python中keras软件包无法使用

为什么我明明安装了keras软件包，但是却一直程序报错说我没安装

Using TensorFlow backend.
Traceback (most recent call last):
  File "D:\py-project\bert_for_ner\bert_for_ner\build_model.py", line 2, in <module>
    import keras
  File "D:\py-project\venv\Lib\site-packages\keras\__init__.py", line 3, in <module>
    from . import utils
  File "D:\py-project\venv\Lib\site-packages\keras\utils\__init__.py", line 26, in <module>
    from .vis_utils import model_to_dot
  File "D:\py-project\venv\Lib\site-packages\keras\utils\vis_utils.py", line 7, in <module>
    from ..models import Model
  File "D:\py-project\venv\Lib\site-packages\keras\models.py", line 10, in <module>
    from .engine.input_layer import Input
  File "D:\py-project\venv\Lib\site-packages\keras\engine\__init__.py", line 8, in <module>
    from .training import Model
  File "D:\py-project\venv\Lib\site-packages\keras\engine\training.py", line 14, in <module>
    from . import training_utils
  File "D:\py-project\venv\Lib\site-packages\keras\engine\training_utils.py", line 17, in <module>
    from .. import metrics as metrics_module
  File "D:\py-project\venv\Lib\site-packages\keras\metrics.py", line 1850, in <module>
    BaseMeanIoU = tf.keras.metrics.MeanIoU
                  ^^^^^^^^^^^^^^^^
  File "D:\py-project\venv\Lib\site-packages\tensorflow\python\util\lazy_loader.py", line 58, in __getattr__
    module = self._load()
             ^^^^^^^^^^^^
  File "D:\py-project\venv\Lib\site-packages\tensorflow\python\util\lazy_loader.py", line 41, in _load
    module = importlib.import_module(self.__name__)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\Python\py\Lib\importlib\__init__.py", line 126, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'keras.api'

之前报下面这个错误，我搜了一下说是因为版本不匹配，我就在设置，软件包那个位置把tensorflow，keras，bert4keras全部卸了想重新装低版本的，但是没全装成功，后来我就在软件包那里重新把这几个都安装了一下，安装后再跑程序就报错说没有keras了

AttributeError: module 'keras.engine.base_layer' has no attribute 'Node'

• 这篇博客也许可以解决你的问题👉 ：使用keras-bert实现 谭松波 酒店评论 文本分类（情感分析）
• 除此之外, 这篇博客: 基于Keras_bert模型的Bert使用与字词预测中的 2.3 多句子特征提取 部分也许能够解决你的问题, 你可以仔细阅读以下内容或跳转源博客中阅读:
  

• 和前面一样，可以实现多个句子的特征提取

  #----------------------------第三步 多句子特征提取------------------------------
  text1 = '语言模型'
  text2 = "你好"
  tokens1 = tokenizer.tokenize(text1)
  print(tokens1)
  tokens2 = tokenizer.tokenize(text2)
  print(tokens2)
   
  indices_new, segments_new = tokenizer.encode(first=text1, second=text2 ,max_len=512)
  print(indices_new[:10])
  #[101, 6427, 6241, 3563, 1798, 102, 0, 0, 0, 0]
  print(segments_new[:10])
  #[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
   
  #提取特征
  predicts_new = model.predict([np.array([indices_new]), np.array([segments_new])])[0]
  for i, token in enumerate(tokens1):
      print(token, predicts_new[i].tolist()[:5])
  for i, token in enumerate(tokens2):
      print(token, predicts_new[i].tolist()[:5])
  

  [‘[CLS]’, ‘语’, ‘言’, ‘模’, ‘型’, ‘[SEP]’]
  [‘[CLS]’, ‘你’, ‘好’, ‘[SEP]’]
  [101, 6427, 6241, 3563, 1798, 102, 872, 1962, 102, 0]
  [0, 0, 0, 0, 0, 0, 1, 1, 1, 0]
  [CLS] [-0.3404940962791443, 0.5169003009796143, 0.8958081603050232, -0.5850763916969299, 0.1620779037475586]
  语 [-0.6919717788696289, 0.37331458926200867, 1.3196662664413452, -0.0865214616060257, 0.5522887110710144]
  言 [0.6706017851829529, -0.5946153402328491, 0.4751562178134918, -0.7590199112892151, 0.9860224723815918]
  模 [-0.4227488040924072, 0.7286509871482849, 0.5555989742279053, -0.43479853868484497, 0.39219915866851807]
  型 [-0.5974094271659851, 0.5976635217666626, 0.7734537124633789, -1.0439568758010864, 0.8142789006233215]
  [SEP] [-1.1663365364074707, 0.541653037071228, 1.396380066871643, 0.014762230217456818, -0.20481276512145996]
  [CLS] [-0.3404940962791443, 0.5169003009796143, 0.8958081603050232, -0.5850763916969299, 0.1620779037475586]
  你 [-0.6919717788696289, 0.37331458926200867, 1.3196662664413452, -0.0865214616060257, 0.5522887110710144]
  好 [0.6706017851829529, -0.5946153402328491, 0.4751562178134918, -0.7590199112892151, 0.9860224723815918]
  [SEP] [-0.4227488040924072, 0.7286509871482849, 0.5555989742279053, -0.43479853868484497, 0.39219915866851807]