bdbc-kg-nlp / ten_emnlp2020 Goto Github PK

Hello, First I would like to appreciate your work in the Domain of DST that you have been done great in TEN article. I am working on your proposed model to understand the code according to published article. I am able to reproduce results on DSTC2 dataset but when i change dataset from DSTC2 to Woz or Multiwoz in config.py , then i am getting the following error:
File "/home/asifdadra/Downloads/enter/envs/ttp37/lib/python3.7/site-packages/torch/nn/modules/module.py", line 847, in load_state_dict
self.class.name, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for Model:
size mismatch for emb_fixed.weight: copying a param with shape torch.Size([1621, 400]) from checkpoint, the shape in current model is torch.Size([950, 400]).
size mismatch for classifier.area.weight: copying a param with shape torch.Size([7, 50]) from checkpoint, the shape in current model is torch.Size([8, 50]).
size mismatch for classifier.area.bias: copying a param with shape torch.Size([7]) from checkpoint, the shape in current model is torch.Size([8]).
size mismatch for classifier.food.weight: copying a param with shape torch.Size([76, 50]) from checkpoint, the shape in current model is torch.Size([77, 50]).
size mismatch for classifier.food.bias: copying a param with shape torch.Size([76]) from checkpoint, the shape in current model is torch.Size([77]).

Process finished with exit code 1

Could you please provide your feedback to resolve this. Thank You.