tensorflow2 object detection API _training process_

I couldn't train the model for object detection when I tried to use tensorflow2 object detection API.
When I run,
<python model_main_tf2.py --model_dir=models/my_ssd_resnet50_v1_fpn --pipeline_config_path=models/my_ssd_resnet50_v1_fpn/pipeline.config>

returns,
Traceback (most recent call last):
<File "model_main_tf2.py", line 32, in
from object_detection import model_lib_v2
File "C:\Users\usr\anaconda3\envs\tensorflow\lib\site-packages\object_detection\model_lib_v2.py", line 29, in
from object_detection import eval_util
File "C:\Users\usr\anaconda3\envs\tensorflow\lib\site-packages\object_detection\eval_util.py", line 35, in
from object_detection.metrics import coco_evaluation
File "C:\Users\usr\anaconda3\envs\tensorflow\lib\site-packages\object_detection\metrics\coco_evaluation.py", line 25, in
from object_detection.metrics import coco_tools
File "C:\Users\usr\anaconda3\envs\tensorflow\lib\site-packages\object_detection\metrics\coco_tools.py", line 51, in
from pycocotools import coco
File "C:\Users\usr\anaconda3\envs\tensorflow\lib\site-packages\pycocotools\coco.py", line 56, in
from . import mask as maskUtils
File "C:\Users\usr\anaconda3\envs\tensorflow\lib\site-packages\pycocotools\mask.py", line 3, in
import pycocotools._mask as _mask
File "pycocotools_mask.pyx", line 1, in init pycocotools._mask
ValueError: numpy.ndarray size changed, may indicate binary incompatibility. Expected 88 from C header, got 80 from PyObject

What should I do with this problem?