def test_loss_model1(self): layer_dim = 512 model = DefaultTranslator( src_reader=self.src_reader, trg_reader=self.trg_reader, src_embedder=LookupEmbedder(emb_dim=layer_dim, vocab_size=100), encoder=BiLSTMSeqTransducer(input_dim=layer_dim, hidden_dim=layer_dim), attender=MlpAttender(input_dim=layer_dim, state_dim=layer_dim, hidden_dim=layer_dim), decoder=AutoRegressiveDecoder( input_dim=layer_dim, embedder=LookupEmbedder(emb_dim=layer_dim, vocab_size=100), rnn=UniLSTMSeqTransducer(input_dim=layer_dim, hidden_dim=layer_dim, decoder_input_dim=layer_dim, yaml_path="model.decoder.rnn"), transform=NonLinear(input_dim=layer_dim * 2, output_dim=layer_dim), scorer=Softmax(input_dim=layer_dim, vocab_size=100), bridge=CopyBridge(dec_dim=layer_dim, dec_layers=1)), ) event_trigger.set_train(False) self.assert_single_loss_equals_batch_loss(model)
def setUp(self): layer_dim = 512 events.clear() ParamManager.init_param_col() src_vocab = Vocab(vocab_file="examples/data/head.ja.vocab") trg_vocab = Vocab(vocab_file="examples/data/head.en.vocab") self.model = DefaultTranslator( src_reader=PlainTextReader(vocab=src_vocab), trg_reader=PlainTextReader(vocab=trg_vocab), src_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100), encoder=BiLSTMSeqTransducer(input_dim=layer_dim, hidden_dim=layer_dim), attender=MlpAttender(input_dim=layer_dim, state_dim=layer_dim, hidden_dim=layer_dim), decoder=AutoRegressiveDecoder( input_dim=layer_dim, embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100), rnn=UniLSTMSeqTransducer(input_dim=layer_dim, hidden_dim=layer_dim, decoder_input_dim=layer_dim, yaml_path="model.decoder.rnn"), transform=NonLinear(input_dim=layer_dim * 2, output_dim=layer_dim), scorer=Softmax(input_dim=layer_dim, vocab_size=100), bridge=CopyBridge(dec_dim=layer_dim, dec_layers=1)), ) event_trigger.set_train(False) self.src_data = list( self.model.src_reader.read_sents("examples/data/head.ja"))
def test_bi_lstm_encoder_len(self): layer_dim = 512 model = DefaultTranslator( src_reader=self.src_reader, trg_reader=self.trg_reader, src_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100), encoder=BiLSTMSeqTransducer(input_dim=layer_dim, hidden_dim=layer_dim, layers=3), attender=MlpAttender(input_dim=layer_dim, state_dim=layer_dim, hidden_dim=layer_dim), decoder=AutoRegressiveDecoder( input_dim=layer_dim, embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100), rnn=UniLSTMSeqTransducer(input_dim=layer_dim, hidden_dim=layer_dim, decoder_input_dim=layer_dim, yaml_path="model.decoder.rnn"), transform=NonLinear(input_dim=layer_dim * 2, output_dim=layer_dim), scorer=Softmax(input_dim=layer_dim, vocab_size=100), bridge=CopyBridge(dec_dim=layer_dim, dec_layers=1)), ) self.assert_in_out_len_equal(model)
def test_py_lstm_encoder_len(self): layer_dim = 512 model = DefaultTranslator( src_reader=self.src_reader, trg_reader=self.trg_reader, src_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100), encoder=PyramidalLSTMSeqTransducer(input_dim=layer_dim, hidden_dim=layer_dim, layers=3), attender=MlpAttender(input_dim=layer_dim, state_dim=layer_dim, hidden_dim=layer_dim), decoder=AutoRegressiveDecoder( input_dim=layer_dim, embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100), rnn=UniLSTMSeqTransducer(input_dim=layer_dim, hidden_dim=layer_dim, decoder_input_dim=layer_dim, yaml_path="model.decoder.rnn"), transform=NonLinear(input_dim=layer_dim * 2, output_dim=layer_dim), scorer=Softmax(input_dim=layer_dim, vocab_size=100), bridge=CopyBridge(dec_dim=layer_dim, dec_layers=1)), ) event_trigger.set_train(True) for sent_i in range(10): dy.renew_cg() src = self.src_data[sent_i].create_padded_sent( 4 - (self.src_data[sent_i].sent_len() % 4)) event_trigger.start_sent(src) embeddings = model.src_embedder.embed_sent(src) encodings = model.encoder.transduce(embeddings) self.assertEqual(int(math.ceil(len(embeddings) / float(4))), len(encodings))
def test_train_dev_loss_equal(self): layer_dim = 512 batcher = SrcBatcher(batch_size=5, break_ties_randomly=False) train_args = {} train_args['src_file'] = "examples/data/head.ja" train_args['trg_file'] = "examples/data/head.en" train_args['loss_calculator'] = MLELoss() train_args['model'] = DefaultTranslator(src_reader=PlainTextReader(vocab=Vocab(vocab_file="examples/data/head.ja.vocab")), trg_reader=PlainTextReader(vocab=Vocab(vocab_file="examples/data/head.en.vocab")), src_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100), encoder=BiLSTMSeqTransducer(input_dim=layer_dim, hidden_dim=layer_dim), attender=MlpAttender(input_dim=layer_dim, state_dim=layer_dim, hidden_dim=layer_dim), decoder=AutoRegressiveDecoder(input_dim=layer_dim, embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100), rnn=UniLSTMSeqTransducer(input_dim=layer_dim, hidden_dim=layer_dim, decoder_input_dim=layer_dim, yaml_path="model.decoder.rnn"), transform=NonLinear(input_dim=layer_dim*2, output_dim=layer_dim), scorer=Softmax(input_dim=layer_dim, vocab_size=100), bridge=CopyBridge(dec_dim=layer_dim, dec_layers=1)), ) train_args['dev_tasks'] = [LossEvalTask(model=train_args['model'], src_file="examples/data/head.ja", ref_file="examples/data/head.en", batcher=batcher)] train_args['trainer'] = DummyTrainer() train_args['batcher'] = batcher train_args['run_for_epochs'] = 1 training_regimen = regimens.SimpleTrainingRegimen(**train_args) training_regimen.run_training(save_fct = lambda: None) self.assertAlmostEqual(training_regimen.train_loss_tracker.epoch_loss.sum_factors() / training_regimen.train_loss_tracker.epoch_words, training_regimen.dev_loss_tracker.dev_score.loss, places=5)
def test_conv_composer(self): composer = ConvolutionComposer(ngram_size=2, transform=NonLinear(self.layer_dim, self.layer_dim, activation="relu"), embed_dim=self.layer_dim, hidden_dim=self.layer_dim) embedder = CharCompositionEmbedder(emb_dim=self.layer_dim, composer=composer, char_vocab=self.src_char_vocab) embedder.embed_sent(self.src[1])
def test_py_lstm_mask(self): layer_dim = 512 model = DefaultTranslator( src_reader=self.src_reader, trg_reader=self.trg_reader, src_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100), encoder=PyramidalLSTMSeqTransducer(input_dim=layer_dim, hidden_dim=layer_dim, layers=1), attender=MlpAttender(input_dim=layer_dim, state_dim=layer_dim, hidden_dim=layer_dim), trg_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100), decoder=AutoRegressiveDecoder( input_dim=layer_dim, trg_embed_dim=layer_dim, rnn=UniLSTMSeqTransducer(input_dim=layer_dim, hidden_dim=layer_dim, decoder_input_dim=layer_dim, yaml_path="model.decoder.rnn"), transform=NonLinear(input_dim=layer_dim * 2, output_dim=layer_dim), scorer=Softmax(input_dim=layer_dim, vocab_size=100), bridge=CopyBridge(dec_dim=layer_dim, dec_layers=1)), ) batcher = batchers.TrgBatcher(batch_size=3) train_src, _ = \ batcher.pack(self.src_data, self.trg_data) event_trigger.set_train(True) for sent_i in range(3): dy.renew_cg() src = train_src[sent_i] event_trigger.start_sent(src) embeddings = model.src_embedder.embed_sent(src) encodings = model.encoder.transduce(embeddings) if train_src[sent_i].mask is None: assert encodings.mask is None else: np.testing.assert_array_almost_equal( train_src[sent_i].mask.np_arr, encodings.mask.np_arr)
def test_overfitting(self): layer_dim = 16 batcher = SrcBatcher(batch_size=10, break_ties_randomly=False) train_args = {} train_args['src_file'] = "examples/data/head.ja" train_args['trg_file'] = "examples/data/head.en" train_args['loss_calculator'] = MLELoss() train_args['model'] = DefaultTranslator( src_reader=PlainTextReader(vocab=Vocab( vocab_file="examples/data/head.ja.vocab")), trg_reader=PlainTextReader(vocab=Vocab( vocab_file="examples/data/head.en.vocab")), src_embedder=LookupEmbedder(vocab_size=100, emb_dim=layer_dim), encoder=BiLSTMSeqTransducer(input_dim=layer_dim, hidden_dim=layer_dim), attender=MlpAttender(input_dim=layer_dim, state_dim=layer_dim, hidden_dim=layer_dim), decoder=AutoRegressiveDecoder( input_dim=layer_dim, embedder=LookupEmbedder(emb_dim=layer_dim, vocab_size=100), rnn=UniLSTMSeqTransducer(input_dim=layer_dim, hidden_dim=layer_dim, decoder_input_dim=layer_dim, yaml_path="model.decoder.rnn"), transform=NonLinear(input_dim=layer_dim * 2, output_dim=layer_dim), scorer=Softmax(input_dim=layer_dim, vocab_size=100), bridge=CopyBridge(dec_dim=layer_dim, dec_layers=1)), ) train_args['dev_tasks'] = [ LossEvalTask(model=train_args['model'], src_file="examples/data/head.ja", ref_file="examples/data/head.en", batcher=batcher) ] train_args['run_for_epochs'] = 1 train_args['trainer'] = AdamTrainer(alpha=0.1) train_args['batcher'] = batcher training_regimen = regimens.SimpleTrainingRegimen(**train_args)