train.py

The following error occurred while running train.py. Can anyone give me some advice?

Traceback (most recent call last):
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 2084, in cond
nest.assert_same_structure(orig_res_t, orig_res_f)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/util/nest.py", line 183, in assert_same_structure
_pywrap_tensorflow.AssertSameStructure(nest1, nest2, check_types)
ValueError: The two structures don't have the same nested structure.

First structure: type=tuple str=([800, 600, 700, 900, 1000, 1100, 1200], )

Second structure: type=tuple str=(, [800, 600, 700, 900, 1000, 1100, 1200])

More specifically: Substructure "type=list str=[800, 600, 700, 900, 1000, 1100, 1200]" is a sequence, while substructure "type=Tensor str=Tensor("get_batch/cond/floordiv_1:0", shape=(7,), dtype=int32)" is not

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/media/ys/000F3E52000A91C0/zheng/R2CNN-Plus-Plus_Tensorflow-master (2)/tools/train.py", line 230, in
train()
File "/media/ys/000F3E52000A91C0/zheng/R2CNN-Plus-Plus_Tensorflow-master (2)/tools/train.py", line 37, in train
is_training=True)
File "/media/ys/000F3E52000A91C0/zheng/R2CNN-Plus-Plus_Tensorflow-master (2)/data/io/read_tfrecord.py", line 87, in next_batch
is_training=is_training)
File "/media/ys/000F3E52000A91C0/zheng/R2CNN-Plus-Plus_Tensorflow-master (2)/data/io/read_tfrecord.py", line 61, in read_and_prepocess_single_img
target_shortside_len=shortside_len)
File "/media/ys/000F3E52000A91C0/zheng/R2CNN-Plus-Plus_Tensorflow-master (2)/data/io/image_preprocess.py", line 24, in short_side_resize
false_fn=lambda: (target_shortside_len * h//w, target_shortside_len))
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/util/deprecation.py", line 432, in new_func
return func(*args, **kwargs)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 2090, in cond
"Incompatible return values of true_fn and false_fn: {}".format(e))
ValueError: Incompatible return values of true_fn and false_fn: The two structures don't have the same nested structure.

First structure: type=tuple str=([800, 600, 700, 900, 1000, 1100, 1200], )

Second structure: type=tuple str=(, [800, 600, 700, 900, 1000, 1100, 1200])

More specifically: Substructure "type=list str=[800, 600, 700, 900, 1000, 1100, 1200]" is a sequence, while substructure "type=Tensor str=Tensor("get_batch/cond/floordiv_1:0", shape=(7,), dtype=int32)" is not