I am getting this error while training my object detection program . how to slove this module error

D:\RealTimeObjectDetection>python Tensorflow/models/research/object_detection/model_main_tf2.py --model_dir=Tensorflow/workspace/models/my_ssd_mobnet --pipeline_config_path=Tensorflow/workspace/models/my_ssd_mobnet/pipeline.config --num_train_steps=10000
WARNING:tensorflow:From C:\Users\LENOVO\AppData\Roaming\Python\Python311\site-packages\keras\src\losses.py:2976: The name tf.losses.sparse_softmax_cross_entropy is deprecated. Please use tf.compat.v1.losses.sparse_softmax_cross_entropy instead.

Traceback (most recent call last):
File “D:\RealTimeObjectDetection\Tensorflow\models\research\object_detection\model_main_tf2.py”, line 31, in
from object_detection import model_lib_v2
File “C:\ProgramData\anaconda3\Lib\site-packages\object_detection\model_lib_v2.py”, line 31, in
from object_detection import model_lib
File “C:\ProgramData\anaconda3\Lib\site-packages\object_detection\model_lib.py”, line 35, in
from object_detection.builders import optimizer_builder
File “C:\ProgramData\anaconda3\Lib\site-packages\object_detection\builders\optimizer_builder.py”, line 25, in
from official.modeling.optimization import ema_optimizer
File “C:\ProgramData\anaconda3\Lib\site-packages\official\modeling\optimization_init_.py”, line 19, in
from official.modeling.optimization.configs.optimization_config import *
File “C:\ProgramData\anaconda3\Lib\site-packages\official\modeling\optimization\configs\optimization_config.py”, line 31, in
@dataclasses.dataclass
^^^^^^^^^^^^^^^^^^^^^
File “C:\ProgramData\anaconda3\Lib\dataclasses.py”, line 1230, in dataclass
return wrap(cls)
^^^^^^^^^
File “C:\ProgramData\anaconda3\Lib\dataclasses.py”, line 1220, in wrap
return _process_class(cls, init, repr, eq, order, unsafe_hash,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “C:\ProgramData\anaconda3\Lib\dataclasses.py”, line 958, in _process_class
cls_fields.append(_get_field(cls, name, type, kw_only))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “C:\ProgramData\anaconda3\Lib\dataclasses.py”, line 815, in _get_field
raise ValueError(f’mutable default {type(f.default)} for field ’
ValueError: mutable default <class ‘official.modeling.optimization.configs.optimizer_config.SGDConfig’> for field sgd is not allowed: use default_factory

The error you’re seeing is due to a mutable default argument in a data class, specifically SGDConfig. To solve this, you can try updating TensorFlow and the Object Detection API to their latest versions. If the issue persists, you may need to manually edit the source code where SGDConfig is used, changing the default value to use default_factory=SGDConfig. Be cautious when editing library code, as it may lead to further issues or be overwritten by updates.