tensorflow - ValueError: Protocol message StringIntLabelMapItem has no field frequency

Question

I'm trying to build an object detector using tensorflow from a YouTube tutorial. I have created a conda environment and installed all the required packages. Now when I try to run its script in VScode, it shows this error.

Traceback (most recent call last):
File "updated_old_example.py", line 79, in <module>
categories = label_map_util.convert_label_map_to_categories(label_map,max_num_classes=NUM_CLASSES, use_display_name=True)
File "/Users/Home/Desktop/Project/Object_Detection/models/research/object_detection/utils/label_map_util.py", line 133, in convert_label_map_to_categories
if item.HasField('frequency'):
ValueError: Protocol message StringIntLabelMapItem has no field frequency.

This is the first time I'm encountering this error. Some fix would be really appreciated.

Answer 1

I have never find this kind of issue before, but after downloading new models from tensorflow API this error just comes out. Then i tried to compare the file that written on error message with the old version of tensorflow api models, that's where the Error comes out. all you need to do is find this file:

Object_Detection/models/research/object_detection/utils/label_map_util.py", line 133

then delete this code

  if item.HasField('frequency'):
    if item.frequency == string_int_label_map_pb2.LVISFrequency.Value(
        'FREQUENT'):
      category['frequency'] = 'f'
    elif item.frequency == string_int_label_map_pb2.LVISFrequency.Value(
        'COMMON'):
      category['frequency'] = 'c'
    elif item.frequency == string_int_label_map_pb2.LVISFrequency.Value(
        'RARE'):
      category['frequency'] = 'r'
  if item.HasField('instance_count'):
    category['instance_count'] = item.instance_count