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'] = AutoRegressiveMLELoss()
train_args['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=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)),
)
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 = xnmt.training_regimen.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 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=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)),
)
self.model.set_train(False)
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"))
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),
trg_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100),
decoder=MlpSoftmaxDecoder(input_dim=layer_dim,
lstm_dim=layer_dim,
mlp_hidden_dim=layer_dim,
trg_embed_dim=layer_dim,
vocab_size=100),
)
self.set_train(True)
for sent_i in range(10):
dy.renew_cg()
src = self.src_data[sent_i].get_padded_sent(
Vocab.ES, 4 - (len(self.src_data[sent_i]) % 4))
self.start_sent(src)
embeddings = model.src_embedder.embed_sent(src)
encodings = model.encoder(embeddings)
self.assertEqual(int(math.ceil(len(embeddings) / float(4))),
len(encodings))
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 = xnmt.batcher.TrgBatcher(batch_size=3)
train_src, _ = \
batcher.pack(self.src_data, self.trg_data)
self.set_train(True)
for sent_i in range(3):
dy.renew_cg()
src = train_src[sent_i]
self.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 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,
lstm_dim=layer_dim,
mlp_hidden_dim=layer_dim,
trg_embed_dim=layer_dim,
vocab_size=100,
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"))
def test_py_lstm_mask(self):
model = DefaultTranslator(
src_reader=self.src_reader,
trg_reader=self.trg_reader,
src_embedder=SimpleWordEmbedder(self.exp_global, vocab_size=100),
encoder=PyramidalLSTMSeqTransducer(self.exp_global, layers=1),
attender=MlpAttender(self.exp_global),
trg_embedder=SimpleWordEmbedder(self.exp_global, vocab_size=100),
decoder=MlpSoftmaxDecoder(self.exp_global, vocab_size=100),
)
batcher = xnmt.batcher.TrgBatcher(batch_size=3)
train_src, _ = \
batcher.pack(self.src_data, self.trg_data)
self.set_train(True)
for sent_i in range(3):
dy.renew_cg()
src = train_src[sent_i]
self.start_sent(src)
embeddings = model.src_embedder.embed_sent(src)
encodings = model.encoder(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 setUp(self):
xnmt.events.clear()
self.model_context = ModelContext()
self.model_context.dynet_param_collection = PersistentParamCollection(
"some_file", 1)
self.model = DefaultTranslator(
src_embedder=SimpleWordEmbedder(self.model_context,
vocab_size=100),
encoder=BiLSTMSeqTransducer(self.model_context),
attender=MlpAttender(self.model_context),
trg_embedder=SimpleWordEmbedder(self.model_context,
vocab_size=100),
decoder=MlpSoftmaxDecoder(self.model_context,
vocab_size=100,
bridge=CopyBridge(self.model_context,
dec_layers=1)),
)
self.model.initialize_training_strategy(TrainingStrategy())
self.model.set_train(False)
self.model.initialize_generator()
self.training_corpus = BilingualTrainingCorpus(
train_src="examples/data/head.ja",
train_trg="examples/data/head.en",
dev_src="examples/data/head.ja",
dev_trg="examples/data/head.en")
self.corpus_parser = BilingualCorpusParser(
src_reader=PlainTextReader(),
trg_reader=PlainTextReader(),
training_corpus=self.training_corpus)
def setUp(self):
xnmt.events.clear()
self.exp_global = ExpGlobal(
dynet_param_collection=PersistentParamCollection("some_file", 1))
self.model = DefaultTranslator(
src_reader=PlainTextReader(),
trg_reader=PlainTextReader(),
src_embedder=SimpleWordEmbedder(exp_global=self.exp_global,
vocab_size=100),
encoder=BiLSTMSeqTransducer(exp_global=self.exp_global),
attender=MlpAttender(exp_global=self.exp_global),
trg_embedder=SimpleWordEmbedder(exp_global=self.exp_global,
vocab_size=100),
decoder=MlpSoftmaxDecoder(exp_global=self.exp_global,
vocab_size=100,
bridge=CopyBridge(
exp_global=self.exp_global,
dec_layers=1)),
)
self.model.set_train(False)
self.model.initialize_generator(beam=1)
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"))
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_uni_lstm_encoder_len(self):
model = DefaultTranslator(
src_reader=self.src_reader,
trg_reader=self.trg_reader,
src_embedder=SimpleWordEmbedder(self.exp_global, vocab_size=100),
encoder=UniLSTMSeqTransducer(self.exp_global),
attender=MlpAttender(self.exp_global),
trg_embedder=SimpleWordEmbedder(self.exp_global, vocab_size=100),
decoder=MlpSoftmaxDecoder(self.exp_global, vocab_size=100),
)
self.assert_in_out_len_equal(model)
def test_res_lstm_encoder_len(self):
model = DefaultTranslator(
src_embedder=SimpleWordEmbedder(self.model_context,
vocab_size=100),
encoder=ResidualLSTMSeqTransducer(self.model_context, layers=3),
attender=MlpAttender(self.model_context),
trg_embedder=SimpleWordEmbedder(self.model_context,
vocab_size=100),
decoder=MlpSoftmaxDecoder(self.model_context, vocab_size=100),
)
self.assert_in_out_len_equal(model)
def test_loss_model2(self):
model = DefaultTranslator(
src_embedder=SimpleWordEmbedder(self.model_context,
vocab_size=100),
encoder=PyramidalLSTMSeqTransducer(self.model_context, layers=3),
attender=MlpAttender(self.model_context),
trg_embedder=SimpleWordEmbedder(self.model_context,
vocab_size=100),
decoder=MlpSoftmaxDecoder(self.model_context, vocab_size=100),
)
model.set_train(False)
self.assert_single_loss_equals_batch_loss(model, pad_src_to_multiple=4)
def test_loss_model1(self):
model = DefaultTranslator(
src_embedder=SimpleWordEmbedder(self.model_context,
vocab_size=100),
encoder=BiLSTMSeqTransducer(self.model_context),
attender=MlpAttender(self.model_context),
trg_embedder=SimpleWordEmbedder(self.model_context,
vocab_size=100),
decoder=MlpSoftmaxDecoder(self.model_context, vocab_size=100),
)
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):
# Seeding
numpy.random.seed(2)
random.seed(2)
layer_dim = 64
xnmt.events.clear()
ParamManager.init_param_col()
self.segment_composer = SumComposer()
self.src_reader = CharFromWordTextReader()
self.trg_reader = PlainTextReader()
self.loss_calculator = AutoRegressiveMLELoss()
self.segmenting_encoder = SegmentingSeqTransducer(
segment_composer=self.segment_composer,
final_transducer=BiLSTMSeqTransducer(input_dim=layer_dim,
hidden_dim=layer_dim),
)
self.model = DefaultTranslator(
src_reader=self.src_reader,
trg_reader=self.trg_reader,
src_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100),
encoder=self.segmenting_encoder,
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,
rnn=UniLSTMSeqTransducer(input_dim=layer_dim,
hidden_dim=layer_dim,
decoder_input_dim=layer_dim,
yaml_path="decoder"),
transform=AuxNonLinear(input_dim=layer_dim,
output_dim=layer_dim,
aux_input_dim=layer_dim),
scorer=Softmax(vocab_size=100, input_dim=layer_dim),
trg_embed_dim=layer_dim,
bridge=CopyBridge(dec_dim=layer_dim, dec_layers=1)),
)
self.model.set_train(True)
self.layer_dim = layer_dim
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"))
my_batcher = xnmt.batcher.TrgBatcher(batch_size=3,
src_pad_token=1,
trg_pad_token=2)
self.src, self.trg = my_batcher.pack(self.src_data, self.trg_data)
dy.renew_cg(immediate_compute=True, check_validity=True)
def test_loss_model2(self):
model = DefaultTranslator(
src_reader=self.src_reader,
trg_reader=self.trg_reader,
src_embedder=SimpleWordEmbedder(self.exp_global, vocab_size=100),
encoder=PyramidalLSTMSeqTransducer(self.exp_global, layers=3),
attender=MlpAttender(self.exp_global),
trg_embedder=SimpleWordEmbedder(self.exp_global, vocab_size=100),
decoder=MlpSoftmaxDecoder(self.exp_global,
vocab_size=100,
bridge=CopyBridge(
exp_global=self.exp_global,
dec_layers=1)),
)
model.set_train(False)
self.assert_single_loss_equals_batch_loss(model, pad_src_to_multiple=4)
def test_loss_model3(self):
model = DefaultTranslator(
src_embedder=SimpleWordEmbedder(self.model_context,
vocab_size=100),
encoder=BiLSTMSeqTransducer(self.model_context, layers=3),
attender=MlpAttender(self.model_context),
trg_embedder=SimpleWordEmbedder(self.model_context,
vocab_size=100),
decoder=MlpSoftmaxDecoder(self.model_context,
vocab_size=100,
bridge=CopyBridge(self.model_context,
dec_layers=1)),
)
model.initialize_training_strategy(TrainingStrategy())
model.set_train(False)
self.assert_single_loss_equals_batch_loss(model)
def test_uni_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=UniLSTMSeqTransducer(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=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)),
)
self.assert_in_out_len_equal(model)
def test_uni_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=UniLSTMSeqTransducer(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,
lstm_dim=layer_dim,
mlp_hidden_dim=layer_dim,
trg_embed_dim=layer_dim,
vocab_size=100),
)
self.assert_in_out_len_equal(model)
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'] = LossCalculator()
train_args['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,
lstm_dim=layer_dim,
mlp_hidden_dim=layer_dim,
trg_embed_dim=layer_dim,
vocab_size=100,
bridge=CopyBridge(dec_layers=1,
dec_dim=layer_dim)),
)
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'] = None
train_args['batcher'] = batcher
train_args['run_for_epochs'] = 1
training_regimen = xnmt.training_regimen.SimpleTrainingRegimen(
**train_args)
training_regimen.run_training(save_fct=lambda: None,
update_weights=False)
self.assertAlmostEqual(training_regimen.logger.epoch_loss.sum() /
training_regimen.logger.epoch_words,
training_regimen.logger.dev_score.loss,
places=5)
def test_overfitting(self):
self.exp_global = ExpGlobal(
dynet_param_collection=NonPersistentParamCollection(), dropout=0.0)
self.exp_global.default_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'] = LossCalculator()
train_args['model'] = DefaultTranslator(
src_reader=PlainTextReader(),
trg_reader=PlainTextReader(),
src_embedder=SimpleWordEmbedder(self.exp_global, vocab_size=100),
encoder=BiLSTMSeqTransducer(self.exp_global),
attender=MlpAttender(self.exp_global),
trg_embedder=SimpleWordEmbedder(self.exp_global, vocab_size=100),
decoder=MlpSoftmaxDecoder(self.exp_global,
vocab_size=100,
bridge=CopyBridge(
exp_global=self.exp_global,
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(self.exp_global, alpha=0.1)
train_args['batcher'] = batcher
training_regimen = xnmt.training_regimen.SimpleTrainingRegimen(
exp_global=self.exp_global, **train_args)
training_regimen.exp_global = self.exp_global
for _ in range(50):
training_regimen.run_training(save_fct=lambda: None,
update_weights=True)
self.assertAlmostEqual(0.0,
training_regimen.logger.epoch_loss.sum() /
training_regimen.logger.epoch_words,
places=2)
def test_loss_model2(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),
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)),
)
model.set_train(False)
self.assert_single_loss_equals_batch_loss(model, pad_src_to_multiple=4)
def test_overfitting(self):
self.model_context = ModelContext()
self.model_context.dynet_param_collection = PersistentParamCollection(
"some_file", 1)
self.model_context.default_layer_dim = 16
train_args = {}
training_corpus = BilingualTrainingCorpus(
train_src="examples/data/head.ja",
train_trg="examples/data/head.en",
dev_src="examples/data/head.ja",
dev_trg="examples/data/head.en")
train_args['corpus_parser'] = BilingualCorpusParser(
training_corpus=training_corpus,
src_reader=PlainTextReader(),
trg_reader=PlainTextReader())
train_args['training_strategy'] = TrainingStrategy()
train_args['model'] = DefaultTranslator(
src_embedder=SimpleWordEmbedder(self.model_context,
vocab_size=100),
encoder=BiLSTMSeqTransducer(self.model_context),
attender=MlpAttender(self.model_context),
trg_embedder=SimpleWordEmbedder(self.model_context,
vocab_size=100),
decoder=MlpSoftmaxDecoder(self.model_context, vocab_size=100),
)
train_args['model_file'] = None
train_args['save_num_checkpoints'] = 0
train_args['trainer'] = AdamTrainer(self.model_context, alpha=0.1)
train_args['batcher'] = SrcBatcher(batch_size=10,
break_ties_randomly=False)
training_regimen = xnmt.train.TrainingRegimen(
yaml_context=self.model_context, **train_args)
training_regimen.model_context = self.model_context
for _ in range(50):
training_regimen.one_epoch(update_weights=True)
self.assertAlmostEqual(
0.0,
training_regimen.logger.epoch_loss.loss_values['loss'] /
training_regimen.logger.epoch_words,
places=2)
def test_loss_model2(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),
trg_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100),
decoder=MlpSoftmaxDecoder(input_dim=layer_dim,
lstm_dim=layer_dim,
mlp_hidden_dim=layer_dim,
trg_embed_dim=layer_dim,
vocab_size=100,
bridge=CopyBridge(dec_layers=1,
dec_dim=layer_dim)),
)
model.set_train(False)
self.assert_single_loss_equals_batch_loss(model, pad_src_to_multiple=4)
def test_train_dev_loss_equal(self):
self.model_context = ModelContext()
self.model_context.dynet_param_collection = NonPersistentParamCollection(
)
train_args = {}
training_corpus = BilingualTrainingCorpus(
train_src="examples/data/head.ja",
train_trg="examples/data/head.en",
dev_src="examples/data/head.ja",
dev_trg="examples/data/head.en")
train_args['corpus_parser'] = BilingualCorpusParser(
training_corpus=training_corpus,
src_reader=PlainTextReader(),
trg_reader=PlainTextReader())
train_args['loss_calculator'] = LossCalculator()
train_args['model'] = DefaultTranslator(
src_embedder=SimpleWordEmbedder(self.model_context,
vocab_size=100),
encoder=BiLSTMSeqTransducer(self.model_context),
attender=MlpAttender(self.model_context),
trg_embedder=SimpleWordEmbedder(self.model_context,
vocab_size=100),
decoder=MlpSoftmaxDecoder(self.model_context, vocab_size=100),
)
train_args['trainer'] = None
train_args['batcher'] = SrcBatcher(batch_size=5,
break_ties_randomly=False)
train_args['run_for_epochs'] = 1
training_regimen = xnmt.training_regimen.SimpleTrainingRegimen(
yaml_context=self.model_context, **train_args)
training_regimen.model_context = self.model_context
training_regimen.run_training(update_weights=False)
self.assertAlmostEqual(
training_regimen.logger.epoch_loss.loss_values['loss'] /
training_regimen.logger.epoch_words,
training_regimen.logger.dev_score.loss)
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),
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)),
)
self.set_train(True)
for sent_i in range(10):
dy.renew_cg()
src = self.src_data[sent_i].get_padded_sent(Vocab.ES, 4 - (self.src_data[sent_i].sent_len() % 4))
self.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 setUp(self):
# Seeding
numpy.random.seed(2)
random.seed(2)
layer_dim = 64
xnmt.events.clear()
ParamManager.init_param_col()
self.segment_encoder_bilstm = BiLSTMSeqTransducer(input_dim=layer_dim,
hidden_dim=layer_dim)
self.segment_composer = SumComposer()
self.src_reader = CharFromWordTextReader()
self.trg_reader = PlainTextReader()
self.loss_calculator = AutoRegressiveMLELoss()
baseline = Linear(input_dim=layer_dim, output_dim=1)
policy_network = Linear(input_dim=layer_dim, output_dim=2)
self.poisson_prior = PoissonPrior(mu=3.3)
self.eps_greedy = EpsilonGreedy(eps_prob=0.0, prior=self.poisson_prior)
self.conf_penalty = ConfidencePenalty()
self.policy_gradient = PolicyGradient(input_dim=layer_dim,
output_dim=2,
baseline=baseline,
policy_network=policy_network,
z_normalization=True,
conf_penalty=self.conf_penalty,
sample=5)
self.length_prior = PoissonLengthPrior(lmbd=3.3, weight=1)
self.segmenting_encoder = SegmentingSeqTransducer(
embed_encoder=self.segment_encoder_bilstm,
segment_composer=self.segment_composer,
final_transducer=BiLSTMSeqTransducer(input_dim=layer_dim,
hidden_dim=layer_dim),
policy_learning=self.policy_gradient,
eps_greedy=self.eps_greedy,
length_prior=self.length_prior,
)
self.model = DefaultTranslator(
src_reader=self.src_reader,
trg_reader=self.trg_reader,
src_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100),
encoder=self.segmenting_encoder,
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,
rnn=UniLSTMSeqTransducer(input_dim=layer_dim,
hidden_dim=layer_dim,
decoder_input_dim=layer_dim,
yaml_path="decoder"),
transform=AuxNonLinear(input_dim=layer_dim,
output_dim=layer_dim,
aux_input_dim=layer_dim),
scorer=Softmax(vocab_size=100, input_dim=layer_dim),
trg_embed_dim=layer_dim,
bridge=CopyBridge(dec_dim=layer_dim, dec_layers=1)),
)
self.model.set_train(True)
self.layer_dim = layer_dim
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"))
my_batcher = xnmt.batcher.TrgBatcher(batch_size=3,
src_pad_token=1,
trg_pad_token=2)
self.src, self.trg = my_batcher.pack(self.src_data, self.trg_data)
dy.renew_cg(immediate_compute=True, check_validity=True)
batcher = SrcBatcher(batch_size=64)
inference = SimpleInference(batcher=batcher)
layer_dim = 512
model = DefaultTranslator(
src_reader=PlainTextReader(vocab=src_vocab),
trg_reader=PlainTextReader(vocab=trg_vocab),
src_embedder=SimpleWordEmbedder(emb_dim=layer_dim,
vocab_size=len(src_vocab)),
encoder=BiLSTMSeqTransducer(input_dim=layer_dim,
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,
