Error when training object detection model

I am using Ubuntu 18.04.2 on Win10.
I am trying to train the model but encountered this error.

File "/home/xqz5222/.local/lib/python2.7/site-packages/tensorflow/python/training/session_manager.py", line 220, in _restore_checkpoint
saver.restore(sess, ckpt.model_checkpoint_path)
File "/home/xqz5222/.local/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1302, in restore
err, "a Variable name or other graph key that is missing")
tensorflow.python.framework.errors_impl.NotFoundError: Restoring from checkpoint failed. This is most likely due to a Variable name or other graph key that is missing from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:

Key FirstStageFeatureExtractor/resnet_v1_101/block1/unit_1/bottleneck_v1/conv1/BatchNorm/beta not found in checkpoint
[[node save/RestoreV2 (defined at /home/xqz5222/tensorflow/models/research/object_detection/model_lib.py:518) ]]

Original stack trace for u'save/RestoreV2':
File "object_detection/model_main.py", line 109, in
tf.app.run()

This is the script that I used to train the model.

PIPELINE_CONFIG_PATH=object_detection/images/ssd_mobilenet_v2_coco.config
MODEL_DIR=object_detection/images
NUM_TRAIN_STEPS=20000
SAMPLE_1_OF_N_EVAL_EXAMPLES=1
python object_detection/model_main.py
--pipeline_config_path=${PIPELINE_CONFIG_PATH}
--model_dir=${MODEL_DIR}
--num_train_steps=${NUM_TRAIN_STEPS}
--sample_1_of_n_eval_examples=$SAMPLE_1_OF_N_EVAL_EXAMPLES
--alsologtostderr

Thank you in advance!