In the notebook _sagemaker_predictivemaintenance.ipynb there is one place which explained how to interpret the inference result. That said "The predictions are a fraction of MAX_RUL which is 130.0, therefore the Remaining Useful Life predictions can be obtained by multiplying the output with 130". This is wrong.
By checking the code in entry_point.py, we know that the label divided 300 in training, and thus we need to multiply 300 to get it back, instead of multiply 130.
In the notebook _sagemaker_predictivemaintenance.ipynb there is one place which explained how to interpret the inference result. That said "The predictions are a fraction of MAX_RUL which is 130.0, therefore the Remaining Useful Life predictions can be obtained by multiplying the output with 130". This is wrong.
By checking the code in entry_point.py, we know that the label divided 300 in training, and thus we need to multiply 300 to get it back, instead of multiply 130.