Course_3_Week_3_Project_2.py

"""
This is is a part of the DeepLearning.AI TensorFlow Developer Professional Certificate offered on Coursera.

All copyrights belong to them. I am sharing this work here to showcase the projects I have worked on
Course: Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning

Week 3: Sequence models

Aim: IMDB Subwords Dataset with LSTM
"""

import tensorflow_datasets as tfds
import tensorflow as tf
import tensorflow_datasets as tfds
import tensorflow as tf

tf.keras.backend.clear_session()

# Get the data
dataset, info = tfds.load('imdb_reviews/subwords8k', with_info=True, as_supervised=True)
train_dataset, test_dataset = dataset['train'], dataset['test']

tokenizer = info.features['text'].encoder

BUFFER_SIZE = 10000
BATCH_SIZE = 64

train_dataset = train_dataset.shuffle(BUFFER_SIZE)
train_dataset = train_dataset.padded_batch(BATCH_SIZE, tf.compat.v1.data.get_output_shapes(train_dataset))
test_dataset = test_dataset.padded_batch(BATCH_SIZE, tf.compat.v1.data.get_output_shapes(test_dataset))

model = tf.keras.Sequential([
    tf.keras.layers.Embedding(tokenizer.vocab_size, 64),
    tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(64, return_sequences=True)),
    tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(32)),
    tf.keras.layers.Dense(64, activation='relu'),
    tf.keras.layers.Dense(1, activation='sigmoid')
])

model.summary()

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

NUM_EPOCHS = 1
history = model.fit(train_dataset, epochs=NUM_EPOCHS, validation_data=test_dataset)

import matplotlib.pyplot as plt


def plot_graphs(history, string):
    plt.plot(history.history[string])
    plt.plot(history.history['val_' + string])
    plt.xlabel("Epochs")
    plt.ylabel(string)
    plt.legend([string, 'val_' + string])
    plt.show()

plot_graphs(history, "acc")
plot_graphs(history, "loss")