def convert_tf_checkpoint_to_pytorch(tf_checkpoint_path, mobilebert_config_file, pytorch_dump_path):
# Initialise PyTorch model
config = MobileBertConfig.from_json_file(mobilebert_config_file)
print(f"Building PyTorch model from configuration: {config}")
model = MobileBertForPreTraining(config)
# Load weights from tf checkpoint
model = load_tf_weights_in_mobilebert(model, config, tf_checkpoint_path)
# Save pytorch-model
print(f"Save PyTorch model to {pytorch_dump_path}")
torch.save(model.state_dict(), pytorch_dump_path)
def create_and_check_mobilebert_for_pretraining(self, config, input_ids,
token_type_ids, input_mask,
sequence_labels,
token_labels,
choice_labels):
model = MobileBertForPreTraining(config=config)
model.to(torch_device)
model.eval()
loss, prediction_scores, seq_relationship_score = model(
input_ids,
attention_mask=input_mask,
token_type_ids=token_type_ids,
labels=token_labels,
next_sentence_label=sequence_labels,
)
result = {
"loss": loss,
"prediction_scores": prediction_scores,
"seq_relationship_score": seq_relationship_score,
}
self.parent.assertListEqual(
list(result["prediction_scores"].size()),
[self.batch_size, self.seq_length, self.vocab_size])
self.parent.assertListEqual(
list(result["seq_relationship_score"].size()),
[self.batch_size, 2])
self.check_loss_output(result)
def create_and_check_mobilebert_for_pretraining(
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
):
model = MobileBertForPreTraining(config=config)
model.to(torch_device)
model.eval()
result = model(
input_ids,
attention_mask=input_mask,
token_type_ids=token_type_ids,
labels=token_labels,
next_sentence_label=sequence_labels,
)
self.parent.assertEqual(result.prediction_logits.shape, (self.batch_size, self.seq_length, self.vocab_size))
self.parent.assertEqual(result.seq_relationship_logits.shape, (self.batch_size, 2))