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 test_bi_lstm_encoder_len(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,
layers=3),
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)),
)
self.assert_in_out_len_equal(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=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.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=LookupEmbedder(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=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(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 setUp(self):
# Seeding
numpy.random.seed(2)
random.seed(2)
layer_dim = 32
xnmt.events.clear()
ParamManager.init_param_col()
src_vocab = Vocab(vocab_file="examples/data/head.ja.vocab")
self.src_reader = CompoundReader(readers=[
PlainTextReader(vocab=src_vocab),
SimultActionTextReader()
], vocab=src_vocab)
self.trg_reader = PlainTextReader(vocab=Vocab(vocab_file="examples/data/head.en.vocab"))
self.layer_dim = layer_dim
self.src_data = list(self.src_reader.read_sents(["examples/data/head.ja", "examples/data/simult/head.jaen.actions"]))
self.trg_data = list(self.trg_reader.read_sents("examples/data/head.en"))
self.input_vocab_size = len(self.src_reader.vocab.i2w)
self.output_vocab_size = len(self.trg_reader.vocab.i2w)
self.loss_calculator = loss_calculators.MLELoss()
self.model = SimultaneousTranslator(
src_reader=self.src_reader,
trg_reader=self.trg_reader,
src_embedder=LookupEmbedder(emb_dim=layer_dim, vocab_size=self.input_vocab_size),
encoder=UniLSTMSeqTransducer(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,
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=self.output_vocab_size, input_dim=layer_dim),
embedder=LookupEmbedder(emb_dim=layer_dim, vocab_size=self.output_vocab_size),
bridge=NoBridge(dec_dim=layer_dim, dec_layers=1)),
policy_network = network.PolicyNetwork(transforms.MLP(2*self.layer_dim, self.layer_dim, 2)),
policy_train_oracle=True,
policy_test_oracle=True
)
event_trigger.set_train(True)
my_batcher = batchers.TrgBatcher(batch_size=3)
self.src, self.trg = my_batcher.pack(self.src_data, self.trg_data)
dy.renew_cg(immediate_compute=True, check_validity=True)
def setUp(self):
# Seeding
numpy.random.seed(2)
random.seed(2)
layer_dim = 32
xnmt.events.clear()
ParamManager.init_param_col()
edge_vocab = Vocab(vocab_file="examples/data/parse/head.en.edge_vocab")
node_vocab = Vocab(vocab_file="examples/data/parse/head.en.node_vocab")
value_vocab = Vocab(vocab_file="examples/data/head.en.vocab")
self.src_reader = input_readers.PlainTextReader(vocab=value_vocab)
self.trg_reader = input_readers.CoNLLToRNNGActionsReader(
surface_vocab=value_vocab,
nt_vocab=node_vocab,
edg_vocab=edge_vocab)
self.layer_dim = layer_dim
self.src_data = list(
self.src_reader.read_sents("examples/data/head.en"))
self.trg_data = list(
self.trg_reader.read_sents("examples/data/parse/head.en.conll"))
self.loss_calculator = MLELoss()
self.head_composer = composer.DyerHeadComposer(
fwd_combinator=UniLSTMSeqTransducer(input_dim=layer_dim,
hidden_dim=layer_dim),
bwd_combinator=UniLSTMSeqTransducer(input_dim=layer_dim,
hidden_dim=layer_dim),
transform=AuxNonLinear(input_dim=layer_dim,
aux_input_dim=layer_dim,
output_dim=layer_dim))
self.model = DefaultTranslator(
src_reader=self.src_reader,
trg_reader=self.trg_reader,
src_embedder=LookupEmbedder(emb_dim=layer_dim,
vocab_size=len(value_vocab)),
encoder=IdentitySeqTransducer(),
attender=MlpAttender(input_dim=layer_dim,
state_dim=layer_dim,
hidden_dim=layer_dim),
decoder=RNNGDecoder(
input_dim=layer_dim,
rnn=UniLSTMSeqTransducer(input_dim=layer_dim,
hidden_dim=layer_dim,
decoder_input_dim=layer_dim),
transform=AuxNonLinear(input_dim=layer_dim,
output_dim=layer_dim,
aux_input_dim=layer_dim),
bridge=NoBridge(dec_dim=layer_dim, dec_layers=1),
graph_reader=self.trg_reader,
head_composer=self.head_composer))
event_trigger.set_train(True)
my_batcher = batchers.TrgBatcher(batch_size=1)
self.src, self.trg = my_batcher.pack(self.src_data, self.trg_data)
dy.renew_cg(immediate_compute=True, check_validity=True)
def test_py_lstm_mask(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=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),
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)),
)
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)
def test_load(self):
"""
Checks that the embeddings can be loaded, have the right dimension, and that one line matches.
"""
embedder = LookupEmbedder(init_fastext='examples/data/wiki.ja.vec.small', emb_dim=300, vocab=self.input_reader.vocab)
# self.assertEqual(embedder.embeddings.shape()[::-1], (self.input_reader.vocab_size(), 300))
with open('examples/data/wiki.ja.vec.small', encoding='utf-8') as vecfile:
test_line = next(islice(vecfile, 9, None)).split() # Select the vector for '日'
test_word = test_line[0]
test_id = self.input_reader.vocab.w2i[test_word]
test_emb = test_line[1:]
self.assertTrue(np.allclose(embedder.embeddings.batch([test_id]).npvalue().tolist(),
np.array(test_emb, dtype=float).tolist(), rtol=1e-5))
def test_composite_composer(self):
composer = DyerHeadComposer(fwd_combinator=UniLSTMSeqTransducer(input_dim=self.layer_dim, hidden_dim=self.layer_dim),
bwd_combinator=UniLSTMSeqTransducer(input_dim=self.layer_dim, hidden_dim=self.layer_dim),
transform=AuxNonLinear(input_dim=self.layer_dim,
output_dim=self.layer_dim,
aux_input_dim=self.layer_dim))
embedder_1 = CharCompositionEmbedder(emb_dim=self.layer_dim,
composer=composer,
char_vocab=self.src_char_vocab)
embedder_2 = LookupEmbedder(emb_dim=self.layer_dim, vocab_size=100)
embedder = CompositeEmbedder(embedders=[embedder_1, embedder_2])
event_trigger.set_train(True)
event_trigger.start_sent(self.src[1])
embedder.embed_sent(self.src[1])
embedder.embed(self.src[1][0].words[0])
def test_lookup_composer(self): embedder = LookupEmbedder(emb_dim=self.layer_dim, vocab_size=100) embedder.embed_sent(self.src[1]) embedder.embed(self.src[1][1][1])
ParamManager.init_param_col()
ParamManager.param_col.model_file = model_file
src_vocab = Vocab(vocab_file="examples/data/head.ja.vocab")
trg_vocab = Vocab(vocab_file="examples/data/head.en.vocab")
batcher = SrcBatcher(batch_size=64)
inference = AutoRegressiveInference(batcher=InOrderBatcher(batch_size=1))
layer_dim = 512
model = DefaultTranslator(
src_reader=PlainTextReader(vocab=src_vocab),
trg_reader=PlainTextReader(vocab=trg_vocab),
src_embedder=LookupEmbedder(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),
decoder=AutoRegressiveDecoder(
input_dim=layer_dim,
embedder=LookupEmbedder(emb_dim=layer_dim, vocab_size=len(trg_vocab)),
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,