Fashion数据集练习八股扩展完整代码

最新推荐文章于 2024-05-22 12:36:45 发布

海边菠萝

最新推荐文章于 2024-05-22 12:36:45 发布

阅读量97

点赞数 2

分类专栏： tensorflow2.0 文章标签：深度学习 tensorflow python

本文链接：https://blog.csdn.net/m0_63054020/article/details/129209626

版权

tensorflow2.0 专栏收录该内容

5 篇文章 1 订阅

订阅专栏

import tensorflow as tf
from tensorflow.keras.preprocessing.image import ImageDataGenerator
import os
import numpy as np
from matplotlib import pyplot as plt
np.set_printoptions(threshold=np.inf)#设置print输出格式
fashion=tf.keras.datasets.fashion_mnist
(x_train, y_train), (x_test, y_test) = fashion.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0

#由于image_gen_train.fit只能输入四维数组所以要增加一个维度
x_train = x_train.reshape(x_train.shape[0], 28, 28, 1)  # 给数据增加一个维度,从(60000, 28, 28)reshape为(60000, 28, 28, 1)


#数据增强又叫数据集扩增
image_gen_train = ImageDataGenerator(
    rescale=1. / 1.,  # 如为图像，分母为255时，可归至0～1
    rotation_range=45,  # 随机45度旋转
    width_shift_range=.15,  # 宽度偏移
    height_shift_range=.15,  # 高度偏移
    horizontal_flip=False,  # 水平翻转
    zoom_range=0.5  # 将图像随机缩放阈量50％
)

image_gen_train.fit(x_train)

#搭建网络结构
model = tf.keras.models.Sequential([
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Dense(10, activation='softmax')
])

#配置训练方法
model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=['sparse_categorical_accuracy'])

#定义模型文件存储的路径
checkpoint_save_path = "checkpoint/fashion.ckpt"

if os.path.exists(checkpoint_save_path + '.index'):
    print('-------------load the model-----------------')
    model.load_weights(checkpoint_save_path)

cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_save_path,
                                                 save_weights_only=True,
                                                 save_best_only=True)

history = model.fit(image_gen_train.flow(x_train, y_train, batch_size=32),epochs=128, validation_data=(x_test, y_test), validation_freq=1,
                    callbacks=[cp_callback])

model.summary()
#参数提取
print(model.trainable_variables)
#提取的参数存储到文件
file = open('weights.txt', 'w')
for v in model.trainable_variables:
    file.write(str(v.name) + '\n')
    file.write(str(v.shape) + '\n')
    file.write(str(v.numpy()) + '\n')
file.close()
#acc/loss曲线
acc = history.history['sparse_categorical_accuracy']
val_acc = history.history['val_sparse_categorical_accuracy']
loss = history.history['loss']
val_loss = history.history['val_loss']

plt.subplot(1, 2, 1)#一行两列，画出第一列
plt.plot(acc, label='Training Accuracy')
plt.plot(val_acc, label='Validation Accuracy')
plt.title('Training and Validation Accuracy')
plt.legend()

plt.subplot(1, 2, 2)#一行两列画出第二列
plt.plot(loss, label='Training Loss')
plt.plot(val_loss, label='Validation Loss')
plt.title('Training and Validation Loss')
plt.legend()
plt.show()