def test_loss_model1(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), 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=MlpSoftmaxDecoder(input_dim=layer_dim, trg_embed_dim=layer_dim, rnn_layer=UniLSTMSeqTransducer( input_dim=layer_dim, hidden_dim=layer_dim, decoder_input_dim=layer_dim, yaml_path="model.decoder.rnn_layer"), mlp_layer=MLP( input_dim=layer_dim, hidden_dim=layer_dim, decoder_rnn_dim=layer_dim, vocab_size=100, yaml_path="model.decoder.rnn_layer"), bridge=CopyBridge(dec_dim=layer_dim, dec_layers=1)), ) model.set_train(False) self.assert_single_loss_equals_batch_loss(model)
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(), trg_reader=PlainTextReader(), src_embedder=SimpleWordEmbedder(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), trg_embedder=SimpleWordEmbedder(vocab_size=100, emb_dim=layer_dim), decoder=MlpSoftmaxDecoder(input_dim=layer_dim, trg_embed_dim=layer_dim, rnn_layer=UniLSTMSeqTransducer( input_dim=layer_dim, hidden_dim=layer_dim, decoder_input_dim=layer_dim, yaml_path="model.decoder.rnn_layer"), mlp_layer=MLP( input_dim=layer_dim, hidden_dim=layer_dim, decoder_rnn_dim=layer_dim, vocab_size=100, yaml_path="model.decoder.rnn_layer"), 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 = xnmt.training_regimen.SimpleTrainingRegimen( **train_args) for _ in range(50): training_regimen.run_training(save_fct=lambda: None, update_weights=True) self.assertAlmostEqual( 0.0, training_regimen.train_loss_tracker.epoch_loss.sum() / training_regimen.train_loss_tracker.epoch_words, places=2)
def setUp(self): layer_dim = 512 xnmt.events.clear() ParamManager.init_param_col() self.model = DefaultTranslator( src_reader=PlainTextReader(), trg_reader=PlainTextReader(), 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), trg_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100), decoder=MlpSoftmaxDecoder(input_dim=layer_dim, trg_embed_dim=layer_dim, rnn_layer=UniLSTMSeqTransducer( input_dim=layer_dim, hidden_dim=layer_dim, decoder_input_dim=layer_dim, yaml_path="model.decoder.rnn_layer"), mlp_layer=MLP( input_dim=layer_dim, hidden_dim=layer_dim, decoder_rnn_dim=layer_dim, vocab_size=100, yaml_path="model.decoder.rnn_layer"), bridge=CopyBridge(dec_dim=layer_dim, dec_layers=1)), ) self.model.set_train(False) self.model.initialize_generator() self.src_data = list( self.model.src_reader.read_sents("examples/data/head.ja")) self.trg_data = list( self.model.trg_reader.read_sents("examples/data/head.en")) self.search = GreedySearch()
hidden_dim=layer_dim, layers=1), attender=MlpAttender(hidden_dim=layer_dim, state_dim=layer_dim, input_dim=layer_dim), trg_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=len(trg_vocab)), decoder=MlpSoftmaxDecoder(input_dim=layer_dim, rnn_layer=UniLSTMSeqTransducer( input_dim=layer_dim, hidden_dim=layer_dim, decoder_input_dim=layer_dim, yaml_path="decoder"), mlp_layer=MLP(input_dim=layer_dim, hidden_dim=layer_dim, decoder_rnn_dim=layer_dim, yaml_path="decoder", vocab_size=len(trg_vocab)), trg_embed_dim=layer_dim, bridge=CopyBridge(dec_dim=layer_dim, dec_layers=1)), inference=inference) train = SimpleTrainingRegimen( name=f"{EXP}", model=model, batcher=batcher, trainer=AdamTrainer(alpha=0.001), run_for_epochs=2, src_file="examples/data/head.ja", trg_file="examples/data/head.en",