Explain an example: how layers are embedded in keras

Question

I do not understand the Keras embed layer. Although there are many articles explaining this, I am still confused. For example, the code below is taken from imdb's sentiment analysis:

top_words = 5000
max_review_length = 500
embedding_vecor_length = 32    

model = Sequential()
model.add(Embedding(top_words, embedding_vecor_length, input_length=max_review_length))
model.add(LSTM(100))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
print(model.summary())
model.fit(X_train, y_train, nb_epoch=3, batch_size=64)

In this code, what exactly does the embed layer do? What will be the output embed layer? It would be nice if someone could explain this with some examples, maybe!

Answer 1

An embeddable layer creates embeddings of vectors from input words (I still don’t understand math myself), similar to word2vec or a precalculated glove.

, .

texts = ['This is a text','This is not a text']

, , , .

from keras.preprocessing.text import Tokenizer
from keras.preprocessing.sequence import pad_sequences 
from keras.utils import to_categorical

max_review_length = 6 #maximum length of the sentence
embedding_vecor_length = 3
top_words = 10

#num_words is tne number of unique words in the sequence, if there more top count words are taken
tokenizer = Tokenizer(top_words)
tokenizer.fit_on_texts(texts)
sequences = tokenizer.texts_to_sequences(texts)
word_index = tokenizer.word_index
input_dim = len(word_index) + 1
print('Found %s unique tokens.' % len(word_index))

#max_review_length is the maximum length of the input text so that we can create vector [... 0,0,1,3,50] where 1,3,50 are individual words
data = pad_sequences(sequences, max_review_length)

print('Shape of data tensor:', data.shape)
print(data)

[Out:] 
'This is a text' --> [0 0 1 2 3 4]
'This is not a text' --> [0 1 2 5 3 4]

from keras.models import Sequential
from keras.layers import Embedding

model = Sequential()
model.add(Embedding(top_words, embedding_vecor_length, input_length=max_review_length,mask_zero=True))
model.compile(optimizer='adam', loss='categorical_crossentropy')
output_array = model.predict(data)

output_array (2, 6, 3): 2 , 6 - (max_review_length) 3 - embedding_vecor_length. .

array([[[-0.01494285, -0.007915  ,  0.01764857],
    [-0.01494285, -0.007915  ,  0.01764857],
    [-0.03019481, -0.02910612,  0.03518577],
    [-0.0046863 ,  0.04763055, -0.02629668],
    [ 0.02297204,  0.02146662,  0.03114786],
    [ 0.01634104,  0.02296363, -0.02348827]],

   [[-0.01494285, -0.007915  ,  0.01764857],
    [-0.03019481, -0.02910612,  0.03518577],
    [-0.0046863 ,  0.04763055, -0.02629668],
    [-0.01736645, -0.03719328,  0.02757809],
    [ 0.02297204,  0.02146662,  0.03114786],
    [ 0.01634104,  0.02296363, -0.02348827]]], dtype=float32)

5000 , 500 ( ) 500 32.

, :

model.layers[0].get_weights()

10, 10 , , 0, 1, 2, 3, 4 5 output_array .

[array([[-0.01494285, -0.007915  ,  0.01764857],
    [-0.03019481, -0.02910612,  0.03518577],
    [-0.0046863 ,  0.04763055, -0.02629668],
    [ 0.02297204,  0.02146662,  0.03114786],
    [ 0.01634104,  0.02296363, -0.02348827],
    [-0.01736645, -0.03719328,  0.02757809],
    [ 0.0100757 , -0.03956784,  0.03794377],
    [-0.02672029, -0.00879055, -0.039394  ],
    [-0.00949502, -0.02805768, -0.04179233],
    [ 0.0180716 ,  0.03622523,  0.02232374]], dtype=float32)]

https://stats.stackexchange.com/questions/270546/how-does-keras-embedding-layer-work, , .