def create_and_check_xlm_model(
self,
config,
input_ids,
token_type_ids,
input_lengths,
sequence_labels,
token_labels,
is_impossible_labels,
choice_labels,
input_mask,
):
model = TFXLMModel(config=config)
inputs = {
"input_ids": input_ids,
"lengths": input_lengths,
"langs": token_type_ids
}
result = model(inputs)
inputs = [input_ids, input_mask]
result = model(inputs)
self.parent.assertEqual(
result.last_hidden_state.shape,
(self.batch_size, self.seq_length, self.hidden_size))
def create_and_check_xlm_model(
self,
config,
input_ids,
token_type_ids,
input_lengths,
sequence_labels,
token_labels,
is_impossible_labels,
input_mask,
):
model = TFXLMModel(config=config)
inputs = {
"input_ids": input_ids,
"lengths": input_lengths,
"langs": token_type_ids
}
outputs = model(inputs)
inputs = [input_ids, input_mask]
outputs = model(inputs)
sequence_output = outputs[0]
result = {
"sequence_output": sequence_output.numpy(),
}
self.parent.assertListEqual(
list(result["sequence_output"].shape),
[self.batch_size, self.seq_length, self.hidden_size])
def test_TFXLMModel(self):
from transformers import XLMConfig, TFXLMModel
keras.backend.clear_session()
# pretrained_weights = 'xlm-mlm-enfr-1024'
tokenizer_file = 'xlm_xlm-mlm-enfr-1024.pickle'
tokenizer = self._get_tokenzier(tokenizer_file)
text, inputs, inputs_onnx = self._prepare_inputs(tokenizer)
config = XLMConfig()
model = TFXLMModel(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))
