eva

def evaluate_model(model, descriptions, photos, tokenizer, max_length):
	actual, predicted = list(), list()
	# step over the whole set
	for key, desc_list in descriptions.items():
		# generate description
		yhat = generate_desc(model, tokenizer, photos[key], max_length)
		# store actual and predicted
		references = [d.split() for d in desc_list]
		actual.append(references)
		predicted.append(yhat.split())
	# calculate BLEU score
	print('BLEU-1: %f' % corpus_bleu(actual, predicted, weights=(1.0, 0, 0, 0)))
	print('BLEU-2: %f' % corpus_bleu(actual, predicted, weights=(0.5, 0.5, 0, 0)))
	print('BLEU-3: %f' % corpus_bleu(actual, predicted, weights=(0.3, 0.3, 0.3, 0)))
	print('BLEU-4: %f' % corpus_bleu(actual, predicted, weights=(0.25, 0.25, 0.25, 0.25)))