-
Notifications
You must be signed in to change notification settings - Fork 46
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Error loading Model #2
Comments
Although the program includes model file and can load it, can't work in the process of predict. You need save "FeatureVectorizer" variable during training your model. When you want to predict test data, loading the matrix variable into memory is necessary for the next stage, then,using your model and the matrix variable can be effective. |
Hi, can you elaborate on how to use the saved model and how to save and load "FeatureVectorizer" variable on new test apks? Many thanks in advance. |
When i have to create a model for the first time there are no problem.
After the creation, i use the tool with the --model option (also with malware and benign apk parameters), but after:
SVMModels = load(Model)
Gives me an error in:
BestModel= SVMModels.best_estimator
Ok, i modify it as:
BestModel= SVMModels.best_estimator_
and it works great, but the next predict doesn't work:y_pred = SVMModels.predict(x_test)
Should i retrain the model after loading, before predict? If yes, why you didn't do it...
The text was updated successfully, but these errors were encountered: