AttributeError:模块'keras.api._v2.keras.utils‘没有属性'Sequential’，我刚刚开始神经网络，所以帮助是有用的。
AttributeError:模块'keras.api._v2.keras.utils‘没有属性'Sequential’，我刚刚开始神经网络，所以帮助是有用的。
提问于 2022-03-18 16:45:10
import cv2
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf
from keras import Sequential
from tensorflow import keras
import os
mnist = tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = tf.keras.utils.normalize(x_train, axis=1)
x_test = tf.keras.utils.normalize(x_test, axis=1)
model = tf.keras.utils.Sequential()
model.add(tf.keras.layers.Flatten(input_shape=(28, 28)))
model.add(tf.keras.layers.Dense(128, activation='relu'))
model.add(tf.keras.layers.Dense(128, activation='relu'))
model.add(tf.keras.layers.Dense(10, activation='softmax'))
model.compile(optimizer='adam', loss='spare_categorical_crossentropy', metrics=['accuracy'])
model.fit(x_train, y_train, epochs=3)
model.save('handwritten.model')Traceback (most recent call last):
File "C:\Users\DELL\PycharmProjects\NeuralNetworks\main.py", line 15, in <module>
model = tf.keras.utils.Sequential()
AttributeError: module 'keras.api._v2.keras.utils' has no attribute 'Sequential'
Process finished with exit code 1**回答 1
Stack Overflow用户
回答已采纳
发布于 2022-03-18 16:47:12
您应该使用tf.keras.Sequential()或tf.keras.models.Sequential()。此外，您需要定义一个有效的损失函数。下面是一个有用的例子：
import cv2
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf
from keras import Sequential
from tensorflow import keras
import os
mnist = tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = tf.keras.utils.normalize(x_train, axis=1)
x_test = tf.keras.utils.normalize(x_test, axis=1)
model = tf.keras.Sequential()
model.add(tf.keras.layers.Flatten(input_shape=(28, 28)))
model.add(tf.keras.layers.Dense(128, activation='relu'))
model.add(tf.keras.layers.Dense(128, activation='relu'))
model.add(tf.keras.layers.Dense(10, activation='softmax'))
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
model.fit(x_train, y_train, epochs=3)
model.save('handwritten.model')页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/71530455
复制相关文章
相似问题
腾讯云开发者
