AttributeError: 'Model' object has no attribute 'epoch' - Keras

user_4555441 0
Viewed 3303

I huild an auto encoder in keras following steps given in a simple autoencoder based on a fully-connected layer (https://blog.keras.io/building-autoencoders-in-keras.html) 

wiki_autoencoder.fit(wiki_train, wiki_train,
                epochs=100,
                batch_size=256,
                shuffle=True,
                validation_data=(wiki_test, wiki_test))

After training and cross vaidation. plotting the results gives me error given below:

    loss = wiki_autoencoder.history.history['loss']
    val_loss = wiki_autoencoder.history.history['val_loss']
    epochs = range(epochs)
    plt.figure()
    plt.plot(epochs, loss, 'bo', label='Training loss')
    plt.plot(epochs, val_loss, 'b', label='Validation loss')
    plt.title('Training and validation loss')
    plt.legend()
    plt.show()


NameError                                 Traceback (most recent call last)
<ipython-input-32-6acdd795daf3> in <module>()
      1 loss = wiki_autoencoder.history.history['loss']
      2 val_loss = wiki_autoencoder.history.history['val_loss']
----> 3 epochs = range(epochs)
      4 plt.figure()
      5 plt.plot(epochs, loss, 'bo', label='Training loss')

NameError: name 'epochs' is not defined

The second thing i tried gives be result : No handles with labels found to put in legend. however plot is generated. how do i solve this problem

enter image description here

plt.plot(wiki_autoencoder.history.history['val_loss'], 'r', wiki_autoencoder.history.history['loss'], 'bo')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.title('Training and validation loss')
plt.legend()
plt.show()
keras tensorflow attributeerror matplotlib python
2 Answers

You need to define range properly as epochs is not defined which you used inside range(). You can use any other number apart from 100 depending on your requirement.

epochs = range(100)
user_89303950

You can actually find epochs from history object.

epochs = wiki_autoencoder.history.epoch

This will give you the epochs for which the model was trained.

user_58259530
Related