0

I am trying to save my Rf model after training it and I get a "Segmentation fault (core dumped)". I have tried to save it before training and it does not give me any problem with pickle. I have tried with other cuML algorithms, and it has let me save them after training.

from cuml.ensemble  import  RandomForestClassifier as rf_cuML
import pickle

model = rf_cuML(random_state=0)
output = open('model.pkl', 'wb')
pickle.dump(model, output) #This saving works

model.fit(train_features, train_labels)
output = open('model_trained.pkl', 'wb')
pickle.dump(model, output) #This saving does not work

This line throws the following error: pickle.dump(model, output) #This saving does not work --> Segmentation fault (core dumped)

System specifications:

  1. Ubuntu 18.04
  2. RAM 32GB
  3. NVIDIA-SMI 495.29.05 Driver Version: 495.29.05 CUDA Version: 11.5[Cuda info][1] [1]: https://i.stack.imgur.com/8reIM.png
  4. Rapids 22.04
  5. Python 3.9
  6. CPU: Intel Core i7-7700
  7. GPU: NVIDIA GeForce RTX 2080 SUPER 8 GB
  8. pickle 4.0
Alberto Gutiérrez
  • 1
  • 1

1 Answers1

0

SOLVED

After some research, I updated the rapids version to 22.06 and it now allows me to save the trained Random Forest model with pickle.

Alberto Gutiérrez
  • 1
  • 1
  • Your answer could be improved with additional supporting information. Please [edit] to add further details, such as citations or documentation, so that others can confirm that your answer is correct. You can find more information on how to write good answers [in the help center](/help/how-to-answer). – Community Jul 23 '22 at 05:44