check folds for issues

based on time between the creation of the pictures

check_cross_validation.py

+from datetime import datetime
+
+def get_date2(filename):
+    if filename.startswith('IMG'):
+        filename = filename[4:]
+    #return filename[:8] # only dates
+    if filename == '20190508-WA0026.jpg':
+        filename = '20190508_123000.jpg'
+    return filename[:13]
+
+def get_date(filename):
+    return get_date2(filename)[:-2]
+
+
+#20190520_120309
+def time_diff(date1, date2):
+    date1 = get_date2(date1)
+    date2 = get_date2(date2)
+    d1 = datetime.strptime(date1, '%Y%m%d_%H%M')
+    d2 = datetime.strptime(date2, '%Y%m%d_%H%M')
+    tmp = None
+    if d1 < d2:
+        tmp = d1
+        d1 = d2
+        d2 = tmp
+    duration = d1 - d2  # For build-in functions
+    duration_in_s = duration.total_seconds()
+    return duration_in_s, d1, d2
+    #if duration_in_s < 600:
+    #    print(duration_in_s)
+    #    print()
+
+num_folds = 5
+min_time_diff = 3 * 60 # N minutes --> in seconds
+output_path = 'data/cross_validate/'
+# Create empty lists for each fold as sublist of folds
+folds = []
+for i in range(num_folds):
+    folds.append([])
+
+for i in range(num_folds):
+    new_dir = output_path + 'fold_' + str(i)
+    with open(new_dir+'/annotations_test.txt', 'r') as file:
+        lines = file.readlines()
+        for line in lines:
+            filename = line.split(',')[0]
+            folds[i].append(filename)
+
+for fold in folds:
+    fold.sort()
+    print('len', len(fold))
+    print(fold)
+
+for i in range(len(folds)):
+    for j in range(i, len(folds)):
+        if i == j:
+            continue
+        min_difference = 60*60*24 # one day in seconds
+        old = min_difference
+        element1 = ''
+        element2 = ''
+        time1 = ''
+        time2 = ''
+        print('Fold', str(i), 'and Fold', str(j))
+        for elem1 in folds[i]:
+            for elem2 in folds[j]:
+                diff, d1, d2 = time_diff(elem1, elem2)
+                if diff < min_time_diff:
+                    print(str(diff / 60) + " min Zeitdifferenz")
+                    print(str(d1) + " - " + str(d2))
+                    print(elem1 + " - " + elem2)
+                    print()
+        print()
\ No newline at end of file