发票识别关系抽取运行推理时报错

[snowcakkke]

• 系统环境/System Environment：Linux
• 版本号/Version：Paddle：2.6.0 PaddleOCR：2.6 问题相关组件/Related components：发票识别场景
• 运行指令/Command Code：运行python3 tools/infer_kie_token_ser_re.py -c fapiao/re_vi_layoutxlm.yml -o Architecture.Backbone.checkpoints=fapiao/models/re_vi_layoutxlm_fapiao_udml/best_accuracy Global.infer_img=./train_data/zzsfp/val.json Global.infer_mode=True -c_ser fapiao/ser_vi_layoutxlm.yml -o_ser Architecture.Backbone.checkpoints=fapiao/models/ser_vi_layoutxlm_fapiao_udml/best_accuracy
• 完整报错/Complete Error Message：Traceback (most recent call last):
  File "/home/linmj/anaconda3/envs/bill_nlp/lib/python3.8/site-packages/flask/app.py", line 1488, in call
  return self.wsgi_app(environ, start_response)
  File "/home/linmj/anaconda3/envs/bill_nlp/lib/python3.8/site-packages/flask/app.py", line 1466, in wsgi_app
  response = self.handle_exception(e)
  File "/home/linmj/anaconda3/envs/bill_nlp/lib/python3.8/site-packages/flask/app.py", line 1463, in wsgi_app
  response = self.full_dispatch_request()
  File "/home/linmj/anaconda3/envs/bill_nlp/lib/python3.8/site-packages/flask/app.py", line 872, in full_dispatch_request
  rv = self.handle_user_exception(e)
  File "/home/linmj/anaconda3/envs/bill_nlp/lib/python3.8/site-packages/flask/app.py", line 870, in full_dispatch_request
  rv = self.dispatch_request()
  File "/home/linmj/anaconda3/envs/bill_nlp/lib/python3.8/site-packages/flask/app.py", line 855, in dispatch_request
  return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args) # type: ignore[no-any-return]
  File "/home/linmj/anaconda3/envs/bill_nlp/lib/python3.8/site-packages/flask_jwt_extended/view_decorators.py", line 170, in decorator
  return current_app.ensure_sync(fn)(*args, **kwargs)
  File "/home/linmj/PaddleOCR-release-2.6/api_bill_nlp.py", line 149, in bill_recognition
  response = picture_recognition(file)
  File "/home/linmj/PaddleOCR-release-2.6/api_bill_nlp.py", line 162, in picture_recognition
  results_re = ser_re_engine({'img_path': file_path})
  File "/home/linmj/PaddleOCR-release-2.6/tools/infer_kie_token_ser_re.py", line 151, in call
  preds = self.model(re_input)
  File "/home/linmj/anaconda3/envs/bill_nlp/lib/python3.8/site-packages/paddle/nn/layer/layers.py", line 1429, in call
  return self.forward(*inputs, **kwargs)
  File "/home/linmj/PaddleOCR-release-2.6/ppocr/modeling/architectures/base_model.py", line 86, in forward
  x = self.backbone(x)
  File "/home/linmj/anaconda3/envs/bill_nlp/lib/python3.8/site-packages/paddle/nn/layer/layers.py", line 1429, in call
  return self.forward(*inputs, **kwargs)
  File "/home/linmj/PaddleOCR-release-2.6/ppocr/modeling/backbones/vqa_layoutlm.py", line 227, in forward
  x = self.model(
  File "/home/linmj/anaconda3/envs/bill_nlp/lib/python3.8/site-packages/paddle/nn/layer/layers.py", line 1429, in call
  return self.forward(*inputs, **kwargs)
  File "/home/linmj/anaconda3/envs/bill_nlp/lib/python3.8/site-packages/paddlenlp/transformers/layoutxlm/modeling.py", line 1329, in forward
  loss, pred_relations = self.extractor(sequence_output, entities, relations)
  File "/home/linmj/anaconda3/envs/bill_nlp/lib/python3.8/site-packages/paddle/nn/layer/layers.py", line 1429, in call
  return self.forward(*inputs, **kwargs)
  File "/home/linmj/anaconda3/envs/bill_nlp/lib/python3.8/site-packages/paddlenlp/transformers/layoutxlm/modeling.py", line 1223, in forward
  relations, entities = self.build_relation(relations, entities)
  File "/home/linmj/anaconda3/envs/bill_nlp/lib/python3.8/site-packages/paddlenlp/transformers/layoutxlm/modeling.py", line 1189, in build_relation
  if negative_mask.sum() > 0:

[cuicheng01]

确保一下依赖包和PaddleOCR的要求是一样的呢？