class EncoderPairwiseModelInput(ModelInputBase):
tokens1: Tensorizer.Config = Tensorizer.Config()
tokens2: Tensorizer.Config = Tensorizer.Config()
labels: LabelTensorizer.Config = LabelTensorizer.Config()
# for metric reporter
num_tokens: NtokensTensorizer.Config = NtokensTensorizer.Config(
names=["tokens1", "tokens2"], indexes=[2, 2])
class EncoderModelInput(BaseModel.Config.ModelInput):
tokens: Tensorizer.Config = Tensorizer.Config()
dense: Optional[FloatListTensorizer.Config] = None
labels: LabelTensorizer.Config = LabelTensorizer.Config()
# for metric reporter
num_tokens: NtokensTensorizer.Config = NtokensTensorizer.Config(
names=["tokens"], indexes=[2])
class InputConfig(ConfigBase):
right_tokens: RoBERTaTensorizer.Config = RoBERTaTensorizer.Config()
left_tokens: RoBERTaTensorizer.Config = RoBERTaTensorizer.Config()
right_dense: Optional[FloatListTensorizer.Config] = None
left_dense: Optional[FloatListTensorizer.Config] = None
labels: LabelTensorizer.Config = LabelTensorizer.Config()
def test_batch_predict_caffe2_model(self):
with tempfile.NamedTemporaryFile() as snapshot_file, tempfile.NamedTemporaryFile() as caffe2_model_file:
train_data = tests_module.test_file("train_data_tiny.tsv")
eval_data = tests_module.test_file("test_data_tiny.tsv")
config = PyTextConfig(
task=DocumentClassificationTask.Config(
model=DocModel.Config(
inputs=DocModel.Config.ModelInput(
tokens=TokenTensorizer.Config(),
dense=FloatListTensorizer.Config(
column="dense", dim=1, error_check=True
),
labels=LabelTensorizer.Config(),
)
),
data=Data.Config(
source=TSVDataSource.Config(
train_filename=train_data,
eval_filename=eval_data,
test_filename=eval_data,
field_names=["label", "slots", "text", "dense"],
)
),
),
version=21,
save_snapshot_path=snapshot_file.name,
export_caffe2_path=caffe2_model_file.name,
)
task = create_task(config.task)
task.export(task.model, caffe2_model_file.name)
model = task.model
save(config, model, meta=None, tensorizers=task.data.tensorizers)
pt_results = task.predict(task.data.data_source.test)
def assert_caffe2_results_correct(caffe2_results):
for pt_res, res in zip(pt_results, caffe2_results):
np.testing.assert_array_almost_equal(
pt_res["score"].tolist()[0],
[score[0] for score in res.values()],
)
results = batch_predict_caffe2_model(
snapshot_file.name, caffe2_model_file.name
)
self.assertEqual(4, len(results))
assert_caffe2_results_correct(results)
results = batch_predict_caffe2_model(
snapshot_file.name, caffe2_model_file.name, cache_size=2
)
self.assertEqual(4, len(results))
assert_caffe2_results_correct(results)
results = batch_predict_caffe2_model(
snapshot_file.name, caffe2_model_file.name, cache_size=-1
)
self.assertEqual(4, len(results))
assert_caffe2_results_correct(results)
class ModelInput(Model.Config.ModelInput):
tokens: TokenTensorizer.Config = TokenTensorizer.Config()
word_labels: SlotLabelTensorizer.Config = SlotLabelTensorizer.Config(
allow_unknown=True)
doc_labels: LabelTensorizer.Config = LabelTensorizer.Config(
allow_unknown=True)
doc_weight: Optional[FloatTensorizer.Config] = None
word_weight: Optional[FloatTensorizer.Config] = None
class BertModelInput(BaseModel.Config.ModelInput):
tokens: BERTTensorizer.Config = BERTTensorizer.Config(max_seq_len=128)
dense: Optional[FloatListTensorizer.Config] = None
labels: LabelTensorizer.Config = LabelTensorizer.Config()
# for metric reporter
num_tokens: NtokensTensorizer.Config = NtokensTensorizer.Config(
names=["tokens"], indexes=[2]
)
class ModelInput(BasePairwiseModel.Config.ModelInput):
tokens1: TokenTensorizer.Config = TokenTensorizer.Config(column="text1")
tokens2: TokenTensorizer.Config = TokenTensorizer.Config(column="text2")
labels: LabelTensorizer.Config = LabelTensorizer.Config()
# for metric reporter
raw_text: JoinStringTensorizer.Config = JoinStringTensorizer.Config(
columns=["text1", "text2"]
)
class ModelInput(BaseModel.Config.ModelInput):
squad_input: Union[
SquadForBERTTensorizer.Config, SquadForRoBERTaTensorizer.Config
] = SquadForBERTTensorizer.Config(max_seq_len=256)
# is_impossible label
has_answer: LabelTensorizer.Config = LabelTensorizer.Config(
column="has_answer"
)
class ModelInput(ModelInputBase):
tokens1: BERTTensorizerBase.Config = BERTTensorizer.Config(
columns=["text1"], max_seq_len=128)
tokens2: BERTTensorizerBase.Config = BERTTensorizer.Config(
columns=["text2"], max_seq_len=128)
labels: LabelTensorizer.Config = LabelTensorizer.Config()
# for metric reporter
num_tokens: NtokensTensorizer.Config = NtokensTensorizer.Config(
names=["tokens1", "tokens2"], indexes=[2, 2])
class ModelInput(Model.Config.ModelInput):
tokens: TokenTensorizer.Config = TokenTensorizer.Config()
word_labels: SlotLabelTensorizer.Config = SlotLabelTensorizer.Config(
allow_unknown=True)
doc_labels: LabelTensorizer.Config = LabelTensorizer.Config(
allow_unknown=True)
doc_weight: FloatTensorizer.Config = FloatTensorizer.Config(
column="doc_weight")
word_weight: FloatTensorizer.Config = FloatTensorizer.Config(
column="word_weight")
class InputConfig(ConfigBase):
tokens: RoBERTaTensorizer.Config = RoBERTaTensorizer.Config()
labels: LabelTensorizer.Config = LabelTensorizer.Config()
class ModelInput(Model.Config.ModelInput):
tokens: WordTensorizer.Config = WordTensorizer.Config()
labels: LabelTensorizer.Config = LabelTensorizer.Config(
allow_unknown=True)
# for metric reporter
raw_text: MetaInput.Config = MetaInput.Config(column="text")
class ModelInput(Model.Config.ModelInput):
tokens: TokenTensorizer.Config = TokenTensorizer.Config()
labels: LabelTensorizer.Config = LabelTensorizer.Config()
class ModelInput(Model.Config.ModelInput):
tokens: TokenTensorizer.Config = TokenTensorizer.Config()
labels: LabelTensorizer.Config = LabelTensorizer.Config(allow_unknown=True)
# for metric reporter
raw_text: RawString.Config = RawString.Config(column="text")
class ModelInput(Model.Config.ModelInput):
tokens: TokenTensorizer.Config = TokenTensorizer.Config()
dense: Optional[FloatListTensorizer.Config] = None
labels: LabelTensorizer.Config = LabelTensorizer.Config()
class InputConfig(ConfigBase):
tokens: RoBERTaTensorizer.Config = RoBERTaTensorizer.Config()
right_dense: FloatListTensorizer.Config = None
left_dense: FloatListTensorizer.Config = None
labels: LabelTensorizer.Config = LabelTensorizer.Config()
class Config(Model.Config, doc_model.DocModel.Config):
inputs: Dict[str, Tensorizer.Config] = {
"tokens": WordTensorizer.Config(),
"labels": LabelTensorizer.Config(),
}
embedding: WordFeatConfig = WordFeatConfig()
class ModelInput(BasePairwiseModel.Config.ModelInput):
tokens1: TokenTensorizer.Config = TokenTensorizer.Config(
column="text1")
tokens2: TokenTensorizer.Config = TokenTensorizer.Config(
column="text2")
labels: LabelTensorizer.Config = LabelTensorizer.Config()
class ModelInput(BaseModel.Config.ModelInput):
squad_input: SquadTensorizer.Config = SquadTensorizer.Config()
has_answer: LabelTensorizer.Config = LabelTensorizer.Config(
column="has_answer")
class ModelInput(NewModel.Config.ModelInput):
tokens: WordTensorizer.Config = WordTensorizer.Config()
labels: LabelTensorizer.Config = LabelTensorizer.Config(allow_unknown=True)
