- 🍨 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
一、前期工作
● 难度:夯实基础⭐⭐
● 语言:Python3、TensorFlow2
🍺 要求:
- 自己搭建VGG-16网络框架
- 调用官方的VGG-16网络框架
🍻 拔高(可选):
- 验证集准确率达到100%
- 使用PPT画出VGG-16算法框架图(发论文需要这项技能)
🔎 探索(难度有点大)
- 在不影响准确率的前提下轻量化模型
○ 目前VGG16的Total params是134,276,932
🦾我的环境:
- 语言环境:Python3.8
- 编译器:Jupyter Lab
- 深度学习环境:
- TensorFlow2
1. 设置GPU
如果使用的是CPU可以忽略这步
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")
gpu0
PhysicalDevice(name='/physical_device:GPU:0', device_type='GPU')
2. 导入数据
import matplotlib.pyplot as plt
import os,PIL
# 设置随机种子尽可能使结果可以重现
import numpy as np
np.random.seed(1)
# 设置随机种子尽可能使结果可以重现
import tensorflow as tf
tf.random.set_seed(1)
from tensorflow import keras
from tensorflow.keras import layers,models
import pathlib
data_dir = "data/p7/"
data_dir = pathlib.Path(data_dir)
data_dir
PosixPath('data/p7')
3. 查看数据
image_count = len(list(data_dir.glob('*/*.jpg')))
print("图片总数为:",image_count)
图片总数为: 1200
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 = 32
img_height = 224
img_width = 224
"""
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=123,
image_size=(img_height, img_width),
batch_size=batch_size)
Found 1200 files belonging to 4 classes.
Using 960 files for training.
"""
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
"""
val_ds = tf.keras.preprocessing.image_dataset_from_directory(
data_dir,
validation_split=0.2,
subset="validation",
seed=123,
image_size=(img_height, img_width),
batch_size=batch_size)
Found 1200 files belonging to 4 classes.
Using 240 files for validation.
我们可以通过class_names输出数据集的标签。标签将按字母顺序对应于目录名称。
class_names = train_ds.class_names
print(class_names)
['Dark', 'Green', 'Light', 'Medium']
2. 可视化数据
plt.figure(figsize=(10, 4)) # 图形的宽为10高为5
for images, labels in train_ds.take(1):
for i in range(10):
ax = plt.subplot(2, 5, i + 1)
plt.imshow(images[i].numpy().astype("uint8"))
plt.title(class_names[labels[i]])
plt.axis("off")
3. 再次检查数据
for image_batch, labels_batch in train_ds:
print(image_batch.shape)
print(labels_batch.shape)
break
(32, 224, 224, 3)
(32,)
4. 配置数据集
shuffle()
:打乱数据,关于此函数的详细介绍可以参考:https://zhuanlan.zhihu.com/p/42417456prefetch()
:预取数据,加速运行
函数原型:
tf.keras.preprocessing.image_dataset_from_directory(
directory,
labels="inferred",
label_mode="int",
class_names=None,
color_mode="rgb",
batch_size=32,
image_size=(256, 256),
shuffle=True,
seed=None,
validation_split=None,
subset=None,
interpolation="bilinear",
follow_links=False,
)
AUTOTUNE = tf.data.AUTOTUNE
train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)
normalization_layer = layers.experimental.preprocessing.Rescaling(1./255)
train_ds = train_ds.map(lambda x, y: (normalization_layer(x), y))
val_ds = val_ds.map(lambda x, y: (normalization_layer(x), y))
image_batch, labels_batch = next(iter(val_ds))
first_image = image_batch[0]
# 查看归一化后的数据
print(np.min(first_image), np.max(first_image))
0.0 1.0
2024-07-13 22:22:48.443056: W tensorflow/core/kernels/data/cache_dataset_ops.cc:854] The calling iterator did not fully read the dataset being cached. In order to avoid unexpected truncation of the dataset, the partially cached contents of the dataset will be discarded. This can happen if you have an input pipeline similar to `dataset.cache().take(k).repeat()`. You should use `dataset.take(k).cache().repeat()` instead.
三、构建VGG-16网络
在官方模型与自建模型之间进行二选一就可以了,选着一个注释掉另外一个。
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
- 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。
3.1. 官方模型
官网模型调用这块我放到后面几篇文章中,下面主要讲一下VGG-16
# model = tf.keras.applications.VGG16(weights='imagenet')
# model.summary()
3.2. 自建模型
from tensorflow.keras import layers, models, Input
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Dense, Flatten, Dropout
def VGG16(nb_classes, input_shape):
input_tensor = Input(shape=input_shape)
# 1st block
x = 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 block
x = 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 block
x = 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 block
x = 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 block
x = 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 connection
x = 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 model
model=VGG16(len(class_names), (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, 4) 16388
=================================================================
Total params: 134276932 (512.23 MB)
Trainable params: 134276932 (512.23 MB)
Non-trainable params: 0 (0.00 Byte)
_________________________________________________________________
4.3. 网络结构图
关于卷积的相关知识可以参考文章:https://mtyjkh.blog.csdn.net/article/details/114278995
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
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。
- 指标(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-4
lr_schedule = tf.keras.optimizers.schedules.ExponentialDecay(
initial_learning_rate,
decay_steps=30, # 敲黑板!!!这里是指 steps,不是指epochs
decay_rate=0.92, # lr经过一次衰减就会变成 decay_rate*lr
staircase=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'])
WARNING:absl:At this time, the v2.11+ optimizer `tf.keras.optimizers.Adam` runs slowly on M1/M2 Macs, please use the legacy Keras optimizer instead, located at `tf.keras.optimizers.legacy.Adam`.
WARNING:absl:There is a known slowdown when using v2.11+ Keras optimizers on M1/M2 Macs. Falling back to the legacy Keras optimizer, i.e., `tf.keras.optimizers.legacy.Adam`.
五、训练模型
🔊注:从本周开始,网络越来越复杂,对算力要求也更高,CPU训练模型时间会很长,建议尽可能的使用GPU来跑。
epochs = 20
history = model.fit(
train_ds,
validation_data=val_ds,
epochs=epochs
)
Epoch 1/20
output, from_logits = _get_logits(
2024-07-13 22:26:30.130268: I tensorflow/core/grappler/optimizers/custom_graph_optimizer_registry.cc:114] Plugin optimizer for device_type GPU is enabled.
30/30 [==============================] - ETA: 0s - loss: 1.3693 - accuracy: 0.2750
30/30 [==============================] - 42s 1s/step - loss: 1.3693 - accuracy: 0.2750 - val_loss: 1.3129 - val_accuracy: 0.5500
...
30/30 [==============================] - 38s 1s/step - loss: 0.1471 - accuracy: 0.9469 - val_loss: 0.0774 - val_accuracy: 0.9792
Epoch 19/20
30/30 [==============================] - 38s 1s/step - loss: 0.0530 - accuracy: 0.9833 - val_loss: 0.0852 - val_accuracy: 0.9750
Epoch 20/20
30/30 [==============================] - 38s 1s/step - loss: 0.0425 - accuracy: 0.9854 - val_loss: 0.1525 - val_accuracy: 0.9625
六、可视化结果
6.1. Loss与Accuracy图
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()
6.2. 指定图片进行预测
from PIL import Image
import numpy as np
img = Image.open("./data/p7/Green/een/green (1).png") #这里选择你需要预测的图片
image = tf.image.resize(img, [img_height, img_width])
img_array = tf.expand_dims(image, 0)
predictions = model.predict(img_array) # 这里选用你已经训练好的模型
print("预测结果为:",class_names[np.argmax(predictions)])
2024-07-13 22:39:15.100914: I tensorflow/core/grappler/optimizers/custom_graph_optimizer_registry.cc:114] Plugin optimizer for device_type GPU is enabled.
1/1 [==============================] - 1s 612ms/step
预测结果为: Green