AttributeError: ‘Model’ object has no attribute ‘predict_classes’

by

The predict_classes method is only available for the Sequential class (which is the class of your first model) but not for the Model class (the class of your second model).

With the Model class, you can use the predict method which will give you a vector of probabilities and then get the argmax of this vector (with np.argmax(y_pred1,axis=1)).

More Related Contents:

  1. What is an “internal error” and how do I fix it?
  2. Unable to compile Rust hello world on Windows: linker link.exe not found
  3. IntelliJ Idea, run code regardless of errors in unrelated project files
  4. Why does the expression 'a++ += b' give an error?
  5. function returns address of local variable, but it still compile in c, why?
  6. TensorFlow and person recognition in video stream
  7. R cannot be resolved – Android error
  8. Cannot make a static reference to the non-static method
  9. Undefined symbols for architecture i386: _OBJC_CLASS_$_SKPSMTPMessage”, referenced from: error
  10. c++ multiple definitions of a variable
  11. Verifying compatibility in compiling extension types, and using them with cdef
  12. Why do I get “non-static variable this cannot be referenced from a static context”?
  13. Anonymous method in Invoke call
  14. When does keras reset an LSTM state?
  15. Getting gradient of model output w.r.t weights using Keras
  16. Why does C# limit the set of types that can be declared as const?
  17. TypeError: __array__() takes 1 positional argument but 2 were given (Image classification Keras)
  18. Using Gensim Fasttext model with LSTM nn in keras
  19. Standard implementation of vectorize_sequences
  20. Get class labels from Keras functional model
  21. sqrt from math.h causes linker error “undefined reference to sqrt” only when the argument is not a constant
  22. maven “cannot find symbol” message unhelpful
  23. How does Keras handle multilabel classification?
  24. Keras Custom loss function to pass arguments other than y_true and y_pred
  25. How do I create a variable-length input LSTM in Keras?
  26. Unknown initializer: GlorotUniform when loading Keras model
  27. How to view the list of compile errors in IntelliJ?
  28. The bundle’s Info.plist does not contain a CFBundleVersion key or its value is not a string
  29. Can’t get visual studio C++ include file ‘excpt.h’ to get installed
  30. How can I convert a trained Tensorflow model to Keras?

Leave a Comment