Please first search our GitHub repository for similar questions. If you don't find a similar example you can use the following template:
System (please complete the following information): - OS: Ubunti 18.04 - Python version: 3.6.7 - AllenNLP version: v0.8.3 - PyTorch version: 1.1.0
Question When I Try to predict string using SimpleSeq2SeqPredictor, It always show that
Traceback (most recent call last):
File "predict.py", line 96, in <module>
p = predictor.predict(i)
File "venv/lib/python3.6/site-packages/allennlp/predictors/seq2seq.py", line 17, in predict
return self.predict_json({"source" : source})
File "/venv/lib/python3.6/site-packages/allennlp/predictors/predictor.py", line 56, in predict_json
return self.predict_instance(instance)
File "/venv/lib/python3.6/site-packages/allennlp/predictors/predictor.py", line 93, in predict_instance
outputs = self._model.forward_on_instance(instance)
File "/venv/lib/python3.6/site-packages/allennlp/models/model.py", line 124, in forward_on_instance
return self.forward_on_instances([instance])[0]
File "/venv/lib/python3.6/site-packages/allennlp/models/model.py", line 153, in forward_on_instances
outputs = self.decode(self(**model_input))
File "/venv/lib/python3.6/site-packages/allennlp/models/encoder_decoders/simple_seq2seq.py", line 247, in decode
predicted_indices = output_dict["predictions"]
KeyError: 'predictions'
I try to do a translate system, but I am newbie, most of code come from https://github.com/mhagiwara/realworldnlp/blob/master/examples/mt/mt.py http://www.realworldnlpbook.com/blog/building-seq2seq-machine-translation-models-using-allennlp.html
this is my training code
EN_EMBEDDING_DIM = 256
ZH_EMBEDDING_DIM = 256
HIDDEN_DIM = 256
CUDA_DEVICE = 0
prefix = 'small'
reader = Seq2SeqDatasetReader(
source_tokenizer=WordTokenizer(),
target_tokenizer=CharacterTokenizer(),
source_token_indexers={'tokens': SingleIdTokenIndexer()},
target_token_indexers={'tokens': SingleIdTokenIndexer(namespace='target_tokens')},
lazy = True)
train_dataset = reader.read(f'./{prefix}-data/train.tsv')
validation_dataset = reader.read(f'./{prefix}-data/val.tsv')
vocab = Vocabulary.from_instances(train_dataset,
min_count={'tokens': 3, 'target_tokens': 3})
en_embedding = Embedding(num_embeddings=vocab.get_vocab_size('tokens'),
embedding_dim=EN_EMBEDDING_DIM)
# encoder = PytorchSeq2SeqWrapper(
# torch.nn.LSTM(EN_EMBEDDING_DIM, HIDDEN_DIM, batch_first=True))
encoder = StackedSelfAttentionEncoder(input_dim=EN_EMBEDDING_DIM, hidden_dim=HIDDEN_DIM, projection_dim=128, feedforward_hidden_dim=128, num_layers=1, num_attention_heads=8)
source_embedder = BasicTextFieldEmbedder({"tokens": en_embedding})
# attention = LinearAttention(HIDDEN_DIM, HIDDEN_DIM, activation=Activation.by_name('tanh')())
# attention = BilinearAttention(HIDDEN_DIM, HIDDEN_DIM)
attention = DotProductAttention()
max_decoding_steps = 20 # TODO: make this variable
model = SimpleSeq2Seq(vocab, source_embedder, encoder, max_decoding_steps,
target_embedding_dim=ZH_EMBEDDING_DIM,
target_namespace='target_tokens',
attention=attention,
beam_size=8,
use_bleu=True)
optimizer = optim.Adam(model.parameters())
iterator = BucketIterator(batch_size=32, sorting_keys=[("source_tokens", "num_tokens")])
iterator.index_with(vocab)
if torch.cuda.is_available():
cuda_device = 0
model = model.cuda(cuda_device)
else:
cuda_device = -1
trainer = Trainer(model=model,
optimizer=optimizer,
iterator=iterator,
train_dataset=train_dataset,
validation_dataset=validation_dataset,
num_epochs=50,
serialization_dir=f'ck/{prefix}/',
cuda_device=cuda_device)
# for i in range(50):
# print('Epoch: {}'.format(i))
trainer.train()
predictor = SimpleSeq2SeqPredictor(model, reader)
for instance in itertools.islice(validation_dataset, 10):
print('SOURCE:', instance.fields['source_tokens'].tokens)
print('GOLD:', instance.fields['target_tokens'].tokens)
print('PRED:', predictor.predict_instance(instance)['predicted_tokens'])
# Here's how to save the model.
with open(f"ck/{prefix}/manually_save_model.th", 'wb') as f:
torch.save(model.state_dict(), f)
vocab.save_to_files(f"ck/{prefix}/vocabulary")
and this is my predict code
EN_EMBEDDING_DIM = 256
ZH_EMBEDDING_DIM = 256
HIDDEN_DIM = 256
CUDA_DEVICE = 0
prefix = 'big'
reader = Seq2SeqDatasetReader(
source_tokenizer=WordTokenizer(),
target_tokenizer=CharacterTokenizer(),
source_token_indexers={'tokens': SingleIdTokenIndexer()},
target_token_indexers={'tokens': SingleIdTokenIndexer(namespace='target_tokens')},
lazy = True)
# train_dataset = reader.read(f'./{prefix}-data/train.tsv')
# validation_dataset = reader.read(f'./{prefix}-data/val.tsv')
# vocab = Vocabulary.from_instances(train_dataset,
# min_count={'tokens': 3, 'target_tokens': 3})
vocab = Vocabulary.from_files("ck/small/vocabulary")
en_embedding = Embedding(num_embeddings=vocab.get_vocab_size('tokens'),
embedding_dim=EN_EMBEDDING_DIM)
# encoder = PytorchSeq2SeqWrapper(
# torch.nn.LSTM(EN_EMBEDDING_DIM, HIDDEN_DIM, batch_first=True))
encoder = StackedSelfAttentionEncoder(input_dim=EN_EMBEDDING_DIM, hidden_dim=HIDDEN_DIM, projection_dim=128, feedforward_hidden_dim=128, num_layers=1, num_attention_heads=8)
source_embedder = BasicTextFieldEmbedder({"tokens": en_embedding})
# attention = LinearAttention(HIDDEN_DIM, HIDDEN_DIM, activation=Activation.by_name('tanh')())
# attention = BilinearAttention(HIDDEN_DIM, HIDDEN_DIM)
attention = DotProductAttention()
max_decoding_steps = 20 # TODO: make this variable
model = SimpleSeq2Seq(vocab, source_embedder, encoder, max_decoding_steps,
target_embedding_dim=ZH_EMBEDDING_DIM,
target_namespace='target_tokens',
attention=attention,
beam_size=8,
use_bleu=True)
# And here's how to reload the model.
with open("./ck/small/best.th", 'rb') as f:
model.load_state_dict(torch.load(f))
predictor = Seq2SeqPredictor(model, dataset_reader=reader)
# print(predictor.predict("The dog ate the apple"))
test = [
'Surely ,he has no power over those who believe and put their trust in their Lord ;',
'And assuredly We have destroyed the generations before you when they did wrong ,while their apostles came unto them with the evidences ,and they were not such as to believe . In this wise We requite the sinning people .',
'And warn your tribe ( O Muhammad SAW ) of near kindred .',
'And to the Noble Messengers whom We have mentioned to you before ,and to the Noble Messengers We have not mentioned to you ; and Allah really did speak to Moosa .',
'It is He who gave you hearing ,sight ,and hearts ,but only few of you give thanks .',
'spreading in them much corruption ?',
'That will envelop the people . This will be a painful punishment .',
'When you received it with your tongues and spoke with your mouths what you had no knowledge of ,and you deemed it an easy matter while with Allah it was grievous .',
'of which you are disregardful .',
'Whoever disbelieves ,then the calamity of his disbelief is only on him ; and those who do good deeds ,are preparing for themselves .'
]
for i in test:
p = predictor.predict(i) # <------------------- ERROR !!!!!!!
print(p)
Am I do something wrong ?
solved
I forgot add model.eval() after load model.
Sorry