
+preds_path = path + '/val2017/preds'
 coco_json_save ='pd_coco.json'
 
 # config coco_json
@@ -27,25 +27,26 @@ for image in images:
     # read pred's txt
     pred_path = preds_path + '/' + image_name + '.txt'
     if not os.path.exists(pred_path):
-      continue
+        continue
     with open(pred_path, 'r') as f:
-      preds = f.readlines()
-      preds = [l.strip() for l in preds]
-      for j,pred in enumerate(preds):
-        pred = pred.split(' ')
-        category_id = int(pred[0])
-        x = float(pred[1]) * width
-        y = float(pred[2]) * height
-        w = float(pred[3]) * width
-        h = float(pred[4]) * height
-        xmin = x - w / 2
-        ymin = y - h / 2
-        
-        coco_json.append({
-         'image_id': int(image_name),
-         'category_id': int(category_id),
-         'bbox': [xmin, ymin, w, h],
-         'score': float(pred[5])})
+        preds = f.readlines()
+        preds = [l.strip() for l in preds]
+        for j,pred in enumerate(preds):
+            pred = pred.split(' ')
+            category_id = int(pred[0])
+            x = float(pred[1]) * width
+            y = float(pred[2]) * height
+            w = float(pred[3]) * width
+            h = float(pred[4]) * height
+            xmin = x - w / 2
+            ymin = y - h / 2
+            
+            coco_json.append({
+                'image_id': int(image_name),
+                'category_id': int(category_id),
+                'bbox': [xmin, ymin, w, h],
+                'score': float(pred[5])
+            })
 
 # save json
 with open(os.path.join(coco_json_save), 'w') as f: