TypeError: forward_train() missing 1 required positional argument: 'objects'

[Julius-ZCJ]

我在使用faster_rcnn_at_pascalvoc_run.pys的时候出现了这个错误：
Traceback (most recent call last):
File "main.py", line 70, in
tf.app.run()
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/platform/app.py", line 125, in run
_sys.exit(main(argv))
File "main.py", line 51, in main
learner = create_learner(sm_writer, model_helper)
File "/PocketFlow/learners/learner_utils.py", line 56, in create_learner
learner = DisChnPrunedLearner(sm_writer, model_helper)
File "/PocketFlow/learners/discr_channel_pruning/learner.py", line 126, in init
self.__build_train()
File "/PocketFlow/learners/discr_channel_pruning/learner.py", line 203, in __build_train
__ = self.forward_train(images)
TypeError: forward_train() missing 1 required positional argument: 'objects'

我进去查看追踪到这个函数确实有一个‘objects’参数，这个函数在faster_rcnn_at_pascalvoc.py里：
def forward_train(self, inputs, objects, data_format='channels_last'):
"""Forward computation at training."""
inputs_dict = {'inputs': inputs, 'objects': objects}
outputs = forward_fn(inputs_dict, True)
self.vars = slim.get_model_variables()
return outputs

这个形式和基类就是多了一个‘objects’参数：
def forward_train(self, inputs, labels=None):
"""Forward computation at training.

Args:
* inputs: inputs to the network's forward pass
* labels: ground-truth labels

Returns:
* outputs: outputs from the network's forward pass
"""
pass

我该怎么修改这个bug？
还有就是‘objects’的结构是什么样的，我要使用自己的数据是否一定转为pascalvoc的格式，在哪里可以修改读取数据的形式？