TRAIN THE MODEL WITH EMBEDDING AND SIMPLE RNN LAYERS

PROGRAM:

import tensorflow as tf

from tensorflow.keras.datasets import imdb

from tensorflow.keras.preprocessing.sequence import pad_sequences

from tensorflow.keras.models import Sequential

from tensorflow.keras.layers import Embedding, SimpleRNN, Dense

# Parameters

vocab_size = 10000 # Only consider the top 10,000 words

maxlen = 500 # Only consider the first 500 words of each review

embedding_dim = 32 # Dimension of the embedding vector

# Load the IMDB dataset

(x_train, y_train), (x_test, y_test) = imdb.load_data(num_words=vocab_size)

# Pad sequences to ensure uniform input size

x_train = pad_sequences(x_train, maxlen=maxlen)

x_test = pad_sequences(x_test, maxlen=maxlen)

# Build the model

model = Sequential()

model.add(Embedding(input_dim=vocab_size, output_dim=embedding_dim,
input_length=maxlen))

model.add(SimpleRNN(100)) # SimpleRNN layer with 100 units

model.add(Dense(1, activation='sigmoid'))

# Compile the model

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

# Print the model summary

model.summary()

# Train the model

model.fit(x_train, y_train, epochs=3, batch_size=64, validation_split=0.2)

# Evaluate the model

loss, accuracy = model.evaluate(x_test, y_test)

print(f"Test Loss: {loss}")

print(f"Test Accuracy: {accuracy}")

OUTPUT:

/usr/local/lib/python3.10/dist-packages/keras/src/layers/core/embedding.py:90:
UserWarning: Argument `input_length` is deprecated. Just remove it.

warnings.warn(
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━
━━━━┓
┃ Layer (type) ┃ Output Shape ┃
Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━
━━━━┩
│ embedding (Embedding) │ ? │ 0
(unbuilt) │
├──────────────────────────────────────┼─────────────────────────────┼─────────────
────┤
│ simple_rnn (SimpleRNN) │ ? │ 0
(unbuilt) │
├──────────────────────────────────────┼─────────────────────────────┼─────────────
────┤
│ dense (Dense) │ ? │ 0
(unbuilt) │
└──────────────────────────────────────┴─────────────────────────────┴─────────────
────┘
Total params: 0 (0.00 B)

Trainable params: 0 (0.00 B)

Non-trainable params: 0 (0.00 B)

Epoch 1/3

313/313 ━━━━━━━━━━━━━━━━━━━━ 84s 260ms/step - accuracy: 0.5576 - loss: 0.6773 -

val_accuracy: 0.8082 - val_loss: 0.4277

Epoch 2/3

313/313 ━━━━━━━━━━━━━━━━━━━━ 75s 237ms/step - accuracy: 0.7789 - loss: 0.5334 -

val_accuracy: 0.7218 - val_loss: 0.5456

Epoch 3/3

313/313 ━━━━━━━━━━━━━━━━━━━━ 82s 239ms/step - accuracy: 0.7633 - loss: 0.5021 -

val_accuracy: 0.7026 - val_loss: 0.5642

782/782 ━━━━━━━━━━━━━━━━━━━━ 37s 47ms/step - accuracy: 0.7066 - loss: 0.5609

Test Loss: 0.5561356544494629

Test Accuracy: 0.7092000246047974

 PLOTTING THE RESULTS

PROGRAM:

import tensorflow as tf

from tensorflow.keras.datasets import imdb

from tensorflow.keras.preprocessing.sequence import pad_sequences

from tensorflow.keras.models import Sequential

from tensorflow.keras.layers import Embedding, SimpleRNN, Dense

import matplotlib.pyplot as plt

# Parameters

vocab_size = 10000 # Only consider the top 10,000 words

maxlen = 500 # Only consider the first 500 words of each review

embedding_dim = 32 # Dimension of the embedding vector

# Load the IMDB dataset

(x_train, y_train), (x_test, y_test) = imdb.load_data(num_words=vocab_size)

# Pad sequences to ensure uniform input size

x_train = pad_sequences(x_train, maxlen=maxlen)

x_test = pad_sequences(x_test, maxlen=maxlen)

# Build the model

model = Sequential()

model.add(Embedding(input_dim=vocab_size, output_dim=embedding_dim,
input_length=maxlen))

model.add(SimpleRNN(100)) # SimpleRNN layer with 100 units

model.add(Dense(1, activation='sigmoid'))

# Compile the model

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

# Print the model summary

model.summary()

# Train the model

history = model.fit(x_train, y_train, epochs=3, batch_size=64, validation_split=0.2)

# Evaluate the model

loss, accuracy = model.evaluate(x_test, y_test)

print(f"Test Loss: {loss}")

print(f"Test Accuracy: {accuracy}")

# Plot the training and validation loss and accuracy

plt.figure(figsize=(12, 4))

# Plot training & validation accuracy values

plt.subplot(1, 2, 1)

plt.plot(history.history['accuracy'], label='Train Accuracy')

plt.plot(history.history['val_accuracy'], label='Validation Accuracy')

plt.title('Model Accuracy')

plt.xlabel('Epoch')

plt.ylabel('Accuracy')

plt.legend(loc='upper left')

# Plot training & validation loss values

plt.subplot(1, 2, 2)

plt.plot(history.history['loss'], label='Train Loss')

plt.plot(history.history['val_loss'], label='Validation Loss')

plt.title('Model Loss')

plt.xlabel('Epoch')

plt.ylabel('Loss')

plt.legend(loc='upper left')

plt.tight_layout()

plt.show()
OUTPUT:

Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-

datasets/imdb.npz

17464789/17464789 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step

/usr/local/lib/python3.10/dist-packages/keras/src/layers/core/embedding.py:90:
UserWarning: Argument `input_length` is deprecated. Just remove it warnings.warn(

Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━
━━━━┓
┃ Layer (type) ┃ Output Shape ┃
Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━
━━━━┩
│ embedding (Embedding) │ ? │ 0
(unbuilt) │
├──────────────────────────────────────┼─────────────────────────────┼─────────────
────┤
│ simple_rnn (SimpleRNN) │ ? │ 0
(unbuilt) │
├──────────────────────────────────────┼─────────────────────────────┼─────────────
────┤
│ dense (Dense) │ ? │ 0
(unbuilt) │
└──────────────────────────────────────┴─────────────────────────────┴─────────────
────┘
Total params: 0 (0.00 B)

Trainable params: 0 (0.00 B)

Non-trainable params: 0 (0.00 B)

Epoch 1/3

313/313 ━━━━━━━━━━━━━━━━━━━━ 67s 207ms/step - accuracy: 0.5453 - loss:

0.6815 - val_accuracy: 0.7312 - val_loss: 0.5341

Epoch 2/3

313/313 ━━━━━━━━━━━━━━━━━━━━ 82s 207ms/step - accuracy: 0.7731 - loss:

0.4889 - val_accuracy: 0.6962 - val_loss: 0.5694

Epoch 3/3
313/313 ━━━━━━━━━━━━━━━━━━━━ 82s 208ms/step - accuracy: 0.7773 - loss:
0.4860 - val_accuracy: 0.8114 - val_loss: 0.4508

782/782 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.8051 - loss:

0.4589

Test Loss: 0.45079389214515686

Test Accuracy: 0.8087199926376343