|
--- |
|
license: afl-3.0 |
|
--- |
|
|
|
# ERNIE-Layout_Pytorch |
|
|
|
This is an unofficial Pytorch implementation of [ERNIE-Layout](http://arxiv.org/abs/2210.06155) which is originally released through PaddleNLP. |
|
|
|
|
|
**A Quick Example** |
|
```python |
|
from networks.modeling_erine_layout import ErnieLayoutConfig, ErnieLayoutForQuestionAnswering |
|
from networks.tokenizer import ErnieLayoutTokenizer |
|
|
|
|
|
pretrain_torch_model_or_path = "path/to/pretrained-model" |
|
|
|
# initialize tokenizer |
|
tokenizer = ErnieLayoutTokenizer.from_pretrained(pretrained_model_name_or_path=pretrain_torch_model_or_path) |
|
encodings = tokenizer.encode_plus(text="Question", text_pair="Answer", add_special_tokens=True, |
|
max_length=512, truncation="only_second", |
|
return_offsets_mapping=True, return_attention_mask=True, |
|
return_overflowing_tokens=True) |
|
|
|
# initialize config |
|
config = ErnieLayoutConfig.from_pretrained(pretrained_model_name_or_path=pretrain_torch_model_or_path) |
|
config.num_classes = 2 |
|
|
|
# initialize ERNIE for VQA |
|
model = ErnieLayoutForQuestionAnswering.from_pretrained( |
|
pretrained_model_name_or_path=pretrain_torch_model_or_path, |
|
config=config, |
|
) |
|
|
|
``` |