TypeError: 'numpy.float64' object cannot be interpreted as an integer during evaluation about table-transformer HOT 2 CLOSED

(env)$ python main.py --data_type detection --config_file detection_config.json --data_root_dir ~/../pubtables/PubTables1M-Detection-PASCAL-VOC/ 
Traceback (most recent call last):
  File "/home/lxyuan/playground/table-transformer/src/main.py", line 16, in <module>
    from engine import evaluate, train_one_epoch
  File "/home/lxyuan/playground/table-transformer/src/../detr/engine.py", line 13, in <module>
    from datasets.coco_eval import CocoEvaluator
  File "/home/lxyuan/playground/table-transformer/src/../detr/datasets/__init__.py", line 5, in <module>
    from .coco import build as build_coco
  File "/home/lxyuan/playground/table-transformer/src/../detr/datasets/coco.py", line 12, in <module>
    from pycocotools import mask as coco_mask
  File "/home/lxyuan/playground/table-transformer/env/lib64/python3.9/site-packages/pycocotools/mask.py", line 3, in <module>
    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 96 from C header, got 80 from PyObject