how can i retrain pretrainmodel

[suven2019]

No description provided.

[suven2019]

Traceback (most recent call last):
File "train.py", line 78, in
main(config, args.resume)
File "train.py", line 50, in main
toolbox = Toolbox)
File "/home/sw2/FOTS.PyTorch-master/FOTS/trainer/trainer.py", line 19, in init
super(Trainer, self).init(model, loss, metrics, resume, config, train_logger)
File "/home/sw2/FOTS.PyTorch-master/FOTS/base/base_trainer.py", line 70, in init
self._resume_checkpoint(resume)
File "/home/sw2/FOTS.PyTorch-master/FOTS/base/base_trainer.py", line 175, in _resume_checkpoint
self.model.load_state_dict(checkpoint['state_dict'])
File "/home/sw2/FOTS.PyTorch-master/FOTS/model/model.py", line 75, in load_state_dict
self.sharedConv.load_state_dict(sd['0'])
File "/home/sw2/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 830, in load_state_dict
self.class.name, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for SharedConv: