2/18/24, 3:28 PM LSTMImplementation.
ipynb - Colaboratory
The following steps are taken in the program:
1) Import necessary libraries.
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import LSTM, Dense, Embedding
from tensorflow.keras.datasets import imdb
from tensorflow.keras.preprocessing import sequence
2) Load and prepare the IMDB dataset.
max_features = 10000 # Number of words to consider as features
maxlen = 500 # Cut texts after this number of words
print("Loading data...")
(input_train, y_train), (input_test, y_test) = imdb.load_data(num_words=max_features)
print(len(input_train), "train sequences")
print(len(input_test), "test sequences")
print("Pad sequences (samples x time)")
input_train = sequence.pad_sequences(input_train, maxlen=maxlen)
input_test = sequence.pad_sequences(input_test, maxlen=maxlen)
print("input_train shape:", input_train.shape)
print("input_test shape:", input_test.shape)
Loading data...
Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/imdb.npz
17464789/17464789 [==============================] - 1s 0us/step
25000 train sequences
25000 test sequences
Pad sequences (samples x time)
input_train shape: (25000, 500)
input_test shape: (25000, 500)
3) Define the model.
model = Sequential()
model.add(Embedding(max_features, 32))
model.add(LSTM(32))
model.add(Dense(1, activation='sigmoid'))
4) Compile the model.
model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['acc'])
5) Train the model.
history = model.fit(input_train, y_train,
epochs=10,
batch_size=128,
validation_split=0.2)
output Epoch 1/10
157/157 [==============================] - 57s 347ms/step - loss: 0.6067 - acc: 0.6564 - val_loss: 0.5497 - val_acc: 0.7200
Epoch 2/10
157/157 [==============================] - 51s 327ms/step - loss: 0.3575 - acc: 0.8517 - val_loss: 0.4184 - val_acc: 0.8042
Epoch 3/10
157/157 [==============================] - 52s 332ms/step - loss: 0.2714 - acc: 0.8957 - val_loss: 0.4682 - val_acc: 0.8214
Epoch 4/10
157/157 [==============================] - 52s 332ms/step - loss: 0.2313 - acc: 0.9123 - val_loss: 0.2921 - val_acc: 0.8858
Epoch 5/10
157/157 [==============================] - 52s 332ms/step - loss: 0.2017 - acc: 0.9245 - val_loss: 0.3899 - val_acc: 0.8634
Epoch 6/10
157/157 [==============================] - 50s 321ms/step - loss: 0.1854 - acc: 0.9326 - val_loss: 0.3171 - val_acc: 0.8656
Epoch 7/10
https://colab.research.google.com/drive/1WAKC0xvBPIn5czAhLmLi5d_al0YTJV3w#scrollTo=TEsONDH_2G6E&printMode=true 1/2
2/18/24, 3:28 PM LSTMImplementation.ipynb - Colaboratory
157/157 [==============================] - 52s 329ms/step - loss: 0.1660 - acc: 0.9398 - val_loss: 0.3038 - val_acc: 0.8798
Epoch 8/10
157/157 [==============================] - 51s 323ms/step - loss: 0.1494 - acc: 0.9483 - val_loss: 0.3052 - val_acc: 0.8770
Epoch 9/10
157/157 [==============================] - 51s 328ms/step - loss: 0.1390 - acc: 0.9518 - val_loss: 0.4212 - val_acc: 0.8686
Epoch 10/10
157/157 [==============================] - 52s 334ms/step - loss: 0.1275 - acc: 0.9557 - val_loss: 0.3880 - val_acc: 0.8438
6) Evaluate the model.
evaluation = model.evaluate(input_test, y_test)
print(f'Test Loss: {evaluation[0]} - Test Accuracy: {evaluation[1]}')
782/782 [==============================] - 34s 43ms/step - loss: 0.4023 - acc: 0.8432
Test Loss: 0.40225595235824585 - Test Accuracy: 0.8432000279426575
https://colab.research.google.com/drive/1WAKC0xvBPIn5czAhLmLi5d_al0YTJV3w#scrollTo=TEsONDH_2G6E&printMode=true 2/2
