Python vocabulary.Vocabulary类代码示例

def train(args):
  trace('loading corpus ...')
  with open(args.source) as fp:
    trees = [make_tree(l) for l in fp]

  trace('extracting leaf nodes ...')
  word_lists = [extract_words(t) for t in trees]

  trace('extracting gold operations ...')
  op_lists = [make_operations(t) for t in trees]

  trace('making vocabulary ...')
  word_vocab = Vocabulary.new(word_lists, args.vocab)
  phrase_set = set()
  semi_set = set()
  for tree in trees:
    phrase_set |= set(extract_phrase_labels(tree))
    semi_set |= set(extract_semi_labels(tree))
  phrase_vocab = Vocabulary.new([list(phrase_set)], len(phrase_set), add_special_tokens=False)
  semi_vocab = Vocabulary.new([list(semi_set)], len(semi_set), add_special_tokens=False)

  trace('converting data ...')
  word_lists = [convert_word_list(x, word_vocab) for x in word_lists]
  op_lists = [convert_op_list(x, phrase_vocab, semi_vocab) for x in op_lists]

  trace('start training ...')
  parser = Parser(
      args.vocab, args.embed, args.queue, args.stack,
      len(phrase_set), len(semi_set),
  )
  if USE_GPU:
    parser.to_gpu()
  opt = optimizers.AdaGrad(lr = 0.005)
  opt.setup(parser)
  opt.add_hook(optimizer.GradientClipping(5))

  for epoch in range(args.epoch):
    n = 0
    
    for samples in batch(zip(word_lists, op_lists), args.minibatch):
      parser.zerograds()
      loss = my_zeros((), np.float32)

      for word_list, op_list in zip(*samples):
        trace('epoch %3d, sample %6d:' % (epoch + 1, n + 1))
        loss += parser.forward(word_list, op_list, 0)
        n += 1
      
      loss.backward()
      opt.update()

    trace('saving model ...')
    prefix = args.model + '.%03.d' % (epoch + 1)
    word_vocab.save(prefix + '.words')
    phrase_vocab.save(prefix + '.phrases')
    semi_vocab.save(prefix + '.semiterminals')
    parser.save_spec(prefix + '.spec')
    serializers.save_hdf5(prefix + '.weights', parser)

  trace('finished.')

 def load(filename):
     self = AttentionalTranslationModel()
     with ModelFile(filename) as fp:
         self.__src_vocab = Vocabulary.load(fp.get_file_pointer())
         self.__trg_vocab = Vocabulary.load(fp.get_file_pointer())
         self.__n_embed = int(fp.read())
         self.__n_hidden = int(fp.read())
         self.__make_model()
         wrapper.begin_model_access(self.__model)
         fp.read_embed(self.__model.w_xi)
         fp.read_linear(self.__model.w_ia)
         fp.read_linear(self.__model.w_aa)
         fp.read_linear(self.__model.w_ib)
         fp.read_linear(self.__model.w_bb)
         fp.read_linear(self.__model.w_aw)
         fp.read_linear(self.__model.w_bw)
         fp.read_linear(self.__model.w_pw)
         fp.read_linear(self.__model.w_we)
         fp.read_linear(self.__model.w_ap)
         fp.read_linear(self.__model.w_bp)
         fp.read_embed(self.__model.w_yp)
         fp.read_linear(self.__model.w_pp)
         fp.read_linear(self.__model.w_cp)
         fp.read_linear(self.__model.w_dp)
         fp.read_linear(self.__model.w_py)
         wrapper.end_model_access(self.__model)
     return self

    def test(self):
        trace('loading model ...')
        src_vocab = Vocabulary.load(self.model + '.srcvocab')
        trg_vocab = Vocabulary.load(self.model + '.trgvocab')
        encdec = EncoderDecoder.load_spec(self.model + '.spec')
        serializers.load_hdf5(self.model + '.weights', encdec)

        trace('generating translation ...')
        generated = 0

        with open(self.target, 'w') as fp:
            for src_batch in gens.batch(gens.word_list(self.source), self.minibatch):
                src_batch = fill_batch(src_batch)
                K = len(src_batch)

                trace('sample %8d - %8d ...' % (generated + 1, generated + K))
                hyp_batch = self.forward(src_batch, None, src_vocab, trg_vocab, encdec, False, self.generation_limit)

                source_cuont = 0
                for hyp in hyp_batch:
                    hyp.append('</s>')
                    hyp = hyp[:hyp.index('</s>')]
                    print("src : " + "".join(src_batch[source_cuont]).replace("</s>", ""))
                    print('hyp : ' +''.join(hyp))
                    print(' '.join(hyp), file=fp)
                    source_cuont = source_cuont + 1

                generated += K

        trace('finished.')

    def train_model(self):
        trace('making vocaburaries ...')
        src_vocab = Vocabulary.new(gens.word_list(self.source), self.vocab)
        trg_vocab = Vocabulary.new(gens.word_list(self.target), self.vocab)

        trace('making model ...')
        model = self.new(src_vocab, trg_vocab, self.embed, self.hidden, self.parameter_dict)

        random_number = random.randint(0, self.minibatch)
        for i_epoch in range(self.epoch):
            trace('epoch %d/%d: ' % (i_epoch + 1, self.epoch))
            trained = 0
            gen1 = gens.word_list(self.source)
            gen2 = gens.word_list(self.target)
            gen3 = gens.batch(gens.sorted_parallel(gen1, gen2, 100 * self.minibatch), self.minibatch)
            model.init_optimizer()

            for src_batch, trg_batch in gen3:
                src_batch = fill_batch(src_batch)
                trg_batch = fill_batch(trg_batch)
                K = len(src_batch)
                hyp_batch = model.train(src_batch, trg_batch)

                if trained == 0:
                    self.print_out(random_number, i_epoch, trained, src_batch, trg_batch, hyp_batch)

                trained += K

            trace('saving model ...')
            model.save("ChainerMachineTranslation" + '.%03d' % (self.epoch + 1))

        trace('finished.')

def test(args):
  trace('loading model ...')
  word_vocab = Vocabulary.load(args.model + '.words')
  phrase_vocab = Vocabulary.load(args.model + '.phrases')
  semiterminal_vocab = Vocabulary.load(args.model + '.semiterminals')
  parser = Parser.load_spec(args.model + '.spec')
  if args.use_gpu:
    parser.to_gpu()
  serializers.load_hdf5(args.model + '.weights', parser)

  embed_cache = {}
  parser.reset()

  trace('generating parse trees ...')
  with open(args.source) as fp:
    for l in fp:
      word_list = to_vram_words(convert_word_list(l.split(), word_vocab))
      tree = combine_xbar(
          restore_labels(
              parser.forward(word_list, None, args.unary_limit, embed_cache),
              phrase_vocab,
              semiterminal_vocab))
      print('( ' + tree_to_string(tree) + ' )')

  trace('finished.')

def train_model(args):
    trace('making vocaburaries ...')
    src_vocab = Vocabulary.new(gens.word_list(args.source), args.vocab)
    trg_vocab = Vocabulary.new(gens.word_list(args.target), args.vocab)

    trace('making model ...')
    model = EncoderDecoderModel.new(src_vocab, trg_vocab, args.embed, args.hidden)

    for epoch in range(args.epoch):
        trace('epoch %d/%d: ' % (epoch + 1, args.epoch))
        trained = 0
        gen1 = gens.word_list(args.source)
        gen2 = gens.word_list(args.target)
        gen3 = gens.batch(gens.sorted_parallel(gen1, gen2, 100 * args.minibatch), args.minibatch)
        model.init_optimizer()

        for src_batch, trg_batch in gen3:
            src_batch = fill_batch(src_batch)
            trg_batch = fill_batch(trg_batch)
            K = len(src_batch)
            hyp_batch = model.train(src_batch, trg_batch)

            for k in range(K):
                trace('epoch %3d/%3d, sample %8d' % (epoch + 1, args.epoch, trained + k + 1))
                trace('  src = ' + ' '.join([x if x != '</s>' else '*' for x in src_batch[k]]))
                trace('  trg = ' + ' '.join([x if x != '</s>' else '*' for x in trg_batch[k]]))
                trace('  hyp = ' + ' '.join([x if x != '</s>' else '*' for x in hyp_batch[k]]))

            trained += K

        trace('saving model ...')
        model.save(args.model + '.%03d' % (epoch + 1))

    trace('finished.')

def test(args):
  trace('loading model ...')
  src_vocab = Vocabulary.load(args.model + '.srcvocab')
  trg_vocab = Vocabulary.load(args.model + '.trgvocab')
  attmt = AttentionMT.load_spec(args.model + '.spec')
  if args.use_gpu:
    attmt.to_gpu()
  serializers.load_hdf5(args.model + '.weights', attmt)
  
  trace('generating translation ...')
  generated = 0

  with open(args.target, 'w') as fp:
    for src_batch in gens.batch(gens.word_list(args.source), args.minibatch):
      src_batch = fill_batch(src_batch)
      K = len(src_batch)

      trace('sample %8d - %8d ...' % (generated + 1, generated + K))
      hyp_batch = forward(src_batch, None, src_vocab, trg_vocab, attmt, False, args.generation_limit)

      for hyp in hyp_batch:
        hyp.append('</s>')
        hyp = hyp[:hyp.index('</s>')]
        print(' '.join(hyp), file=fp)

      generated += K

  trace('finished.')

 def __predict_sentence(self, src_batch):
     dialogue = EncoderDecoderModelForwardSlack(self.parameter)
     src_vocab = Vocabulary.load(self.model_name + '.srcvocab')
     trg_vocab = Vocabulary.load(self.model_name + '.trgvocab')
     model = EncoderDecoder.load_spec(self.model_name + '.spec')
     serializers.load_hdf5(dialogue.model + '.weights', model)
     hyp_batch = dialogue.forward(src_batch, None, src_vocab, trg_vocab, model, False, self.generation_limit)
     return hyp_batch

  def __init__(self, args):
    trace('loading model ...')
    self.args = args
    self.src_vocab = Vocabulary.load(args.model + '.srcvocab')
    self.trg_vocab = Vocabulary.load(args.model + '.trgvocab')
    self.encdec = EncoderDecoder.load_spec(args.model + '.spec')
    if args.use_gpu:
      self.encdec.to_gpu()
    serializers.load_hdf5(args.model + '.weights', self.encdec)

    trace('generating translation ...')

 def __predict_sentence(self, src_batch):
     """
     predict sentence
     :param src_batch: get the source sentence
     :return:
     """
     dialogue = EncoderDecoderModelAttention(self.parameter)
     src_vocab = Vocabulary.load(self.model_name + '.srcvocab')
     trg_vocab = Vocabulary.load(self.model_name + '.trgvocab')
     model = AttentionDialogue.load_spec(self.model_name + '.spec', self.XP)
     serializers.load_hdf5(self.model_name + '.weights', model)
     hyp_batch = dialogue.forward_implement(src_batch, None, src_vocab, trg_vocab, model, False, self.generation_limit)
     return hyp_batch

    def train(self):
        """
        Train method
        If you use the word2vec model, you possible to use the copy weight
        Optimizer method use the Adagrad
        """
        trace("making vocabularies ...")
        src_vocab = Vocabulary.new(gens.word_list(self.source), self.vocab)
        trg_vocab = Vocabulary.new(gens.word_list(self.target), self.vocab)

        trace("making model ...")
        self.attention_dialogue = AttentionDialogue(self.vocab, self.embed, self.hidden, self.XP)
        if self.word2vecFlag:
            self.copy_model(self.word2vec, self.attention_dialogue.emb)
            self.copy_model(self.word2vec, self.attention_dialogue.dec, dec_flag=True)

        for epoch in range(self.epoch):
            trace("epoch %d/%d: " % (epoch + 1, self.epoch))
            trained = 0
            gen1 = gens.word_list(self.source)
            gen2 = gens.word_list(self.target)
            gen3 = gens.batch(gens.sorted_parallel(gen1, gen2, 100 * self.minibatch), self.minibatch)
            opt = optimizers.AdaGrad(lr=0.01)
            opt.setup(self.attention_dialogue)
            opt.add_hook(optimizer.GradientClipping(5))

            random_number = random.randint(0, self.minibatch - 1)
            for src_batch, trg_batch in gen3:
                src_batch = fill_batch(src_batch)
                trg_batch = fill_batch(trg_batch)
                K = len(src_batch)
                hyp_batch, loss = self.forward_implement(
                    src_batch, trg_batch, src_vocab, trg_vocab, self.attention_dialogue, True, 0
                )
                loss.backward()
                opt.update()

                self.print_out(random_number, epoch, trained, src_batch, trg_batch, hyp_batch)

                trained += K

        trace("saving model ...")
        prefix = self.model
        model_path = APP_ROOT + "/model/" + prefix
        src_vocab.save(model_path + ".srcvocab")
        trg_vocab.save(model_path + ".trgvocab")
        self.attention_dialogue.save_spec(model_path + ".spec")
        serializers.save_hdf5(model_path + ".weights", self.attention_dialogue)

        trace("finished.")

    def train(self):
        trace('making vocabularies ...')
        src_vocab = Vocabulary.new(gens.word_list(self.source), self.vocab)
        trg_vocab = Vocabulary.new(gens.word_list(self.target), self.vocab)

        trace('making model ...')
        encdec = EncoderDecoder(self.vocab, self.embed, self.hidden)
        if self.word2vecFlag:
            self.copy_model(self.word2vec, encdec.enc)
            self.copy_model(self.word2vec, encdec.dec, dec_flag=True)
        else:
            encdec = self.encdec

        for epoch in range(self.epoch):
            trace('epoch %d/%d: ' % (epoch + 1, self.epoch))
            trained = 0
            gen1 = gens.word_list(self.source)
            gen2 = gens.word_list(self.target)
            gen3 = gens.batch(gens.sorted_parallel(gen1, gen2, 100 * self.minibatch), self.minibatch)
            opt = optimizers.AdaGrad(lr = 0.01)
            opt.setup(encdec)
            opt.add_hook(optimizer.GradientClipping(5))

            random_number = random.randint(0, self.minibatch - 1)
            for src_batch, trg_batch in gen3:
                src_batch = fill_batch(src_batch)
                trg_batch = fill_batch(trg_batch)
                K = len(src_batch)
                hyp_batch, loss = self.forward(src_batch, trg_batch, src_vocab, trg_vocab, encdec, True, 0)
                loss.backward()
                opt.update()

                if trained == 0:
                    self.print_out(random_number, epoch, trained, src_batch, trg_batch, hyp_batch)

                trained += K

        trace('saving model ...')
        prefix = self.model
        src_vocab.save(prefix + '.srcvocab')
        trg_vocab.save(prefix + '.trgvocab')
        encdec.save_spec(prefix + '.spec')
        serializers.save_hdf5(prefix + '.weights', encdec)

        trace('finished.')

 def load(self, filename):
     with ModelFile(filename) as fp:
         self.src_vocab = Vocabulary.load(fp.get_file_pointer())
         self.trg_vocab = Vocabulary.load(fp.get_file_pointer())
         self.n_embed = int(fp.read())
         self.n_hidden = int(fp.read())
         self.make_model()
         wrapper.begin_model_access(self.model)
         fp.read_embed(self.model.weight_xi)
         fp.read_linear(self.model.weight_ip)
         fp.read_linear(self.model.weight_pp)
         fp.read_linear(self.model.weight_pq)
         fp.read_linear(self.model.weight_qj)
         fp.read_linear(self.model.weight_jy)
         fp.read_embed(self.model.weight_yq)
         fp.read_linear(self.model.weight_qq)
         wrapper.end_model_access(self.model)
     return self

def train(args):
  trace('making vocabularies ...')
  src_vocab = Vocabulary.new(gens.word_list(args.source), args.vocab)
  trg_vocab = Vocabulary.new(gens.word_list(args.target), args.vocab)

  trace('making model ...')
  attmt = AttentionMT(args.vocab, args.embed, args.hidden)
  if args.use_gpu:
    attmt.to_gpu()

  for epoch in range(args.epoch):
    trace('epoch %d/%d: ' % (epoch + 1, args.epoch))
    trained = 0
    gen1 = gens.word_list(args.source)
    gen2 = gens.word_list(args.target)
    gen3 = gens.batch(gens.sorted_parallel(gen1, gen2, 100 * args.minibatch), args.minibatch)
    opt = optimizers.AdaGrad(lr = 0.01)
    opt.setup(attmt)
    opt.add_hook(optimizer.GradientClipping(5))

    for src_batch, trg_batch in gen3:
      src_batch = fill_batch(src_batch)
      trg_batch = fill_batch(trg_batch)
      K = len(src_batch)
      hyp_batch, loss = forward(src_batch, trg_batch, src_vocab, trg_vocab, attmt, True, 0)
      loss.backward()
      opt.update()

      for k in range(K):
        trace('epoch %3d/%3d, sample %8d' % (epoch + 1, args.epoch, trained + k + 1))
        trace('  src = ' + ' '.join([x if x != '</s>' else '*' for x in src_batch[k]]))
        trace('  trg = ' + ' '.join([x if x != '</s>' else '*' for x in trg_batch[k]]))
        trace('  hyp = ' + ' '.join([x if x != '</s>' else '*' for x in hyp_batch[k]]))

      trained += K

    trace('saving model ...')
    prefix = args.model + '.%03.d' % (epoch + 1)
    src_vocab.save(prefix + '.srcvocab')
    trg_vocab.save(prefix + '.trgvocab')
    attmt.save_spec(prefix + '.spec')
    serializers.save_hdf5(prefix + '.weights', attmt)

  trace('finished.')

 def load(filename):
     self = EncoderDecoderModel()
     with ModelFile(filename) as fp:
         self.__src_vocab = Vocabulary.load(fp.get_file_pointer())
         self.__trg_vocab = Vocabulary.load(fp.get_file_pointer())
         self.__n_embed = int(fp.read())
         self.__n_hidden = int(fp.read())
         self.__make_model()
         wrapper.begin_model_access(self.__model)
         fp.read_embed(self.__model.w_xi)
         fp.read_linear(self.__model.w_ip)
         fp.read_linear(self.__model.w_pp)
         fp.read_linear(self.__model.w_pq)
         fp.read_linear(self.__model.w_qj)
         fp.read_linear(self.__model.w_jy)
         fp.read_embed(self.__model.w_yq)
         fp.read_linear(self.__model.w_qq)
         wrapper.end_model_access(self.__model)
     return self