问题

现在有很多的图片，里面分别有猫与狗，识别这些图片，区分猫与狗

设计解决这个问题的思路

1、下载与放置训练图片

2、现在对应的依赖，tensorflow、numpy等等

3、解析文件名，识别dog还是cat

4、建模

5、对模型进行训练

6、用测试模型进行验证

7、输出结果

8、优化模型 to step4

[1]图片地址

https://www.kaggle.com/c/dogs-vs-cats/data
现在数据，现在速度比较慢，可以使用网盘。

网盘地址(提取码:lhrr)

image.png

【2】处理训练集的数据结构

import os

filenames = os.listdir('./dogs-vs-cats/train’)

# 动物类型

categories = []

for filename in filenames:

    category = filename.split('.')[0]

    categories.append(category)

import pandas as pd

# 结构化数据

df = pd.DataFrame({

    'filename':filenames,

    'category':categories

})

#展示对应的数据

import random

from keras.preprocessing import image

import matplotlib.pyplot as plt

## 看看结构化之后的结果

print(df.head())

print(df.tail())

print(df['category'].value_counts())

df['category'].value_counts().plot(kind = 'bar')

plt.show()

# 展示个图片看看

sample = random.choice(filenames)

image = image.load_img('./dogs-vs-cats/train/' + sample)

plt.imshow(image)

plt.show()

【3】出来训练集与验证集

# 切割训练集合

train_df, validate_df = train_test_split(df, test_size = 0.20, random_state = 42)

train_df = train_df.reset_index(drop=True)

validate_df = validate_df.reset_index(drop=True)

print(train_df.head())

print(validate_df.head())

total_train = train_df.shape[0]

total_validate = validate_df.shape[0]

print("Total number of example in training dataset : {0}".format(total_train))

print("Total number of example in validation dataset : {0}".format(total_validate))

【4】创建模型

from tensorflow.keras.models import Sequential

from tensorflow.keras.layers import Conv2D, MaxPooling2D, Dense, BatchNormalization, Flatten,Dropout

from tensorflow.keras import optimizers

## 创建第一个模型

class Model:

def __init__(self, IMG_WIDTH, IMG_HEIGHT, IMG_CHANNELS):

    self.IMG_WIDTH = IMG_WIDTH

    self.IMG_HEIGHT = IMG_HEIGHT

    self.IMG_CHANNELS = IMG_CHANNELS

def create_model(self):

    model = Sequential()

    #第一层

    #图像空间的2维卷积 32个卷积输出滤波器，卷积窗口的高度和宽度(3,3)，输入像素150*150

    model.add(Conv2D(32, (3,3), activation = 'relu', kernel_initializer='he_uniform',

    padding='same',input_shape = (150, 150, 3)))

    #卷积窗口的高度和宽度降低为(2,2)

    model.add(MaxPooling2D((2,2)))

    #第二层

    model.add(Conv2D(64, (3,3), activation = 'relu'))

    model.add(MaxPooling2D((2,2)))

    #第三层

    model.add(Conv2D(128, (3,3), activation = 'relu'))

    model.add(MaxPooling2D((2,2)))

    #第四层

    model.add(Conv2D(128, (3,3), activation = 'relu'))

    model.add(MaxPooling2D((2,2)))

    #Flatten层用来将输入“压平”，即把多维的输入一维化

    model.add(Flatten())

    #全链接层,输出空间的维数

    model.add(Dense(512, activation = 'relu'))

    model.add(Dense(1, activation = 'sigmoid'))

    from keras import optimizers

    # 设置损失算法与优化

    model.compile(loss = 'binary_crossentropy', optimizer = optimizers.RMSprop(lr = 1e-4), metrics =['acc'])

    return model

【5】训练模型

# 初始化模型

IMG_WIDTH = 150

IMG_HEIGHT = 150

IMG_CHANNELS = 3

model = Model(IMG_WIDTH, IMG_HEIGHT, IMG_CHANNELS)

model_1 = model.create_model()

model_1.summary()

from keras.preprocessing.image import ImageDataGenerator

#原来是255的像素做 0与1的处理

train_imgdatagen = ImageDataGenerator(rescale = 1./255)

valid_imgdatagen = ImageDataGenerator(rescale = 1./255)

train_generator_m1 = train_imgdatagen.flow_from_dataframe(

                        train_df,

                        directory="./dogs-vs-cats/train",

                        x_col='filename',

                        y_col='category',

                        target_size = (150, 150), # resize image to 150x150

                        batch_size = 64,

                        class_mode = 'binary'

                    )

validation_generator_m1 = valid_imgdatagen.flow_from_dataframe(

                            validate_df,

                            directory="./dogs-vs-cats/train",

                            x_col='filename',

                            y_col='category',

                            target_size = (150, 150), # resize image to 150x150

                            batch_size = 64,

                            class_mode = 'binary'

                    )

import numpy as np

# model 1 开始训练

history_1 = model_1.fit(

        train_generator_m1,

        epochs = 30,

        steps_per_epoch = 100,

        validation_data = validation_generator_m1,

        validation_steps = 50

)

#保存模型

model_1.save('model_1.h5')

【6】打印训练结果

print(np.mean(history_1.history['acc']))

print(np.mean(history_1.history['val_acc']))

【7】形成图像结果

plt.plot(history_1.history['acc'], color = 'black')

plt.plot(history_1.history['val_acc'], color = 'blue')

plt.title('Training and validation accuracy of model 1')

plt.xlabel('Epochs')

plt.ylabel('Accuracy’)4

plt.show()

plt.plot(history_1.history['loss'], color = 'black')

plt.plot(history_1.history['val_loss'], color = 'blue')

plt.title('Training and validation loss of model 1')

plt.xlabel('Epochs')

plt.ylabel('Accuracy')

plt.show()

image.png image.png