Evaluating the model

With the model trained, let’s test the model on our unseen test dataset. Testing logic is almost identical to the validation logic we discussed earlier during model training. Therefore, we won’t repeat our discussion here.

bleu_metric = BLEUMetric(tokenizer=tokenizer)
test_dataset, _ = generate_tf_dataset(
    test_captions_df, tokenizer=tokenizer, n_vocab=n_vocab, batch_
size=batch_size, training=False
)
test_loss, test_accuracy, test_bleu = [], [], []
for ti, t_batch in enumerate(test_dataset):
    print(f"{ti+1} batches processed", end='\r')
    loss, accuracy = full_model.test_on_batch(t_batch[0], t_batch[1])
    batch_predicted = full_model.predict_on_batch(t_batch[0])
    bleu_score = bleu_metric.calculate_bleu_from_predictions(t_batch[1],
batch_predicted)
    test_loss.append(loss)
    test_accuracy.append(accuracy)
    test_bleu.append(bleu_score)
print(
    f"\ntest_loss: {np.mean(test_loss)} - test_accuracy: {np.mean(test_
accuracy)} - test_bleu: {np.mean(test_bleu)}"
)

Introduction to Natural Language Processing

Understanding TensorFlow 2

Word2vec: Learning Word Embeddings

Advanced Word Vector Algorithms

Sentence Classification with Convolutional Neural Networks

Recurrent Neural Networks

Understanding Long Short-Term Memory Networks

Applications of LSTM: Generating Text

Sequence-to-Sequence Learning: Neural Machine Translation

Transformers

Image Captioning with Transformers

Final Remarks

Appendix: Mathematical Foundations and Advanced TensorFlow

Evaluating the Model and Generating Captions from It

Evaluating the model

Captions generated for test images