tensorflow 搭建模型框架数据集为Mnist

最新推荐文章于 2024-10-04 22:36:54 发布

过往码农

最新推荐文章于 2024-10-04 22:36:54 发布

阅读量54

点赞数

文章标签： tensorflow 人工智能 python

本文链接：https://blog.csdn.net/qq_63730939/article/details/133354024

版权

导入相应库文件

from tensorflow.keras.datasets import mnist,fashion_mnist
from tensorflow.keras.layers import Conv2D,MaxPooling2D,Flatten,Dense
from tensorflow.keras.models import Sequential, load_model
from tensorflow.keras import optimizers,losses,callbacks
import tensorflow as tf

下载数据集并进行数据的划分

(x_train,y_train),(x_test,y_test) = fashion_mnist.load_data()
x_train,x_test = x_train/255.0,x_test/255.0

搭建模型

model = tf.keras.Sequential([
    tf.keras.layers.Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28, 1)),
    tf.keras.layers.MaxPooling2D((2, 2)),
    tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),
    tf.keras.layers.MaxPooling2D((2, 2)),
    tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(64, activation='relu'),
    tf.keras.layers.Dense(10, activation='softmax')
])
model.summary()

定义损失函数及优化器

model.compile(optimizer=tf.keras.optimizers.Adam(),
              loss=tf.keras.losses.categorical_crossentropy,
              metrics=['acc'])

将训练集、测试集的x进行维度转换

x_test = x_test.reshape(-1,28,28,1)
x_train = x_train.reshape(-1,28,28,1)

将y进行one_hat 编码

y_train_one = tf.keras.utils.to_categorical(y_train)
y_test_one = tf.keras.utils.to_categorical(y_test)

训练模型

hist = model.fit(x_train,y_train_one,epochs=20)

训练结果：

在这里插入图片描述

评估模型

acc = hist.history['acc']
loss = hist.history['loss']

import matplotlib.pyplot as plt
plt.rcParams['font.family'] = 'SimHei'
plt.rcParams['axes.unicode_minus'] = False
T = len(loss)
plt.plot(range(T),loss,label = '损失')
plt.plot(range(T),acc,label='准确率')

plt.legend()
plt.show()

在这里插入图片描述

model.evaluate(x_test,y_test_one)

[0.4195633828639984, 0.9110000133514404]

预测数据并输出

pred = model.predict(x_test)

# 创建数据
data = x_test[:100]  # 输出十张照片

# 创建子图布局
fig, axes = plt.subplots(10, 10, figsize=(12, 12))

# 展示图片
for i, ax in enumerate(axes.flat):
    ax.imshow(data[i],cmap='gray')  
    ax.axis('off')  # 关闭坐标轴
    ax.set_title(f'预测： {np.argmax(pred[i])}')  # 设置标题

# 调整子图布局
plt.tight_layout()

# 展示图表
plt.show()