How to add Bi directional LSTM layer to keras model?
This recipe helps you add Bi directional LSTM layer to keras model
Recipe Objective
Adding Bi directional LSTM layer to keras model
Bi-directional LSTMs is an extension of LSTM, can improve the working of the model on sequence classification problems.
Table of Contents
Step 1- Importing Libraries
from keras.layers import Bidirectional
from tensorflow import keras
from keras.models import Sequential
from keras.layers import LSTM
from keras.layers import Activation, Dense
import numpy as np
Step 2- Create a neural network model.
adding a Bidirectional layer.
model = Sequential()
model.add(Bidirectional(LSTM(32, return_sequences=True), input_shape=(5, 10)))
model.add(Bidirectional(LSTM(32)))
model.add(Activation('relu'))
model.compile(loss='categorical_crossentropy', optimizer='Adam')
Step-3 Create a sample model and make prediction from it.
y = np.array([1, 2, 3, 4, 5, 6, 7, 8, 9, 10]).reshape((1,1,10))
# make and show prediction
print(model.predict(y))
[[0.02718286 0.02762156 0.02089063 0.01052572 0.06378494 0.01932984
0. 0. 0.06944765 0.01507997 0. 0.
0.05792578 0.04587546 0. 0.01098552 0.04473235 0.06602424
0. 0. 0. 0.01608978 0. 0.
0.03304935 0. 0.05253785 0.04292118 0.10207159 0.07474144
0. 0.01693208 0.06157123 0.02414081 0.05233147 0.03505142
0.03542253 0.01108169 0.01113066 0. 0. 0.05232322
0. 0.10277228 0.02966982 0. 0. 0.
0.03759805 0. 0. 0.01015551 0.08046164 0.
0. 0.00290035 0. 0.02540161 0. 0.
0.05021353 0. 0.03642806 0. ]]
What Users are saying..
Ameeruddin Mohammed
I come from a background in Marketing and Analytics and when I developed an interest in Machine Learning algorithms, I did multiple in-class courses from reputed institutions though I got good... Read More