CODEWITHSUNDEEP
pythonkerasmodel
Tommy
Tommy

Reputation: 51

TypeError: The added layer must be an instance of class Layer. Found: <tensorflow.python.keras.layers.recurrent.LSTM object at 0x00000272F295E508>

I am about the train a modell with LSTM, but I am receiving this error message:

TypeError: The added layer must be an instance of class Layer. Found: <tensorflow.python.keras.layers.recurrent.LSTM object at 0x00000272F295E508>

I've seen that some other people had the same problem but none of their solutions worked for me. I need quick help because my deadline is almost over.

Please help!

Here my imports:

import pandas as pd
import os
from os import walk
from os.path import join
import numpy as np
import re
from numpy import array
from numpy import asarray
from numpy import zeros




import nltk
from nltk.stem import PorterStemmer
from nltk.stem import SnowballStemmer
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize


from tensorflow.keras import models
from keras.preprocessing.text import one_hot
from keras.preprocessing.sequence import pad_sequences
from keras.models import Sequential
from keras.layers.core import Activation, Dropout, Dense
from keras.layers import Flatten
from keras.layers import GlobalMaxPooling1D
from keras.layers.embeddings import Embedding
from sklearn.model_selection import train_test_split
from keras.preprocessing.text import Tokenizer


import matplotlib.pyplot as plt

And here my code:

model = Sequential()
embedding_layer = Embedding(vocab_size, 100, weights=[embedding_matrix], input_length=maxlen , trainable=False)
model.add(embedding_layer)
model.add(LSTM(128))

model.add(Dense(1, activation='sigmoid'))
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['acc'])

The error-message:

TypeError                                 Traceback (most recent call last)
<ipython-input-501-6005bb036887> in <module>
      2 embedding_layer = Embedding(vocab_size, 100, weights=[embedding_matrix], input_length=maxlen , trainable=False)
      3 model.add(embedding_layer)
----> 4 model.add(LSTM(128))
      5 
      6 model.add(Dense(1, activation='sigmoid'))

~\Anaconda3\lib\site-packages\keras\engine\sequential.py in add(self, layer)
    131             raise TypeError('The added layer must be '
    132                             'an instance of class Layer. '
--> 133                             'Found: ' + str(layer))
    134         self.built = False
    135         if not self._layers:

TypeError: The added layer must be an instance of class Layer. Found: <tensorflow.python.keras.layers.recurrent.LSTM object at 0x00000272F295E508>

Please help me!

Upvotes: 0

Views: 2549

Answers (2)

Muhammad Fayzan
Muhammad Fayzan

Reputation: 91

similary problem is solved by following:

   from tensorflow.keras.layers import LSTM

Upvotes: -1

Bashir Kazimi
Bashir Kazimi

Reputation: 1377

You are importing other layers and your Sequential model from keras directly, but from the error, it is understood that your LSTM layer is imported from tensorflow.keras.layers instead of keras.layers. Import all layers from one, either keras or tensorflow and the error would be gone.

Upvotes: 2

Related Questions