def on_epoch_end(self, epoch, logs={}):
print("On Epoch End: ")
print("epoch: ", epoch)
t = time.time()
builder = Seq2SeqBuilder()
encoder_model, decoder_model = builder.build_encoder_decoder_inference(
self.model)
inference = Inference(
'./dataset/image_embeddings_to_sentence/stories_to_index_' +
self.dataset_type + '.hdf5', './dataset/vist2017_vocabulary.json',
encoder_model, decoder_model)
hypotheses_filename = "./results/temp/hypotheses_" + self.dataset_type + "_epoch_" + str(
epoch) + ".txt"
references_filename = "./results/original_" + self.dataset_type + ".txt"
inference.predict_all(batch_size=64,
references_file_name='',
hypotheses_file_name=hypotheses_filename)
# calculating Meteor
status, output_meteor = commands.getstatusoutput(
"java -Xmx2G -jar nlp/meteor-1.5.jar " + hypotheses_filename +
" " + references_filename + " -t hter -l en -norm")
# Calculating BLEU score
status, output_bleu = commands.getstatusoutput(
"perl ./nlp/multi-bleu.perl " + references_filename + " < " +
hypotheses_filename)
text_file = open(
'./results/temp/' + "bleu_" + self.dataset_type + "_epoch_" +
str(epoch), "w")
text_file.write(output_bleu)
text_file.close()
text_file = open(
'./results/temp/' + "meteor_" + self.dataset_type + "_epoch_" +
str(epoch), "w")
text_file.write(output_meteor)
text_file.close()
print("Meteor/Bleu time(minutes) : ", (time.time() - t) / 60.0)
print("end calculating")
def __init__(self, dataset_file_path, vocabulary_file_path, encoder_model,
decoder_model):
self.vocab_json = json.load(open(vocabulary_file_path))
self.num_decoder_tokens = len(self.vocab_json['idx_to_words'])
self.words_to_idx = self.vocab_json["words_to_idx"]
self.idx_to_words = self.vocab_json["idx_to_words"]
self.dataset_file = h5py.File(dataset_file_path, 'r')
self.story_ids = self.dataset_file["story_ids"]
self.image_embeddings = self.dataset_file["image_embeddings"]
self.story_sentences = self.dataset_file["story_sentences"]
self.encoder_model = encoder_model
self.decoder_model = decoder_model
self.vocab_size = len(self.words_to_idx)
self.num_stacked_layers = Seq2SeqBuilder().get_number_of_layers(
encoder_model, layer_prefix="encoder_layer_")
return
from seq2seqbuilder import Seq2SeqBuilder, SentenceEncoderRNN, SentenceEncoderCNN
from result_visualisation import Inference
import time as time
from keras import backend as K
from keras.utils import plot_model
# The learning phase flag is a bool tensor (0 = test, 1 = train) to be passed as input to any Keras function that uses a different behavior at train time and test time.
K.set_learning_phase(0)
#dataset_type = "valid"
dataset_type = "review_test1"
#model_name = "2018-04-30_08:56:33-2018-04-30_20:37:12"
model_name = "2019-01-20_18-13-57-2019-01-20_19-20-14"
model_file_name = "./trained_models/" + model_name + ".h5"
# model_file_name = "trained_models/2018-01-18_17:39:24-2018-01-20_18:50:39:image_to_text_gru.h5"
builder = Seq2SeqBuilder()
sentence_encoder = SentenceEncoderRNN()
encoder_model, decoder_model = builder.build_encoder_decoder_inference_from_file(model_file_name, sentence_encoder,
include_sentence_encoder=True,
attention=True)
# plot_model(encoder_model, to_file='encomodel.png',show_shapes=True)
# plot_model(decoder_model, to_file='decomodel.png',show_shapes=True)
inference = Inference('./dataset/image_embeddings_to_sentence/stories_to_index_' + dataset_type + '.hdf5',
'./dataset/vist2017_vocabulary.json', encoder_model, decoder_model)
t = time.time()
# inference.predict_all(batch_size=64, references_file_name='',
# hypotheses_file_name="./results/"+ model_name +"/hypotheses_" +dataset_type + ".txt")
# beam_size = 10
# inference.predict_all_beam_search(batch_size=600, beam_size=beam_size, hypotheses_file_name="./results/"+ model_name +"/hypotheses_" +dataset_type + "_beam"+str(beam_size)+".txt")
inference.predict_all(batch_size=50, references_file_name='',
hypotheses_file_name="./results/hypotheses_" + dataset_type + ".txt",