PRATIK C

How to visulaize attention weight in output?

> You would be much better off using LIT for this task, as opposed to WIT. https://pair-code.github.io/lit/ > > LIT has built-in support for most NLP analysis tasks, including attention...

> Leverage the "inference_on" parameter, and updated it to make it more intuitive now for multi-GPU usage. -1 is reserved for CPU and ```0 through 998 is reserved for GPUs``....

> > Leverage the "inference_on" parameter, and updated it to make it more intuitive now for multi-GPU usage. -1 is reserved for CPU and ```0 through 998 is reserved for...

What is n_splits=2, order=2?

@bmreiniger any help.

> The converter for OneVsOneClassifier has not been implemented yet. It should not be too complicated to do. In the meantime, OneVsRestClassifier has a converter. But in the document OneVsOneClassifier...

Hi @xadupre any help on this?

> @pratikchhapolika I'm working on this converter now. Can you please share me some of your data (X_train, y_train, X_test, y_test, etc.) so I can do a fully testing? sure....

> @pratikchhapolika I'm working on this converter now. Can you please share me some of your data (X_train, y_train, X_test, y_test, etc.) so I can do a fully testing? @xiaowuhu...