LSTM的一些安装问题

关于LSTM跑不动呀

x = LSTM(128, dropout=0.5)(embedded_sequences)

总是会报错：
Cannot convert a symbolic Tensor (lstm_10/strided_slice:0) to a numpy array. This error may indicate that you’re trying to pass a Tensor to a NumPy call, which is not supported
因为说是tensorflow和numpy的兼容问题，所以我卸载重安装了好几次，直接给爷整麻了。
目前我的python是3.9，tensorflow=2.5.0，keras=2.4.3，python=1.19.2，可以通过cmd输入pip list查找

此时有些安装包在直接通过keras安装时仍然会报错，例如：

from keras import backend as K
from keras import Model
from keras import Sequential
from keras.preprocessing.text import Tokenizer

module ‘keras.utils.generic_utils’ has no attribute ‘populate_dict_with_module_objects’
可以通过在“keras”前面添加“tensorflow.”来完成：

from tensorflow.keras import backend as K
from tensorflow.keras import Model
from tensorflow.keras import Sequential
from tensorflow.keras.preprocessing.text import Tokenizer