How to achieve text after training model

[shamine5]

@gagan3012 I have run the codes in your Trainer.ipynb file

The command in your collab is this

keywords=["ski", "mountain", "sky"]
model.predict(keywords)

But I wouldlike to predict text for the same.

How do I do it after training as you did.

[gagan3012]

Hello,
You also use the pipeline function from K2T.ipynb
Let me know if this helps

[shamine5]

Hi, Thankyou for your reply. But using the pipeline function gives me this error [image: image.png]

…

On Thu, 7 Oct 2021 at 01:20, Gagan Bhatia ***@***.***> wrote: Hello, You also use the pipeline function from K2T.ipynb <https://github.com/gagan3012/keytotext/blob/master/notebooks/K2T.ipynb> Let me know if this helps — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#76 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AQWXH5RUUNYTBYGXZ4ERJELUFSSBTANCNFSM5FL57SYQ> .

[gagan3012]

Sorry the image is not visible

[deduble]

The current problem while trying this is if you used GPU to train the model, you have to use it like so.

keywords=["ski", "mountain", "sky"]
model.predict(keywords, use_gpu=False)

[prak8]

TypeError: Trainer.init() got an unexpected keyword argument 'gpus'
could you explain this error when running this line:
model.train(train_df=train_df, test_df=eval_df, batch_size=4, max_epochs=10, use_gpu= False ,tpu_cores= 8)