size mismatch for classifier about ten_emnlp2020

[AlbertChen1991]

It seems that the errors you have mentioned are caused by loading a wrong saved model. Note that the TEN model is initialized by a TEN-X model, so when you change to another dataset, you should not only change the args['data_dir'] argument, but also the args['resume'] argument which indicates the directory where the TEN-X model is saved. Maybe you have loaded a TEN-X model on the DSTC2 dataset when you train a TEN model on the WOZ dataset, which leads to the mismatching of parameter dimensions in your created model and loaded model.

[asifdadra]

Actually, i am just training TEN-X model, i did not went to TEN. By default in config file the args['resume'] is none for Ten-X. you are right that when i changed dataset then it was loading the last saved model from directory which might be causing to lead mismatching dimensions parameters. now i have just changed the directory from TEN-X to TEN-X/woz for woz dataset in root experimental folder i.e. args ['dexp']. its now training and working. thank you.