def create_training_model(FLAGS,vocab_in, vocab_out = None):
batcher_train = Batcher(FLAGS.data_path, vocab_in,vocab_out, FLAGS, data_file=FLAGS.train_name)
train_model = SummarizationModel(FLAGS, vocab_in,vocab_out,batcher_train)
logging.info("Building graph...")
train_model.build_graph()
# Create dev model
# I can't deepCopy tf.flags, so I change flags into nametuple.
# Find another way in the future
FLAGS_eval = FLAGS._asdict()
FLAGS_eval["mode"] = "eval"
FLAGS_eval = config.generate_nametuple(FLAGS_eval)
#variable_scope.get_variable_scope().reuse_variables()
batcher_dev = Batcher(FLAGS.data_path, vocab_in,vocab_out, FLAGS, data_file=FLAGS.dev_name)
dev_model = SummarizationModel(FLAGS_eval, vocab_in,vocab_out,batcher_dev)
dev_model.build_graph()
train_model.create_or_load_recent_model()
return train_model,dev_model
def decode_Beam(FLAGS):
# If in decode mode, set batch_size = beam_size
# Reason: in decode mode, we decode one example at a time.
# On each step, we have beam_size-many hypotheses in the beam, so we need to make a batch of these hypotheses.
#if FLAGS.mode == 'decode':
# FLAGS.batch_size = FLAGS.beam_size
# If single_pass=True, check we're in decode mode
#if FLAGS.single_pass and FLAGS.mode != 'decode':
# raise Exception("The single_pass flag should only be True in decode mode")
vocab_in, vocab_out = data.load_dict_data(FLAGS)
FLAGS_batcher = config.retype_FLAGS()
FLAGS_decode = FLAGS_batcher._asdict()
FLAGS_decode["max_dec_steps"] = 1
FLAGS_decode["mode"] = "decode"
FLAGS_decode = config.generate_nametuple(FLAGS_decode)
# The model is configured with max_dec_steps=1 because we only ever run one step of the decoder at a time (to do beam search). Note that the batcher is initialized with max_dec_steps equal to e.g. 100 because the batches need to contain the full summaries
batcher = Batcher(FLAGS.data_path, vocab_in,vocab_out, FLAGS_batcher, data_file=FLAGS.test_name)
model = SummarizationModel(FLAGS_decode, vocab_in,vocab_out,batcher)
decoder = BeamSearchDecoder(model, batcher, vocab_out)
decoder.decode()
def create_decode_model(FLAGS, vocab_in,vocab_out):
batcher = Batcher(FLAGS.data_path, vocab_in, vocab_out, FLAGS, data_file=FLAGS.qq_name)
import eval
FLAGS_decode = config.retype_FLAGS()._asdict()
FLAGS_decode["max_dec_steps"] = 1
FLAGS_decode["mode"] = "decode"
FLAGS_decode = config.generate_nametuple(FLAGS_decode)
model = SummarizationModel(FLAGS_decode, vocab_in, vocab_out, batcher)
#model.graph.as_default()
decoder = eval.EvalDecoder(model, batcher, vocab_out)
return decoder
def decode_multi(FLAGS):
vocab_in, vocab_out = data.load_dict_data(FLAGS)
batcher = Batcher(FLAGS.data_path, vocab_in, vocab_out, FLAGS, data_file=FLAGS.test_name,shuffle=False)
import eval
FLAGS_decode = config.retype_FLAGS()._asdict()
FLAGS_decode["max_dec_steps"] = 1
FLAGS_decode = config.generate_nametuple(FLAGS_decode)
model = SummarizationModel(FLAGS_decode, vocab_in, vocab_out, batcher)
decoder = eval.EvalDecoder(model, batcher, vocab_out)
time_start = time.time()
decoder.pair_wise_decode()
time_end = time.time()
print(time_end - time_start)