def test_TFRobertaForMaskedLM(self):
from transformers import RobertaConfig, TFRobertaForMaskedLM
keras.backend.clear_session()
# pretrained_weights = 'roberta-base'
tokenizer_file = 'roberta_roberta-base.pickle'
tokenizer = self._get_tokenzier(tokenizer_file)
text, inputs, inputs_onnx = self._prepare_inputs(tokenizer)
config = RobertaConfig()
model = TFRobertaForMaskedLM(config)
predictions = model.predict(inputs)
onnx_model = keras2onnx.convert_keras(model, model.name)
self.assertTrue(
run_onnx_runtime(onnx_model.graph.name, onnx_model, inputs_onnx, predictions, self.model_files, rtol=1.e-2,
atol=1.e-4))
def test_TFRobertaForMaskedLM(self):
from transformers import RobertaTokenizer, TFRobertaForMaskedLM
pretrained_weights = 'roberta-base'
tokenizer = RobertaTokenizer.from_pretrained(pretrained_weights)
text, inputs, inputs_onnx = self._prepare_inputs(tokenizer)
model = TFRobertaForMaskedLM.from_pretrained(pretrained_weights)
predictions = model.predict(inputs)
onnx_model = keras2onnx.convert_keras(model, model.name)
self.assertTrue(
run_onnx_runtime(onnx_model.graph.name,
onnx_model,
inputs_onnx,
predictions,
self.model_files,
rtol=1.e-2,
atol=1.e-4))
def get_pretrained_roberta(pretrained_model):
# NOTE: This will be pretrained unlike our analogous method for bert.
return TFRobertaForMaskedLM.from_pretrained(
pretrained_model, from_pt=roberta.from_pt(pretrained_model))