do you know how to train crosswoz dataset in tutorial

[weizhenzhao]

I follow the instructions in the tutorial, and change the dataset to crosswoz. but it always return the following result. 抱歉,没有查到符合条件的餐馆信息,你看可以吗?

Load actions from file.. Dimension of system actions: 89 Dimension of user actions: 81 State dimension: 232 Load actions from file.. Dimension of system actions: 89 Dimension of user actions: 81 State dimension: 232 Load actions from file.. Dimension of system actions: 89 Dimension of user actions: 81 State dimension: 232 WARNING:root:nlu info_dict is not initialized WARNING:root:dst info_dict is not initialized WARNING:root:nlg info_dict is not initialized [['Inform', '餐馆', '人均消费', '50-100元'], ['Request', '餐馆', '名称', '']] {'belief_state': {'餐馆': {'人均消费': '50-100元'}}, 'booked': {}, 'history': [['sys', 'null'], ['user', '帮我推荐一个人均消费在50-100元的餐馆']], 'system_action': [], 'user_action': [['Inform', '餐馆', '人均消费', '50-100元'], ['Request', '餐馆', '名称', '']], 'terminated': False} [['NoOffer', '餐馆', 'none', 'none']] 抱歉,没有查到符合条件的餐馆信息,你看可以吗? 抱歉,没有查到符合条件的餐馆信息,你看可以吗?

Process finished with exit code 0

I think it's fail to run If anyone can help . thanks very much

[zqwerty]

See https://github.com/ConvLab/ConvLab-3/issues/116#issuecomment-1380365310

We will fix it after ACL submission ddl.

[ChrisGeishauser]

I updated to code to use crosswoz with DDPT, but i did not check properly if supervised training works. You can try it using

python convlab/policy/vtrace_DPT/supervised/train_supervised.py --dataset_name=crosswoz

[lowpair]

@weizhenzhao Can you run normally after the latest update?

[weizhenzhao]

I've tried the change. but there's still something wrong here. it see's that after preprocessing . the data in the action list is all zero. and It went wrong in that line

[ChrisGeishauser]

Hey @weizhenzhao ! Thanks a lot for pointing me towards that. The issue was that the intents in crosswoz were upper-case and then it couldn't match the lowercase one in the action dictionary. I changed one line (and pushed the change to master) and for me it now minimizes the loss. Please let me know if you face more issues then!

[dyy401453043]

face problem when i run the code in crosswoz like https://github.com/ConvLab/ConvLab-3/issues/120#issue-1537141658.