Tensorflow实现猫狗识别

数据集

网盘地址(提取码:lhrr) 数据下载速度比较慢，可以使用网盘。

预处理

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()

划分数据集

# 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))

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

模型训练

# 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')