ValueError: Shape (2, 56, 56, 1024) must have rank 0

 ###### 问题遇到的现象和发生背景
我最近在复现TALL论文，遇到了valueError
原作者给的code 使用的python2以及tensorflow1.*
我是python3和tensorflow2.0
数据集也是和论文一致的
 ###### 问题相关代码，请勿粘贴截图

 ###### 运行结果及报错内容

Traceback (most recent call last):
  File "/home/yinmengran/TALL-master/TALL-master/main.py", line 193, in <module>
    tf.app.run()
  File "/home/yinmengran/miniconda3/envs/tensorflow/lib/python3.7/site-packages/tensorflow_core/python/platform/app.py", line 40, in run
    _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
  File "/home/yinmengran/miniconda3/envs/tensorflow/lib/python3.7/site-packages/absl/app.py", line 312, in run
    _run_main(main, args)
  File "/home/yinmengran/miniconda3/envs/tensorflow/lib/python3.7/site-packages/absl/app.py", line 258, in _run_main
    sys.exit(main(argv))
  File "/home/yinmengran/TALL-master/TALL-master/main.py", line 189, in main
    run_training()
  File "/home/yinmengran/TALL-master/TALL-master/main.py", line 166, in run_training
    loss_align_reg, vs_train_op, vs_eval_op, offset_pred, loss_reg = model.construct_model()
  File "/home/yinmengran/TALL-master/TALL-master/ctrl_model.py", line 167, in construct_model
    sim_reg_mat, sim_reg_mat_test = self.visual_semantic_infer(self.visual_featmap_ph_train, self.sentence_ph_train, self.visual_featmap_ph_test, self.sentence_ph_test)
  File "/home/yinmengran/TALL-master/TALL-master/ctrl_model.py", line 78, in visual_semantic_infer
    cross_modal_vec_train = self.cross_modal_comb(transformed_clip_train_norm, transformed_sentence_train_norm, self.batch_size)
  File "/home/yinmengran/TALL-master/TALL-master/ctrl_model.py", line 59, in cross_modal_comb
    concat_feature = tf.reshape(tf.concat(2,[vv_feature, ss_feature]),[batch_size, batch_size, self.semantic_size+self.semantic_size])
  File "/home/yinmengran/miniconda3/envs/tensorflow/lib/python3.7/site-packages/tensorflow_core/python/util/dispatch.py", line 180, in wrapper
    return target(*args, **kwargs)
  File "/home/yinmengran/miniconda3/envs/tensorflow/lib/python3.7/site-packages/tensorflow_core/python/ops/array_ops.py", line 1515, in concat
    dtype=dtypes.int32).get_shape().assert_has_rank(0)
  File "/home/yinmengran/miniconda3/envs/tensorflow/lib/python3.7/site-packages/tensorflow_core/python/framework/tensor_shape.py", line 990, in assert_has_rank
    raise ValueError("Shape %s must have rank %d" % (self, rank))
ValueError: Shape (2, 56, 56, 1024) must have rank 0

 ###### 我的解答思路和尝试过的方法
感觉是向量维数不对，是导入的数据集有问题吗？
或者是引文版本的问题？
 ###### 我想要达到的结果