Add files via upload

get_gt_txt.py

+#----------------------------------------------------#
+#   获取测试集的ground-truth
+#   具体视频教程可查看
+#   https://www.bilibili.com/video/BV1zE411u7Vw
+#----------------------------------------------------#
 import sys
 import os
 import glob
 import xml.etree.ElementTree as ET
-from tqdm import tqdm
 
 image_ids = open('VOCdevkit/VOC2007/ImageSets/Main/test.txt').read().strip().split()
 
@@ -11,19 +15,24 @@ if not os.path.exists("./input"):
 if not os.path.exists("./input/ground-truth"):
     os.makedirs("./input/ground-truth")
 
-for image_id in tqdm(image_ids):
+for image_id in image_ids:
     with open("./input/ground-truth/"+image_id+".txt", "w") as new_f:
         root = ET.parse("VOCdevkit/VOC2007/Annotations/"+image_id+".xml").getroot()
         for obj in root.findall('object'):
+            difficult_flag = False
             if obj.find('difficult')!=None:
                 difficult = obj.find('difficult').text
                 if int(difficult)==1:
-                    continue
+                    difficult_flag = True
             obj_name = obj.find('name').text
             bndbox = obj.find('bndbox')
             left = bndbox.find('xmin').text
             top = bndbox.find('ymin').text
             right = bndbox.find('xmax').text
             bottom = bndbox.find('ymax').text
-            new_f.write("%s %s %s %s %s\n" % (obj_name, left, top, right, bottom))
+            if difficult_flag:
+                new_f.write("%s %s %s %s %s difficult\n" % (obj_name, left, top, right, bottom))
+            else:
+                new_f.write("%s %s %s %s %s\n" % (obj_name, left, top, right, bottom))
+
 print("Conversion completed!")

get_map.py

@@ -346,7 +346,10 @@ if os.path.exists(results_files_path): # if it exist already
 
 os.makedirs(results_files_path)
 if draw_plot:
-    os.makedirs(os.path.join(results_files_path, "classes"))
+    os.makedirs(os.path.join(results_files_path, "AP"))
+    os.makedirs(os.path.join(results_files_path, "F1"))
+    os.makedirs(os.path.join(results_files_path, "Recall"))
+    os.makedirs(os.path.join(results_files_path, "Precision"))
 if show_animation:
     os.makedirs(os.path.join(results_files_path, "images", "detections_one_by_one"))
 
@@ -503,6 +506,7 @@ lamr_dictionary = {}
 with open(results_files_path + "/results.txt", 'w') as results_file:
     results_file.write("# AP and precision/recall per class\n")
     count_true_positives = {}
+
     for class_index, class_name in enumerate(gt_classes):
         count_true_positives[class_name] = 0
         """
@@ -517,8 +521,14 @@ with open(results_files_path + "/results.txt", 'w') as results_file:
         nd = len(dr_data)
         tp = [0] * nd # creates an array of zeros of size nd
         fp = [0] * nd
+        score = [0] * nd
+        score05_idx = 0
         for idx, detection in enumerate(dr_data):
             file_id = detection["file_id"]
+            score[idx]   = float(detection["confidence"])
+            if score[idx] > 0.5:
+                score05_idx = idx
+
             if show_animation:
                 # find ground truth image
                 ground_truth_img = glob.glob1(IMG_PATH, file_id + ".*")
@@ -652,7 +662,6 @@ with open(results_files_path + "/results.txt", 'w') as results_file:
                 # save the image with all the objects drawn to it
                 cv2.imwrite(img_cumulative_path, img_cumulative)
 
-        #print(tp)
         # compute precision/recall
         cumsum = 0
         for idx, val in enumerate(fp):
@@ -664,6 +673,7 @@ with open(results_files_path + "/results.txt", 'w') as results_file:
             cumsum += val
         #print(tp)
         rec = tp[:]
+
         for idx, val in enumerate(tp):
             rec[idx] = float(tp[idx]) / gt_counter_per_class[class_name]
         #print(rec)
@@ -671,10 +681,20 @@ with open(results_files_path + "/results.txt", 'w') as results_file:
         for idx, val in enumerate(tp):
             prec[idx] = float(tp[idx]) / (fp[idx] + tp[idx])
         #print(prec)
-
         ap, mrec, mprec = voc_ap(rec[:], prec[:])
+        F1 = np.array(rec)*np.array(prec)/(np.array(prec)+np.array(rec))*2
+
         sum_AP += ap
         text = "{0:.2f}%".format(ap*100) + " = " + class_name + " AP " #class_name + " AP = {0:.2f}%".format(ap*100)
+
+        if len(prec)>0:
+            F1_text = "{0:.2f}".format(F1[score05_idx]) + " = " + class_name + " F1 "
+            Recall_text = "{0:.2f}%".format(rec[score05_idx]*100) + " = " + class_name + " Recall "
+            Precision_text = "{0:.2f}%".format(prec[score05_idx]*100) + " = " + class_name + " Precision "
+        else:
+            F1_text = "0.00" + " = " + class_name + " F1 " 
+            Recall_text = "0.00%" + " = " + class_name + " Recall " 
+            Precision_text = "0.00%" + " = " + class_name + " Precision " 
         """
          Write to results.txt
         """
@@ -682,7 +702,8 @@ with open(results_files_path + "/results.txt", 'w') as results_file:
         rounded_rec = [ '%.2f' % elem for elem in rec ]
         results_file.write(text + "\n Precision: " + str(rounded_prec) + "\n Recall :" + str(rounded_rec) + "\n\n")
         if not args.quiet:
-            print(text)
+            print(text + "\t||\tscore_threhold=0.5 : " + "F1=" + "{0:.2f}".format(F1[score05_idx])\
+                 + " ; Recall=" + "{0:.2f}%".format(rec[score05_idx]*100) + " ; Precision=" + "{0:.2f}%".format(prec[score05_idx]*100))
         ap_dictionary[class_name] = ap
 
         n_images = counter_images_per_class[class_name]
@@ -713,11 +734,42 @@ with open(results_files_path + "/results.txt", 'w') as results_file:
             axes.set_xlim([0.0,1.0])
             axes.set_ylim([0.0,1.05]) # .05 to give some extra space
             # Alternative option -> wait for button to be pressed
-            #while not plt.waitforbuttonpress(): pass # wait for key display
+            # while not plt.waitforbuttonpress(): pass # wait for key display
             # Alternative option -> normal display
-            #plt.show()
+            # plt.show()
+
             # save the plot
-            fig.savefig(results_files_path + "/classes/" + class_name + ".png")
+            fig.savefig(results_files_path + "/AP/" + class_name + ".png")
+            plt.cla() # clear axes for next plot
+
+            plt.plot(score, F1, "-", color='orangered')
+            plt.title('class: ' + F1_text + "\nscore_threhold=0.5")
+            plt.xlabel('Score_Threhold')
+            plt.ylabel('F1')
+            axes = plt.gca() # gca - get current axes
+            axes.set_xlim([0.0,1.0])
+            axes.set_ylim([0.0,1.05]) # .05 to give some extra space
+            fig.savefig(results_files_path + "/F1/" + class_name + ".png")
+            plt.cla() # clear axes for next plot
+
+            plt.plot(score, rec, "-H", color='gold')
+            plt.title('class: ' + Recall_text + "\nscore_threhold=0.5")
+            plt.xlabel('Score_Threhold')
+            plt.ylabel('Recall')
+            axes = plt.gca() # gca - get current axes
+            axes.set_xlim([0.0,1.0])
+            axes.set_ylim([0.0,1.05]) # .05 to give some extra space
+            fig.savefig(results_files_path + "/Recall/" + class_name + ".png")
+            plt.cla() # clear axes for next plot
+
+            plt.plot(score, prec, "-s", color='palevioletred')
+            plt.title('class: ' + Precision_text + "\nscore_threhold=0.5")
+            plt.xlabel('Score_Threhold')
+            plt.ylabel('Precision')
+            axes = plt.gca() # gca - get current axes
+            axes.set_xlim([0.0,1.0])
+            axes.set_ylim([0.0,1.05]) # .05 to give some extra space
+            fig.savefig(results_files_path + "/Precision/" + class_name + ".png")
             plt.cla() # clear axes for next plot
 
     if show_animation:

voc_annotation.py

@@ -3,18 +3,18 @@ from os import getcwd
 
 sets=[('2007', 'train'), ('2007', 'val'), ('2007', 'test')]
 
-wd = getcwd()
 classes = ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
 
 def convert_annotation(year, image_id, list_file):
     in_file = open('VOCdevkit/VOC%s/Annotations/%s.xml'%(year, image_id))
     tree=ET.parse(in_file)
     root = tree.getroot()
-    if root.find('object')==None:
-        return
-    list_file.write('%s/VOCdevkit/VOC%s/JPEGImages/%s.jpg'%(wd, year, image_id))
+
     for obj in root.iter('object'):
-        difficult = obj.find('difficult').text
+        difficult = 0 
+        if obj.find('difficult')!=None:
+            difficult = obj.find('difficult').text
+            
         cls = obj.find('name').text
         if cls not in classes or int(difficult)==1:
             continue
@@ -23,11 +23,13 @@ def convert_annotation(year, image_id, list_file):
         b = (int(xmlbox.find('xmin').text), int(xmlbox.find('ymin').text), int(xmlbox.find('xmax').text), int(xmlbox.find('ymax').text))
         list_file.write(" " + ",".join([str(a) for a in b]) + ',' + str(cls_id))
 
-    list_file.write('\n')
+wd = getcwd()
 
 for year, image_set in sets:
     image_ids = open('VOCdevkit/VOC%s/ImageSets/Main/%s.txt'%(year, image_set)).read().strip().split()
     list_file = open('%s_%s.txt'%(year, image_set), 'w')
     for image_id in image_ids:
+        list_file.write('%s/VOCdevkit/VOC%s/JPEGImages/%s.jpg'%(wd, year, image_id))
         convert_annotation(year, image_id, list_file)
+        list_file.write('\n')
     list_file.close()