def test_generator(self):
model = Seq2SeqModel.from_config(
Seq2SeqModel.Config(
source_embedding=WordEmbedding.Config(embed_dim=512),
target_embedding=WordEmbedding.Config(embed_dim=512),
),
self._get_tensorizers(),
)
sample, _ = get_example_and_check()
repacked_inputs = {
"src_tokens": sample[0].t(),
"src_lengths": sample[1]
}
scripted_generator = ScriptedSequenceGenerator(
[model.model], model.trg_eos_index,
ScriptedSequenceGenerator.Config())
scripted_preds = scripted_generator.generate_hypo(repacked_inputs)
self.assertIsNotNone(scripted_preds)
class Config(Model.Config):
class ModelInput(Model.Config.ModelInput):
src_seq_tokens: TokenTensorizer.Config = TokenTensorizer.Config()
trg_seq_tokens: TokenTensorizer.Config = TokenTensorizer.Config()
dict_feat: Optional[GazetteerTensorizer.Config] = None
inputs: ModelInput = ModelInput()
encoder_decoder: RNNModel.Config = RNNModel.Config()
source_embedding: WordEmbedding.Config = WordEmbedding.Config()
target_embedding: WordEmbedding.Config = WordEmbedding.Config()
dict_embedding: Optional[DictEmbedding.Config] = None
output_layer: Seq2SeqOutputLayer.Config = Seq2SeqOutputLayer.Config()
sequence_generator: ScriptedSequenceGenerator.Config = (
ScriptedSequenceGenerator.Config())