关于在使用Tensorflow训练时产生AttributeError: ‘Function‘ object has no attribute ‘_concrete_stateful_fn‘的一个解法

本文链接：https://blog.youkuaiyun.com/tfl2003xhhssh/article/details/147703265

在使用Tensorflow的RNN进行情感分析时，发现在模型训练时出现一个报错：

AttributeError: 'Function' object has no attribute '_concrete_stateful_fn'

之前还有其他报错类似：AttributeError: 'Function' object has no attribute 'xxx'

浏览后发现是Tensorflow版本更替后使用以往版本代码的问题。

如下图，产生报错的源头在于：python

from tensorflow.python.keras.models import Model

from tensorflow.python.keras.models import load_model
from sklearn.preprocessing import LabelEncoder,OneHotEncoder
from tensorflow.python.keras.models import Model
from tensorflow.python.keras.layers import  Dense, Dropout, Input, Embedding,SimpleRNN
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing import sequence
from jieba import lcut
from sklearn.model_selection import train_test_split
import numpy as np
from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay
import matplotlib.pyplot as plt
from sklearn.metrics import precision_score, accuracy_score, f1_score, recall_score
from tensorflow.python.keras.callbacks import TensorBoard,EarlyStopping

删除后代码正常运行，开始训练模型。