AttributeError: object has no attribute '_output_tensor_cache'

Question

I'm trying to do a sentiment analysis classifier based on the rotten tomatoes dataset. I'm getting this error:

AttributeError: 'RNN' object has no attribute '_output_tensor_cache'

Unfortunately, there isn't help anywhere. I have no idea where to even look.

import pandas as pd
from sklearn.model_selection import train_test_split
from tensorflow import keras
from keras import Model
from tensorflow.keras.layers import LSTM, Embedding, Dense
import os
os.chdir('/home/nicolas/Documents/datasets')

df = pd.read_csv('rotten_tomatoes_reviews.csv', nrows=50_000)

df = df.loc[df.Review.str.len() >= 3]

array = df.Review.values
target = df.Freshness.values

tokenizer = keras.preprocessing.text.Tokenizer(num_words=3_000)

tokenizer.fit_on_texts(array)
vector = tokenizer.texts_to_sequences(array)

padded = keras.preprocessing.sequence.pad_sequences(vector, maxlen=40)

X_train, X_test, y_train, y_test = train_test_split(padded, target, test_size=2e-1)


class RNN(Model):
    def __init__(self):
        super(RNN, self).__init__()
        self.rnn1 = LSTM(8, return_sequences=True, return_state=True)
        self.rnn2 = LSTM(8)
        self.emb1 = Embedding(input_dim=3_000, output_dim=50, input_length=40)
        self.flc1 = Dense(2)

    def __call__(self, inputs, training=None, mask=None):
        x = self.emb1(inputs)
        x = self.rnn1(x)
        x = self.rnn2(x)
        out = self.flc1(x)
        print(out.shape)
        return out


def main():
    model = RNN()

    model.compile(optimizer=keras.optimizers.Adam(0.001),
                  loss=keras.losses.BinaryCrossentropy(from_logits=True),
                  metrics=['accuracy'])

    model.fit(X_train, y_train, batch_size=16, epochs=10,
              validation_data=[X_test, y_test], verbose=1)

    scores = model.evaluate(X_test, y_test, batch_size=16, verbose=1)
    print("Final test loss and accuracy :", scores)


if __name__ == '__main__':
    main()

today · Accepted Answer · 2020-04-14 16:43:40Z

1

That's because you are mixing native Keras implementation and TensorFlow implementation of Keras (i.e. tf.keras):

from tensorflow import keras
from keras import Model     # Wrong! DON'T mix keras and tf.keras!
from tensorflow.keras.layers import LSTM, Embedding, Dense

You should never do that. Fix the import for Model class by using: from tensorflow.keras import Model

answered Apr 14, 2020 at 16:43

today

33.6k8 gold badges100 silver badges122 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

AttributeError: object has no attribute '_output_tensor_cache'

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related