BC-LSTM text unimodal checkpoint is broken

[SeanXiaoyuSun]

I could run audio unimodal and bimodal BC-LSTM pretrained model, but got the following error when running text unimodal BC-LSTM.

Model initiated for Sentiment classification
Loading data
Labels used for this classification:  {'neutral': 0, 'positive': 1, 'negative': 2}
Traceback (most recent call last):
  File "baseline.py", line 312, in <module>
    model.test_model()
  File "baseline.py", line 234, in test_model
    model = load_model(self.PATH)
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/saving/save.py", line 200, in load_model
    return hdf5_format.load_model_from_hdf5(filepath, custom_objects,
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/saving/hdf5_format.py", line 180, in load_model_from_hdf5
    model = model_config_lib.model_from_config(model_config,
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/saving/model_config.py", line 52, in model_from_config
    return deserialize(config, custom_objects=custom_objects)
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/layers/serialization.py", line 208, in deserialize
    return generic_utils.deserialize_keras_object(
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/utils/generic_utils.py", line 674, in deserialize_keras_object
    deserialized_obj = cls.from_config(
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/engine/training.py", line 2397, in from_config
    functional.reconstruct_from_config(config, custom_objects))
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/engine/functional.py", line 1273, in reconstruct_from_config
    process_layer(layer_data)
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/engine/functional.py", line 1255, in process_layer
    layer = deserialize_layer(layer_data, custom_objects=custom_objects)
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/layers/serialization.py", line 208, in deserialize
    return generic_utils.deserialize_keras_object(
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/utils/generic_utils.py", line 674, in deserialize_keras_object
    deserialized_obj = cls.from_config(
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/layers/core.py", line 1005, in from_config
    function = cls._parse_function_from_config(
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/layers/core.py", line 1057, in _parse_function_from_config
    function = generic_utils.func_load(
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/utils/generic_utils.py", line 789, in func_load
    code = marshal.loads(raw_code)
ValueError: bad marshal data (unknown type code)

The command I'm running is:
python baseline.py -classify sentiment -modality text -test.

[Triaill]

I could run audio unimodal and bimodal BC-LSTM pretrained model, but got the following error when running text unimodal BC-LSTM.我可以运行音频单峰和双峰 BC-LSTM 预训练模型，但在运行文本单峰 BC-LSTM 时出现以下错误。

Model initiated for Sentiment classification
Loading data
Labels used for this classification:  {'neutral': 0, 'positive': 1, 'negative': 2}
Traceback (most recent call last):
  File "baseline.py", line 312, in <module>
    model.test_model()
  File "baseline.py", line 234, in test_model
    model = load_model(self.PATH)
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/saving/save.py", line 200, in load_model
    return hdf5_format.load_model_from_hdf5(filepath, custom_objects,
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/saving/hdf5_format.py", line 180, in load_model_from_hdf5
    model = model_config_lib.model_from_config(model_config,
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/saving/model_config.py", line 52, in model_from_config
    return deserialize(config, custom_objects=custom_objects)
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/layers/serialization.py", line 208, in deserialize
    return generic_utils.deserialize_keras_object(
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/utils/generic_utils.py", line 674, in deserialize_keras_object
    deserialized_obj = cls.from_config(
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/engine/training.py", line 2397, in from_config
    functional.reconstruct_from_config(config, custom_objects))
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/engine/functional.py", line 1273, in reconstruct_from_config
    process_layer(layer_data)
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/engine/functional.py", line 1255, in process_layer
    layer = deserialize_layer(layer_data, custom_objects=custom_objects)
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/layers/serialization.py", line 208, in deserialize
    return generic_utils.deserialize_keras_object(
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/utils/generic_utils.py", line 674, in deserialize_keras_object
    deserialized_obj = cls.from_config(
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/layers/core.py", line 1005, in from_config
    function = cls._parse_function_from_config(
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/layers/core.py", line 1057, in _parse_function_from_config
    function = generic_utils.func_load(
  File "/Users/xiaoyu/.pyenv/versions/3.8.7/lib/python3.8/site-packages/keras/utils/generic_utils.py", line 789, in func_load
    code = marshal.loads(raw_code)
ValueError: bad marshal data (unknown type code)

The command I'm running is:我正在运行的命令是： python baseline.py -classify sentiment -modality text -test.

I meet the same problem, could you tell me how you solved it?