深度学习--猫狗图像分类

1、环境介绍
python3.6，tensorflow1.4版本，pycharm编译器
2、函数库导入

import cv2
import matplotlib.pyplot as plt
import os, PIL, pathlib
import numpy as np
from tensorflow.keras.layers import Conv2D,MaxPooling2D,Dropout,Dense,Flatten,Activation
import pandas as pd
from tensorflow.keras.models import Sequential
import warnings
from tensorflow import keras
import pathlib
from tensorflow.keras.layers import BatchNormalization
import tensorflow as tf

3、数据集获取
数据集链接，含有猫狗两类图像，图像尺寸不等，猫狗图片各1000张。

猫：

狗：
4、神经网络搭建：

def createModel(num_classes):
    model = Sequential()  # 顺序模型
    model.add(
        Conv2D(16, (5, 5), strides=(2, 2), padding="same", input_shape=(256, 256, 3), data_format='channels_last',
               kernel_initializer='uniform', activation="relu"))
    model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
    model.add(Conv2D(32, (3, 3), strides=(2, 2), activation="relu"))
    model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))

    model.add(Conv2D(64, (3, 3), activation="relu"))
    model.add(Conv2D(128, (3, 3), activation="relu"))
    model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name="pool5"))

    model.add(Conv2D(256, (1, 1), activation="relu"))
    model.add(Dropout(0.25))
    model.add(Flatten())
    model.add(Dense(256))
    model.add(BatchNormalization())
    model.add(Activation('relu'))
    model.add(BatchNormalization())
    model.add(Dropout(0.5))
    model.add(Dense(num_classes))
    model.add(BatchNormalization())
    model.add(Activation("softmax"))
    model.summary()
    return model

神经网络结构如下：

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d (Conv2D)              (None, 128, 128, 16)      1216      
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 64, 64, 16)        0         
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 31, 31, 32)        4640      
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 15, 15, 32)        0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 13, 13, 64)        18496     
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 11, 11, 128)       73856     
_________________________________________________________________
pool5 (MaxPooling2D)         (None, 5, 5, 128)         0         
_________________________________________________________________
conv2d_4 (Conv2D)            (None, 5, 5, 256)         33024     
_________________________________________________________________
dropout (Dropout)            (None, 5, 5, 256)         0         
_________________________________________________________________
flatten (Flatten)            (None, 6400)              0         
_________________________________________________________________
dense (Dense)                (None, 256)               1638656   
_________________________________________________________________
batch_normalization (BatchNo (None, 256)               1024      
_________________________________________________________________
activation (Activation)      (None, 256)               0         
_________________________________________________________________
batch_normalization_1 (Batch (None, 256)               1024      
_________________________________________________________________
dropout_1 (Dropout)          (None, 256)               0         
_________________________________________________________________
dense_1 (Dense)              (None, 2)                 514       
_________________________________________________________________
batch_normalization_2 (Batch (None, 2)                 8         
_________________________________________________________________
activation_1 (Activation)    (None, 2)                 0         
=================================================================
Total params: 1,772,458
Trainable params: 1,771,430
Non-trainable params: 1,028

5、训练结果展示：

print(history.history.keys())
plt.plot(history.history['accuracy'])
plt.plot(history.history['val_accuracy'])
plt.title('model1 accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['trian','test'],loc='upper left')
plt.show()

plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('model1 loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['trian','test'],loc='upper left')
plt.show()

6、完整代码：

import cv2
import matplotlib.pyplot as plt
import os, PIL, pathlib
import numpy as np
from tensorflow.keras.layers import Conv2D,MaxPooling2D,Dropout,Dense,Flatten,Activation
import pandas as pd
from tensorflow.keras.models import Sequential
import warnings
from tensorflow import keras
import pathlib
from tensorflow.keras.layers import BatchNormalization
import tensorflow as tf
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
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
# 数据集路径
trainpath='.\data\cats_and_dogs_v2\\train'
testpath='.\data\cats_and_dogs_v2\\test'
trainpath1 = pathlib.Path(trainpath)
# testpath1 = pathlib.Path(testpath)
m= len(list(trainpath1.glob('*/*')))
m2= len(list(trainpath1.glob('*/*')))
# 图片尺寸
batch_size = 16
# img_height = 50
# img_width  = 50
# 二分类
num_classes=2
def changeDim(img):#扩展维度变4维
    img=np.expand_dims(img,axis=2)#
    return img
def Generator(path, batch_size):
    data = []
    label = []
    while True:
        file = os.listdir(path)
        i = 0
        img1 = []
        img2 = []
        imgname1 = os.listdir(path + '/' + file[0])
        imgname2 = os.listdir(path + '/' + file[1])
        # print(imgname1)
        for name1 in imgname1:
            img1.append(path + '/' + file[0] + '/' + name1)
        for name2 in imgname2:
            img2.append(path + '/' + file[1] + '/' + name2)
        imgname = img1 + img2  ######横向连接
        # print(imgname)
        # print((len(imgname)))
        np.random.shuffle(imgname)
        # 猫是0，狗是1
        for finame in imgname:
            im = cv2.imread(finame)
            im = cv2.resize(im,(256,256))
            label_a = finame.split('/')[-2]

            # print(label_a)
            if label_a=='cats':
                label_a=0
            else:
                label_a = 1

            # im = changeDim(im)
            # print(im.shape)
            data.append(im)
            # print(data.shape)
            label.append(label_a)
            if (len(label) == batch_size):
                data = np.array(data)
                data = data.astype('float32')
                data /= 255.0
                label = keras.utils.to_categorical(label, 2)
                yield data, label
                data = []
                label = []
            i += 1
def createModel(num_classes):
    model = Sequential()  # 顺序模型
    model.add(
        Conv2D(16, (5, 5), strides=(2, 2), padding="same", input_shape=(256, 256, 3), data_format='channels_last',
               kernel_initializer='uniform', activation="relu"))
    model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
    model.add(Conv2D(32, (3, 3), strides=(2, 2), activation="relu"))
    model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))

    model.add(Conv2D(64, (3, 3), activation="relu"))
    model.add(Conv2D(128, (3, 3), activation="relu"))
    model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name="pool5"))

    model.add(Conv2D(256, (1, 1), activation="relu"))
    model.add(Dropout(0.25))
    model.add(Flatten())
    model.add(Dense(256))
    model.add(BatchNormalization())
    model.add(Activation('relu'))
    model.add(BatchNormalization())
    model.add(Dropout(0.5))
    model.add(Dense(num_classes))
    model.add(BatchNormalization())
    model.add(Activation("softmax"))
    model.summary()
    return model
model = createModel(num_classes)
model.compile(optimizer="adam",
                loss='binary_crossentropy',
                metrics=['accuracy'])
from tensorflow.keras.callbacks import ModelCheckpoint, Callback, EarlyStopping, ReduceLROnPlateau, LearningRateScheduler

NO_EPOCHS = 50
PATIENCE  = 5
VERBOSE   = 1

# 设置动态学习率
annealer = LearningRateScheduler(lambda x: 1e-3 * 0.99 ** (x+NO_EPOCHS))

# 设置早停
earlystopper = EarlyStopping(monitor='loss', patience=PATIENCE, verbose=VERBOSE)

#
checkpointer = ModelCheckpoint('best_model.h5',
                                monitor='val_accuracy',
                                verbose=VERBOSE,
                                save_best_only=True,
                                save_weights_only=True)
history=model.fit_generator(Generator(trainpath, batch_size),
                    steps_per_epoch=int(m) // batch_size,
                    epochs=NO_EPOCHS,
                    verbose=1,
                    shuffle=True,
                    callbacks=[earlystopper, checkpointer, annealer])

# 保存训练模型

model.save('best_model.h5')
# score = model.evaluate(Generator(testpath, batch_size), verbose=0)
score = model.evaluate_generator(Generator(testpath,batch_size),steps=int(m2) // batch_size)
print(history.history.keys())
plt.plot(history.history['acc'])
# plt.plot(history.history['val_accuracy'])
plt.title('model1 accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['trian','test'],loc='upper left')
plt.show()

plt.plot(history.history['loss'])
# plt.plot(history.history['val_loss'])
plt.title('model1 loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['trian','test'],loc='upper left')
plt.show()