表格识别报错

[ChaoII]

表格识别训练、评估没有问题（但是根据example中的数据训练完acc一直是0），但是在执行预测命令后报错

(paddle) D:\PaddleX>python main.py -c paddlex/configs/table_recognition/SLANet.yaml ^
More?     -o Global.mode=predict ^
More?     -o Predict.model_dir="./output/best_accuracy" ^
More?     -o Predict.input_path="./dataset/table_rec_dataset_examples/images/border_19_0TKFMWCF3STF5QF1BJ3N.jpg" ^
More?     -o Global.output="output"

报错信息：

The device id has been set to 0.
Traceback (most recent call last):
  File "D:\PaddleX\paddlex\utils\result_saver.py", line 30, in wrap
    result = func(self, *args, **kwargs)
  File "D:\PaddleX\paddlex\engine.py", line 49, in run
    predictor = build_predictor(self.config)
  File "D:\PaddleX\paddlex\modules\base\predictor\predictor.py", line 189, in build_predictor
    return PredictorBuilderByConfig(*args, **kwargs)
  File "D:\PaddleX\paddlex\modules\base\predictor\predictor.py", line 173, in __init__
    self.predictor = BasePredictor.get(model_name)(
  File "D:\PaddleX\paddlex\modules\base\predictor\utils\node.py", line 43, in _wrapper
    ret = init_func(self, *args, **kwargs)
  File "D:\PaddleX\paddlex\modules\table_recognition\predictor\predictor.py", line 41, in __init__
    super().__init__(
  File "D:\PaddleX\paddlex\modules\base\predictor\utils\node.py", line 43, in _wrapper
    ret = init_func(self, *args, **kwargs)
  File "D:\PaddleX\paddlex\modules\base\predictor\predictor.py", line 56, in __init__
    self.pre_tfs, self.post_tfs = self.build_transforms(pre_transforms,
  File "D:\PaddleX\paddlex\modules\base\predictor\predictor.py", line 67, in build_transforms
    pre_tfs = pre_transforms if pre_transforms is not None else self._get_pre_transforms_from_config(
  File "D:\PaddleX\paddlex\modules\table_recognition\predictor\predictor.py", line 84, in _get_pre_transforms_from_config
    image_common.ResizeByLong(target_long_edge=self.table_max_len),
AttributeError: 'TableRecPredictor' object has no attribute 'table_max_len'

windows11 x64
python3.10
paddle 3.0.0b1
感觉像是通过父类调子类的方法，是不是zaiwindows上和其他平台上有不同的表现？

[cuicheng01]

您好，问题我们已经收到，我们尝试复现下

[cuicheng01]

@ChaoII 您好，问题已经修复，可以使用最新的代码尝试下~

[TrioTea]

@cuicheng01
【根据example中的数据训练完acc一直是0】

您好，请问这个问题有解决吗？