Xception实现动物识别（TensorFlow）
Posted csp_
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了Xception实现动物识别（TensorFlow）相关的知识，希望对你有一定的参考价值。
活动地址：CSDN21天学习挑战赛
目录
1.任务介绍
数据结构为：
data
├── cat（文件夹含1000张图像）
│
├── chook（文件夹含1000张图像）
│
├── dog（文件夹含1000张图像）
│
└── horse（文件夹含1000张图像）
需要把数据分成训练集train和验证集val，对train数据集进行训练，达到给定val数据集中的一张猫 / 狗的图片，识别其是猫还是狗的目的
2.数据处理
2.1.数据预处理
设置GPU环境进行训练：
import tensorflow as tf
gpus = tf.config.list_physical_devices("GPU")
if gpus:
tf.config.experimental.set_memory_growth(gpus[0], True) #设置GPU显存用量按需使用
tf.config.set_visible_devices([gpus[0]],"GPU")
# 打印显卡信息，确认GPU可用
print(gpus)
输出：
[PhysicalDevice(name='/physical_device:GPU:0', device_type='GPU')]
导入图片数据：
import matplotlib.pyplot as plt
# 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
# 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)
import pathlib
data_dir = "./data"
data_dir = pathlib.Path(data_dir)
image_count = len(list(data_dir.glob('*/*')))
print("图片总数为：",image_count)
输出：
图片总数为： 4000
之后初始化参数，并使用image_dataset_from_directory方法将磁盘中的数据加载到tf.data.Dataset中
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,
)
官网介绍：tf.keras.utils.image_dataset_from_directory
代码：
batch_size = 4
img_height = 299
img_width = 299
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)
输出：
Found 4000 files belonging to 4 classes.
Using 3200 files for training.
同理配置验证集：
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)
输出：
Found 4000 files belonging to 4 classes.
Using 800 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)
输出：
['cat', 'chook', 'dog', 'horse']
查看batch的数据类型：
for image_batch, labels_batch in train_ds:
print(image_batch.shape)
print(labels_batch.shape)
break
输出：
(4, 299, 299, 3)
(4,)
2.2.可视化数据
plt.figure(figsize=(10, 5)) # 图形的宽为10高为5
plt.suptitle("数据展示")
num = -1
for images, labels in train_ds.take(2):
for i in range(4):
num = num + 1
ax = plt.subplot(2, 4, num + 1)
plt.imshow(images[i].numpy().astype("uint8"))
plt.title(class_names[labels[i]])
plt.savefig('pic1.jpg', dpi=600) #指定分辨率保存
plt.axis("off")
输出：
2.3.配置数据集
shuffle() ： 打乱数据，详细可参考：数据集shuffle方法中buffer_size的理解
prefetch() ：预取数据，加速运行，详细可参考：Better performance with the tf.data API
cache() ：将数据集缓存到内存当中，加速运行
AUTOTUNE = tf.data.AUTOTUNE
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(val_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)
)
2.网络设计
2.1.Xception简单介绍
详细可看：知乎
论文地址：Xception: Deep Learning with Depthwise Separable Convolutions
工程代码：https://github.com/keras-team/keras-applications/blob/master/keras_applications/xception.py
Xception是Google2016年10月提出的，时间在Google家的MobileNet v1之后，MobileNet v2之前。其吸纳了ResNet、Inception、MobileNet v1的设计思想，直接以Inception v3为模子，将里面的基本Inception module的卷积替换为使用 Depthwise Separable Convolution，又外加了残差连接
Xception 的结构基于ResNet，整个网络被分为了三个部分：Entry，Middle和Exit
Entry部分主要是用来不断下采样，减小空间维度Middle部分则是不断学习关联关系，优化特征，其有8个部分；所有的普通卷积和可分离卷积后面都接了BN，不过图中没有给出- 最终
Exit部分则是汇总、整理特征，最后交由FC来进行表达
网络的整个流程如下图，Xception架构有36个卷积层作为网络特征提取的基础，这36个卷积层被分为14个模块，除了第一个和最后一个，其他每一个模块都使用了残差连接
简而言之，Xception架构是一个深度可分离卷积层的线性叠加，这个架构易于修改，仅使用30-40行代码就可以完成
2.2.设计网络模型
#====================================#
# Xception的网络部分
#====================================#
from tensorflow.keras.preprocessing import image
from tensorflow.keras.models import Model
from tensorflow.keras import layers
from tensorflow.keras.layers import Dense,Input,BatchNormalization,Activation,Conv2D,SeparableConv2D,MaxPooling2D
from tensorflow.keras.layers import GlobalAveragePooling2D,GlobalMaxPooling2D
from tensorflow.keras import backend as K
from tensorflow.keras.applications.imagenet_utils import decode_predictions
def Xception(input_shape = [299,299,3],classes=1000):
img_input = Input(shape=input_shape)
#=================#
# Entry flow
#=================#
# block1
# 299,299,3 -> 149,149,64
x = Conv2D(32, (3, 3), strides=(2, 2), use_bias=False, name='block1_conv1')(img_input)
x = BatchNormalization(name='block1_conv1_bn')(x)
x = Activation('relu', name='block1_conv1_act')(x)
x = Conv2D(64, (3, 3), use_bias=False, name='block1_conv2')(x)
x = BatchNormalization(name='block1_conv2_bn')(x)
x = Activation('relu', name='block1_conv2_act')(x)
# block2
# 149,149,64 -> 75,75,128
residual = Conv2D(128, (1, 1), strides=(2, 2), padding='same', use_bias=False)(x)
residual = BatchNormalization()(residual)
x = SeparableConv2D(128, (3, 3), padding='same', use_bias=False, name='block2_sepconv1')(x)
x = BatchNormalization(name='block2_sepconv1_bn')(x)
x = Activation('relu', name='block2_sepconv2_act')(x)
x = SeparableConv2D(128, (3, 3), padding='same', use_bias=False, name='block2_sepconv2')(x)
x = BatchNormalization(name='block2_sepconv2_bn')(x)
x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block2_pool')(x)
x = layers.add([x, residual])
# block3
# 75,75,128 -> 38,38,256
residual = Conv2D(256, (1, 1), strides=(2, 2),padding='same', use_bias=False)(x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block3_sepconv1_act')(x)
x = SeparableConv2D(256, (3, 3), padding='same', use_bias=False, name='block3_sepconv1')(x)
x = BatchNormalization(name='block3_sepconv1_bn')(x)
x = Activation('relu', name='block3_sepconv2_act')(x)
x = SeparableConv2D(256, (3, 3), padding='same', use_bias=False, name='block3_sepconv2')(x)
x = BatchNormalization(name='block3_sepconv2_bn')(x)
x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block3_pool')(x)
x = layers.add([x, residual])
# block4
# 38,38,256 -> 19,19,728
residual = Conv2D(728, (1, 1), strides=(2, 2),padding='same', use_bias=False)(x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block4_sepconv1_act')(x)
x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name='block4_sepconv1')(x)
x = BatchNormalization(name='block4_sepconv1_bn')(x)
x = Activation('relu', name='block4_sepconv2_act')(x)
x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name='block4_sepconv2')(x)
x = BatchNormalization(name='block4_sepconv2_bn')(x)
x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block4_pool')(x)
x = layers.add([x, residual])
#=================#
# Middle flow
#=================#
# block5--block12
# 19,19,728 -> 19,19,728
for i in range(8):
residual = x
prefix = 'block' + str(i + 5)
x = Activation('relu', name=prefix + '_sepconv1_act')(x)
x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv1')(x)
x = BatchNormalization(name=prefix + '_sepconv1_bn')(x)
x = Activation('relu', name=prefix + '_sepconv2_act')(x)
x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv2')(x)
x = BatchNormalization(name=prefix + '_sepconv2_bn')(x)
x = Activation('relu', name=prefix + '_sepconv3_act')(x)
x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv3')(x)
x = BatchNormalization(name=prefix + '_sepconv3_bn')(x)
x = layers.add([x, residual])
#=================#
# Exit flow
#=================#
# block13
# 19,19,728 -> 10,10,1024
residual = Conv2D(1024, (1, 1), strides=(2, 2),
padding='same', use_bias=False)(x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block13_sepconv1_act')(x)
x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name='block13_sepconv1')(x)
x = BatchNormalization(name='block13_sepconv1_bn')(x)
x = Activation('relu', name='block13_sepconv2_act')(x)
x = SeparableConv2D(1024, (3, 3), padding='same', use_bias=False, name='block13_sepconv2')(x)
x = BatchNormalization(name='block13_sepconv2_bn')(x)
x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block13_pool')(x)
x = layers.add([x, residual])
# block14
# 10,10,1024 -> 10,10,2048
x = SeparableConv2D(1536, (3, 3), padding='same', use_bias=False, name='block14_sepconv1')(x)
x = BatchNormalization(name='block14_sepconv1_bn')(x)
x = Activation('relu', name='block14_sepconv1_act')(x)
x = SeparableConv2D(2048, (3, 3), padding='same', use_bias=False, name='block14_sepconv2')(x)
x = BatchNormalization(name='block14_sepconv2_bn')(x)
x = Activation('relu', name='block14_sepconv2_act')(x)
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
inputs = img_input
model = Model(inputs, x, name='xception')
return model
打印模型信息：
深度学习100例 | 第24天-卷积神经网络（Xception）：动物识别
人脸表情识别系统——基于Mini-Xception网络模型实现表情分类