🍨 本文为🔗365天深度学习训练营 中的学习记录博客
🍖 原作者：K同学啊
文章目录
电脑环境：
语言环境：Python 3.8.0
编译器：Jupyter Notebook
深度学习环境：tensorflow 2.17.0
一、前期工作
1.设置GPU（如果使用的是CPU可以忽略这步）
python
import tensorflow as tf
gpus = tf.config.list_physical_devices("GPU")
if gpus:
gpu0 = gpus[0] #如果有多个GPU，仅使用第0个GPU
tf.config.experimental.set_memory_growth(gpu0, True) #设置GPU显存用量按需使用
tf.config.set_visible_devices([gpu0],"GPU")
from tensorflow import keras
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import warnings,os,PIL,pathlib
warnings.filterwarnings("ignore") #忽略警告信息
plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False # 用来正常显示负号二、导入数据
1、导入数据
python
data_dir = "./365-8-data/"
data_dir = pathlib.Path(data_dir)
image_count = len(list(data_dir.glob('*/*')))
print("图片总数为：",image_count)
python
batch_size = 16
img_height = 336
img_width = 336
"""
关于image_dataset_from_directory()的详细介绍可以参考文章：https://mtyjkh.blog.csdn.net/article/details/117018789
"""
train_ds = tf.keras.preprocessing.image_dataset_from_directory(
data_dir,
validation_split=0.2,
subset="training",
seed=12,
image_size=(img_height, img_width),
batch_size=batch_size)
val_ds = tf.keras.preprocessing.image_dataset_from_directory(
data_dir,
validation_split=0.2,
subset="validation",
seed=12,
image_size=(img_height, img_width),
batch_size=batch_size)
class_names = train_ds.class_names2、检查数据
python
for image_batch, labels_batch in train_ds:
print(image_batch.shape)
print(labels_batch.shape)
break(16, 336, 336, 3)
(16,)
3、配置数据集
python
AUTOTUNE = tf.data.AUTOTUNE
def train_preprocessing(image,label):
return (image/255.0,label)
train_ds = (
train_ds.cache()
.shuffle(1000)
.map(train_preprocessing) # 这里可以设置预处理函数
# .batch(batch_size) # 在image_dataset_from_directory处已经设置了batch_size
.prefetch(buffer_size=AUTOTUNE)
)
val_ds = (
val_ds.cache()
.shuffle(1000)
.map(train_preprocessing) # 这里可以设置预处理函数
# .batch(batch_size) # 在image_dataset_from_directory处已经设置了batch_size
.prefetch(buffer_size=AUTOTUNE)
)4、数据可视化
python
plt.figure(figsize=(10, 8)) # 图形的宽为10高为5
plt.suptitle("数据展示")
for images, labels in train_ds.take(1):
for i in range(15):
plt.subplot(4, 5, i + 1)
plt.xticks([])
plt.yticks([])
plt.grid(False)
# 显示图片
plt.imshow(images[i])
# 显示标签
plt.xlabel(class_names[labels[i]])
plt.show()
三、构建模型
model1为Adam优化器，model2为SGD优化器，网络结构都一致。
python
from tensorflow.keras.layers import Dropout,Dense,BatchNormalization
from tensorflow.keras.models import Model
def create_model(optimizer='adam'):
# 加载预训练模型
vgg16_base_model = tf.keras.applications.vgg16.VGG16(weights='imagenet',
include_top=False,
input_shape=(img_width, img_height, 3),
pooling='avg')
for layer in vgg16_base_model.layers:
layer.trainable = False
X = vgg16_base_model.output
X = Dense(170, activation='relu')(X)
X = BatchNormalization()(X)
X = Dropout(0.5)(X)
output = Dense(len(class_names), activation='softmax')(X)
vgg16_model = Model(inputs=vgg16_base_model.input, outputs=output)
vgg16_model.compile(optimizer=optimizer,
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
return vgg16_model
model1 = create_model(optimizer=tf.keras.optimizers.Adam())
model2 = create_model(optimizer=tf.keras.optimizers.SGD())
model2.summary()四、训练模型
python
NO_EPOCHS = 50
history_model1 = model1.fit(train_ds, epochs=NO_EPOCHS, verbose=1, validation_data=val_ds)
history_model2 = model2.fit(train_ds, epochs=NO_EPOCHS, verbose=1, validation_data=val_ds)
python
Epoch 1/50
90/90 ━━━━━━━━━━━━━━━━━━━━ 99s 872ms/step - accuracy: 0.1097 - loss: 3.1620 - val_accuracy: 0.0750 - val_loss: 2.7208
..............
Epoch 50/50
90/90 ━━━━━━━━━━━━━━━━━━━━ 20s 197ms/step - accuracy: 0.8159 - loss: 0.5525 - val_accuracy: 0.5806 - val_loss: 1.4261五、评估模型
1、Accuracy与Loss图
python
from matplotlib.ticker import MultipleLocator
plt.rcParams['savefig.dpi'] = 300 #图片像素
plt.rcParams['figure.dpi'] = 300 #分辨率
acc1 = history_model1.history['accuracy']
acc2 = history_model2.history['accuracy']
val_acc1 = history_model1.history['val_accuracy']
val_acc2 = history_model2.history['val_accuracy']
loss1 = history_model1.history['loss']
loss2 = history_model2.history['loss']
val_loss1 = history_model1.history['val_loss']
val_loss2 = history_model2.history['val_loss']
epochs_range = range(len(acc1))
plt.figure(figsize=(16, 4))
plt.subplot(1, 2, 1)
plt.plot(epochs_range, acc1, label='Training Accuracy-Adam')
plt.plot(epochs_range, acc2, label='Training Accuracy-SGD')
plt.plot(epochs_range, val_acc1, label='Validation Accuracy-Adam')
plt.plot(epochs_range, val_acc2, label='Validation Accuracy-SGD')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')
# 设置刻度间隔，x轴每1一个刻度
ax = plt.gca()
ax.xaxis.set_major_locator(MultipleLocator(1))
plt.subplot(1, 2, 2)
plt.plot(epochs_range, loss1, label='Training Loss-Adam')
plt.plot(epochs_range, loss2, label='Training Loss-SGD')
plt.plot(epochs_range, val_loss1, label='Validation Loss-Adam')
plt.plot(epochs_range, val_loss2, label='Validation Loss-SGD')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
# 设置刻度间隔，x轴每1一个刻度
ax = plt.gca()
ax.xaxis.set_major_locator(MultipleLocator(1))
plt.show()
2.、模型评估
python
def test_accuracy_report(model):
score = model.evaluate(val_ds, verbose=0)
print('Loss function: %s, accuracy:' % score[0], score[1])
test_accuracy_report(model2)Loss function: 1.4261106252670288, accuracy: 0.5805555582046509
六、总结
我们可以从两个不同的图中分别观察到训练和验证的准确率以及损失值的变化，Adam优化器在训练集上表现优异，迅速提高准确率并减少损失值，但在验证集上的表现不稳定，可能会导致过拟合。SGD优化器在训练集上学习速度较慢，但验证集上的表现较为稳定，适合在更长期的训练中提升模型的泛化能力。具体使用哪种优化器还要看具体任务。