Tensorflow---使用Tensorflow初步进行卷积层的基本使用

一、代码中的数据可以通过以下代码进行加载

# 数据的加载
fashion_mnist = tf.keras.datasets.fashion_mnist
(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()
train_images = tf.expand_dims(train_images, -1)
test_images = tf.expand_dims(test_images, -1)

二、代码运行环境

Tensorflow-gpu==2.4.0

Python==3.7

三、具体实现代码如下所示：

import tensorflow as tf
import os

# 环境变量的配置
os.environ['TF_XLA_FLAGS'] = '--tf_xla_enable_xla_devices'
os.environ['TF_FORCE_GPU_ALLOW_GROWTH'] = 'true'

# 数据的加载
fashion_mnist = tf.keras.datasets.fashion_mnist
(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()
train_images = tf.expand_dims(train_images, -1)
test_images = tf.expand_dims(test_images, -1)

# 模型的构建
model = tf.keras.Sequential()
model.add(tf.keras.layers.Conv2D(64, (3, 3), input_shape=train_images.shape[1:], activation='relu', padding='same'))
model.add(tf.keras.layers.Conv2D(64, (3, 3), activation='relu', padding='same'))
model.add(tf.keras.layers.MaxPooling2D())
model.add(tf.keras.layers.Dropout(0.5))
model.add(tf.keras.layers.Conv2D(128, (3, 3), activation='relu', padding='same'))
model.add(tf.keras.layers.Conv2D(128, (3, 3), activation='relu', padding='same'))
model.add(tf.keras.layers.MaxPooling2D())
model.add(tf.keras.layers.Dropout(0.5))
model.add(tf.keras.layers.Conv2D(256, (3, 3), activation='relu', padding='same'))
model.add(tf.keras.layers.Conv2D(256, (3, 3), activation='relu', padding='same'))
model.add(tf.keras.layers.MaxPooling2D())
model.add(tf.keras.layers.Dropout(0.5))
model.add(tf.keras.layers.Conv2D(512, (3, 3), activation='relu', padding='same'))
model.add(tf.keras.layers.Conv2D(512, (3, 3), activation='relu', padding='same'))
model.add(tf.keras.layers.Dropout(0.5))
model.add(tf.keras.layers.GlobalMaxPooling2D())
model.add(tf.keras.layers.Dense(256, activation='relu'))
model.add(tf.keras.layers.Dense(10, activation='softmax'))
model.summary()

# 模型的相关配置
model.compile(
    optimizer='adam',
    loss='sparse_categorical_crossentropy',
    metrics=['acc']
)

# 模型的训练
history = model.fit(train_images, train_labels, epochs=100, validation_data=(test_images, test_labels), workers=5)

# 模型的保存
model.save(r'model_data/conv_model.h5')