error when loading a saved fine tunned model
RafieeAshkan opened this issue · 2 comments
RafieeAshkan commented
Discussed in #1507
Originally posted by RafieeAshkan March 20, 2023
HI,
Thank you for your excellent package. I have fine tuned a roberta model for text classification and saved the fine tuned model. I would like to now load the saved best model and use it for inference. However, I get runtime error as follows:
RuntimeError:
An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.
This probably means that you are not using fork to start your
child processes and you have forgotten to use the proper idiom
in the main module:
if __name__ == '__main__':
freeze_support()
...
The "freeze_support()" line can be omitted if the program
is not going to be frozen to produce an executable.
Here is how I am loading the saved model:
model_path = os.path.join(
"nlp", "classification", "models", "roberta_base", "best_model"
)
model = ClassificationModel("roberta", model_path, use_cuda=True)
preds, outs = model.predict(test_data)
Any help is highly appreciated
luketudge commented
Not sure, but this might be the same as #1375, specifically in this comment. Try the workaround provided there.
RafieeAshkan commented
@luketudge thank you so much, it solved my issue