本文为为🔗365天深度学习训练营内部文章
原作者:K同学啊
一 导入数据
import matplotlib.pyplot as plt
import tensorflow as tf
# 支持中文
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import os,PIL,pathlib#隐藏警告
import warnings
warnings.filterwarnings('ignore')data_dir = "./data"
data_dir = pathlib.Path(data_dir)image_count = len(list(data_dir.glob('*/*')))print("图片总数为:",image_count)
图片总数为: 3400
二、数据预处理
1. 加载数据
使用
image_dataset_from_directory
方法将磁盘中的数据加载到tf.data.Dataset
中
batch_size = 8
img_height = 224
img_width = 224
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)
Found 3400 files belonging to 2 classes. Using 2720 files for training.
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)
Found 3400 files belonging to 2 classes. Using 680 files for validation.
class_names = train_ds.class_names
print(class_names)
['cat', 'dog']
2. 再次检查数据
for image_batch, labels_batch in train_ds:print(image_batch.shape)print(labels_batch.shape)break
(8, 224, 224, 3) (8,)
3. 配置数据集
- shuffle() : 打乱数据
- prefetch() :预取数据,加速运行
- cache() :将数据集缓存到内存当中,加速运行
AUTOTUNE = tf.data.AUTOTUNEdef preprocess_image(image,label):return (image/255.0,label)# 归一化处理
train_ds = train_ds.map(preprocess_image, num_parallel_calls=AUTOTUNE)
val_ds = val_ds.map(preprocess_image, num_parallel_calls=AUTOTUNE)train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)
在这里数据处理的过程中,比前几次稍微不同的是多加了一个归一化的处理
4.可视化数据
plt.figure(figsize=(15, 10)) # 图形的宽为15高为10for images, labels in train_ds.take(1):for i in range(8):ax = plt.subplot(5, 8, i + 1) plt.imshow(images[i])plt.title(class_names[labels[i]])plt.axis("off")
三、构建VG-16网络
VGG优缺点分析:
- VGG优点
VGG的结构非常简洁,整个网络都使用了同样大小的卷积核尺寸(3x3)和最大池化尺寸(2x2)。
- VGG缺点
1)训练时间过长,调参难度大。2)需要的存储容量大,不利于部署。例如存储VGG-16权重值文件的大小为500多MB,不利于安装到嵌入式系统中。
结构说明:
- 13个卷积层(Convolutional Layer),分别用
blockX_convX
表示
- 3个全连接层(Fully connected Layer),分别用
fcX
与predictions
表示
- 5个池化层(Pool layer),分别用
blockX_pool
表示
VGG-16
包含了16个隐藏层(13个卷积层和3个全连接层),故称为VGG-16
构建方法1:调用官网封装好的模型函数
model = tf.keras.applications.VGG16(weights='imagenet')
model.summary()
Model: "vgg16" _________________________________________________________________Layer (type) Output Shape Param # =================================================================input_1 (InputLayer) [(None, 224, 224, 3)] 0 block1_conv1 (Conv2D) (None, 224, 224, 64) 1792 block1_conv2 (Conv2D) (None, 224, 224, 64) 36928 block1_pool (MaxPooling2D) (None, 112, 112, 64) 0 block2_conv1 (Conv2D) (None, 112, 112, 128) 73856 block2_conv2 (Conv2D) (None, 112, 112, 128) 147584 block2_pool (MaxPooling2D) (None, 56, 56, 128) 0 block3_conv1 (Conv2D) (None, 56, 56, 256) 295168 block3_conv2 (Conv2D) (None, 56, 56, 256) 590080 block3_conv3 (Conv2D) (None, 56, 56, 256) 590080 block3_pool (MaxPooling2D) (None, 28, 28, 256) 0 block4_conv1 (Conv2D) (None, 28, 28, 512) 1180160 block4_conv2 (Conv2D) (None, 28, 28, 512) 2359808 block4_conv3 (Conv2D) (None, 28, 28, 512) 2359808 block4_pool (MaxPooling2D) (None, 14, 14, 512) 0 block5_conv1 (Conv2D) (None, 14, 14, 512) 2359808 block5_conv2 (Conv2D) (None, 14, 14, 512) 2359808 block5_conv3 (Conv2D) (None, 14, 14, 512) 2359808 block5_pool (MaxPooling2D) (None, 7, 7, 512) 0 flatten (Flatten) (None, 25088) 0 fc1 (Dense) (None, 4096) 102764544 fc2 (Dense) (None, 4096) 16781312 predictions (Dense) (None, 1000) 4097000 ================================================================= Total params: 138,357,544 Trainable params: 138,357,544 Non-trainable params: 0 _________________________________________________________________
构建方法二:自己手动搭建模型
from tensorflow.keras import layers, models, Input
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Dense, Flatten, Dropoutdef VGG16(nb_classes, input_shape):input_tensor = Input(shape=input_shape)# 1st blockx = Conv2D(64, (3,3), activation='relu', padding='same',name='block1_conv1')(input_tensor)x = Conv2D(64, (3,3), activation='relu', padding='same',name='block1_conv2')(x)x = MaxPooling2D((2,2), strides=(2,2), name = 'block1_pool')(x)# 2nd blockx = Conv2D(128, (3,3), activation='relu', padding='same',name='block2_conv1')(x)x = Conv2D(128, (3,3), activation='relu', padding='same',name='block2_conv2')(x)x = MaxPooling2D((2,2), strides=(2,2), name = 'block2_pool')(x)# 3rd blockx = Conv2D(256, (3,3), activation='relu', padding='same',name='block3_conv1')(x)x = Conv2D(256, (3,3), activation='relu', padding='same',name='block3_conv2')(x)x = Conv2D(256, (3,3), activation='relu', padding='same',name='block3_conv3')(x)x = MaxPooling2D((2,2), strides=(2,2), name = 'block3_pool')(x)# 4th blockx = Conv2D(512, (3,3), activation='relu', padding='same',name='block4_conv1')(x)x = Conv2D(512, (3,3), activation='relu', padding='same',name='block4_conv2')(x)x = Conv2D(512, (3,3), activation='relu', padding='same',name='block4_conv3')(x)x = MaxPooling2D((2,2), strides=(2,2), name = 'block4_pool')(x)# 5th blockx = Conv2D(512, (3,3), activation='relu', padding='same',name='block5_conv1')(x)x = Conv2D(512, (3,3), activation='relu', padding='same',name='block5_conv2')(x)x = Conv2D(512, (3,3), activation='relu', padding='same',name='block5_conv3')(x)x = MaxPooling2D((2,2), strides=(2,2), name = 'block5_pool')(x)# full connectionx = Flatten()(x)x = Dense(4096, activation='relu', name='fc1')(x)x = Dense(4096, activation='relu', name='fc2')(x)output_tensor = Dense(nb_classes, activation='softmax', name='predictions')(x)model = Model(input_tensor, output_tensor)return modelmodel=VGG16(1000, (img_width, img_height, 3))
model.summary()
Model: "model" _________________________________________________________________Layer (type) Output Shape Param # =================================================================input_1 (InputLayer) [(None, 224, 224, 3)] 0 block1_conv1 (Conv2D) (None, 224, 224, 64) 1792 block1_conv2 (Conv2D) (None, 224, 224, 64) 36928 block1_pool (MaxPooling2D) (None, 112, 112, 64) 0 block2_conv1 (Conv2D) (None, 112, 112, 128) 73856 block2_conv2 (Conv2D) (None, 112, 112, 128) 147584 block2_pool (MaxPooling2D) (None, 56, 56, 128) 0 block3_conv1 (Conv2D) (None, 56, 56, 256) 295168 block3_conv2 (Conv2D) (None, 56, 56, 256) 590080 block3_conv3 (Conv2D) (None, 56, 56, 256) 590080 block3_pool (MaxPooling2D) (None, 28, 28, 256) 0 block4_conv1 (Conv2D) (None, 28, 28, 512) 1180160 block4_conv2 (Conv2D) (None, 28, 28, 512) 2359808 block4_conv3 (Conv2D) (None, 28, 28, 512) 2359808 block4_pool (MaxPooling2D) (None, 14, 14, 512) 0 block5_conv1 (Conv2D) (None, 14, 14, 512) 2359808 block5_conv2 (Conv2D) (None, 14, 14, 512) 2359808 block5_conv3 (Conv2D) (None, 14, 14, 512) 2359808 block5_pool (MaxPooling2D) (None, 7, 7, 512) 0 flatten (Flatten) (None, 25088) 0 fc1 (Dense) (None, 4096) 102764544 fc2 (Dense) (None, 4096) 16781312 predictions (Dense) (None, 1000) 4097000 ================================================================= Total params: 138,357,544 Trainable params: 138,357,544 Non-trainable params: 0 _________________________________________________________________
四、编译
在准备对模型进行训练之前,还需要再对其进行一些设置。以下内容是在模型的编译步骤中添加的:
- 损失函数(loss):用于衡量模型在训练期间的准确率。
- 优化器(optimizer):决定模型如何根据其看到的数据和自身的损失函数进行更新。
- 评价函数(metrics):用于监控训练和测试步骤。以下示例使用了准确率,即被正确分类的图像的比率。
# 设置初始学习率
initial_learning_rate = 1e-4lr_schedule = tf.keras.optimizers.schedules.ExponentialDecay(initial_learning_rate, decay_steps=30, # 敲黑板!!!这里是指 steps,不是指epochsdecay_rate=0.92, # lr经过一次衰减就会变成 decay_rate*lrstaircase=True)# 设置优化器
opt = tf.keras.optimizers.Adam(learning_rate=initial_learning_rate)model.compile(optimizer=opt,loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),metrics=['accuracy'])
早停法:
from tensorflow.keras.callbacks import ModelCheckpoint, EarlyStoppingepochs = 10# 保存最佳模型参数
checkpointer = ModelCheckpoint('best_model.h5',monitor='val_accuracy',verbose=1,save_best_only=True,save_weights_only=True)# 设置早停
earlystopper = EarlyStopping(monitor='val_accuracy', min_delta=0.001,patience=20, verbose=1)
五、训练模型
history = model.fit(train_ds,validation_data=val_ds,epochs=epochs,callbacks=[checkpointer, earlystopper])
Epoch 1/10 340/340 [==============================] - ETA: 0s - loss: 0.2396 - accuracy: 0.8930 Epoch 1: val_accuracy improved from -inf to 0.99412, saving model to best_model.h5 340/340 [==============================] - 1376s 4s/step - loss: 0.2396 - accuracy: 0.8930 - val_loss: 0.0210 - val_accuracy: 0.9941 Epoch 2/10 340/340 [==============================] - ETA: 0s - loss: 0.0276 - accuracy: 0.9908 Epoch 2: val_accuracy did not improve from 0.99412 340/340 [==============================] - 1345s 4s/step - loss: 0.0276 - accuracy: 0.9908 - val_loss: 0.0465 - val_accuracy: 0.9853 Epoch 3/10 340/340 [==============================] - ETA: 0s - loss: 0.1150 - accuracy: 0.9717 Epoch 3: val_accuracy did not improve from 0.99412 340/340 [==============================] - 1316s 4s/step - loss: 0.1150 - accuracy: 0.9717 - val_loss: 0.0704 - val_accuracy: 0.9750 Epoch 4/10 340/340 [==============================] - ETA: 0s - loss: 0.0192 - accuracy: 0.9949 Epoch 4: val_accuracy improved from 0.99412 to 0.99853, saving model to best_model.h5 340/340 [==============================] - 1336s 4s/step - loss: 0.0192 - accuracy: 0.9949 - val_loss: 0.0083 - val_accuracy: 0.9985 Epoch 5/10 340/340 [==============================] - ETA: 0s - loss: 0.0248 - accuracy: 0.9930 Epoch 5: val_accuracy did not improve from 0.99853 340/340 [==============================] - 1321s 4s/step - loss: 0.0248 - accuracy: 0.9930 - val_loss: 0.0036 - val_accuracy: 0.9985 Epoch 6/10 340/340 [==============================] - ETA: 0s - loss: 0.0240 - accuracy: 0.9937 Epoch 6: val_accuracy did not improve from 0.99853 340/340 [==============================] - 1323s 4s/step - loss: 0.0240 - accuracy: 0.9937 - val_loss: 0.0074 - val_accuracy: 0.9956 Epoch 7/10 340/340 [==============================] - ETA: 0s - loss: 0.0039 - accuracy: 0.9982 Epoch 7: val_accuracy did not improve from 0.99853 340/340 [==============================] - 1324s 4s/step - loss: 0.0039 - accuracy: 0.9982 - val_loss: 0.0069 - val_accuracy: 0.9971 Epoch 8/10 340/340 [==============================] - ETA: 0s - loss: 8.3202e-04 - accuracy: 1.0000 Epoch 8: val_accuracy did not improve from 0.99853 340/340 [==============================] - 1318s 4s/step - loss: 8.3202e-04 - accuracy: 1.0000 - val_loss: 0.0205 - val_accuracy: 0.9956 Epoch 9/10 340/340 [==============================] - ETA: 0s - loss: 0.0759 - accuracy: 0.9801 Epoch 9: val_accuracy did not improve from 0.99853 340/340 [==============================] - 1326s 4s/step - loss: 0.0759 - accuracy: 0.9801 - val_loss: 0.0372 - val_accuracy: 0.9882 Epoch 10/10 340/340 [==============================] - ETA: 0s - loss: 0.0242 - accuracy: 0.9934 Epoch 10: val_accuracy did not improve from 0.99853 340/340 [==============================] - 1328s 4s/step - loss: 0.0242 - accuracy: 0.9934 - val_loss: 0.0072 - val_accuracy: 0.9985
六 模型评估
acc = history.history['accuracy']
val_acc = history.history['val_accuracy']loss = history.history['loss']
val_loss = history.history['val_loss']epochs_range = range(epochs)plt.figure(figsize=(12, 4))
plt.subplot(1, 2, 1)
plt.plot(epochs_range, acc, label='Training Accuracy')
plt.plot(epochs_range, val_acc, label='Validation Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')plt.subplot(1, 2, 2)
plt.plot(epochs_range, loss, label='Training Loss')
plt.plot(epochs_range, val_loss, label='Validation Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()
预测
import numpy as np# 采用加载的模型(new_model)来看预测结果
plt.figure(figsize=(18, 3)) # 图形的宽为18高为5
plt.suptitle("预测结果展示")for images, labels in val_ds.take(1):for i in range(8):ax = plt.subplot(1,8, i + 1) # 显示图片plt.imshow(images[i].numpy())# 需要给图片增加一个维度img_array = tf.expand_dims(images[i], 0) # 使用模型预测图片中的人物predictions = model.predict(img_array)plt.title(class_names[np.argmax(predictions)])plt.axis("off")
1/1 [==============================] - 1s 609ms/step 1/1 [==============================] - 0s 123ms/step 1/1 [==============================] - 0s 140ms/step 1/1 [==============================] - 0s 134ms/step 1/1 [==============================] - 0s 129ms/step 1/1 [==============================] - 0s 126ms/step 1/1 [==============================] - 0s 124ms/step 1/1 [==============================] - 0s 123ms/step
在训练模型的时候,除了用上述的代码之外,还可以用另一种方式。
改用model.train_on_batch方法。两种方法的比较:
model.fit()
:用起来十分简单,对新手非常友好
model.train_on_batch()
:封装程度更低,可以玩更多花样。此外我也引入了进度条的显示方式,更加方便我们及时查看模型训练过程中的情况,可以及时打印各项指标
model.compile(optimizer="adam",loss ='sparse_categorical_crossentropy',metrics =['accuracy'])
from tqdm import tqdm
import tensorflow.keras.backend as Kepochs = 10
lr = 1e-4# 记录训练数据,方便后面的分析
history_train_loss = []
history_train_accuracy = []
history_val_loss = []
history_val_accuracy = []for epoch in range(epochs):train_total = len(train_ds)val_total = len(val_ds)"""total:预期的迭代数目ncols:控制进度条宽度mininterval:进度更新最小间隔,以秒为单位(默认值:0.1)"""with tqdm(total=train_total, desc=f'Epoch {epoch + 1}/{epochs}',mininterval=1,ncols=100) as pbar:lr = lr*0.92K.set_value(model.optimizer.lr, lr)for image,label in train_ds: """训练模型,简单理解train_on_batch就是:它是比model.fit()更高级的一个用法想详细了解 train_on_batch 的同学,可以看看我的这篇文章:https://www.yuque.com/mingtian-fkmxf/hv4lcq/ztt4gy"""history = model.train_on_batch(image,label)train_loss = history[0]train_accuracy = history[1]pbar.set_postfix({"loss": "%.4f"%train_loss,"accuracy":"%.4f"%train_accuracy,"lr": K.get_value(model.optimizer.lr)})pbar.update(1)history_train_loss.append(train_loss)history_train_accuracy.append(train_accuracy)print('开始验证!')with tqdm(total=val_total, desc=f'Epoch {epoch + 1}/{epochs}',mininterval=0.3,ncols=100) as pbar:for image,label in val_ds: history = model.test_on_batch(image,label)val_loss = history[0]val_accuracy = history[1]pbar.set_postfix({"loss": "%.4f"%val_loss,"accuracy":"%.4f"%val_accuracy})pbar.update(1)history_val_loss.append(val_loss)history_val_accuracy.append(val_accuracy)print('结束验证!')print("验证loss为:%.4f"%val_loss)print("验证准确率为:%.4f"%val_accuracy)
对比之前的model.fit()方法,这次还引用了更详细的进度条。后续的操作和上述方法一样