本文共 20363 字，大约阅读时间需要 67 分钟。

卷积神经网络：猫狗识别

目录

• 第一步：导入数据集
• 第二步：数据预处理
• 第三步：迁移学习
• 第四步：模型保存
• 第五步：模型融合

第一步：导入数据集

kaggle猫狗大战数据集地址:

# 将kaggle的数据集直接下载到codelab中!pip install -U -q kaggle!mkdir -p ~/.kaggle!echo '{"username":"填写你自己的username","key":"填写你自己的key"}' > ~/.kaggle/kaggle.json!chmod 600 ~/.kaggle/kaggle.json!kaggle competitions download -c dogs-vs-cats-redux-kernels-edition

Downloading test.zip to /content 98% 265M/271M [00:02<00:00, 125MB/s]100% 271M/271M [00:02<00:00, 115MB/s]Downloading train.zip to /content 99% 536M/544M [00:03<00:00, 192MB/s]100% 544M/544M [00:03<00:00, 163MB/s]Downloading sample_submission.csv to /content  0% 0.00/111k [00:00
   

# 将文件解压! unzip ./train.zip ! unzip ./test.zip

总之，训练集有25000张图片，猫狗各占一半。测试集有12500张，没有标定是猫还是狗

!ls ./train

可以看出图片名是以type.number.jpg格式命名的

# 导入开发需要的库import kerasimport osimport shutilimport threadingimport numpy as npimport cv2import h5pyfrom tqdm import tqdmfrom sklearn.model_selection import train_test_splitfrom keras.models import *from keras.layers import *from keras.applications import *from keras.preprocessing import *from keras.preprocessing.image import *

Using TensorFlow backend.

第二步：数据预处理

加载数据

def load_data(load_type="train"):    path = None    n = 25000    if load_type=="train":        imgs = []        labels = []                path = "./train/"        img_names = os.listdir(path)                for name in img_names:            imgs.append("train/"+name)            labels.append([0] if name[:3] == "cat" else [1])                    train_img_names,valid_img_names,train_labels,valid_labels = train_test_split(imgs,labels,test_size=0.2,random_state=42)        return train_img_names,valid_img_names,train_labels,valid_labels    else:        # test,don`t have the labels        path = "./test"        img_names = os.listdir(path)        imgs = []        for img in img_names:            imgs.append(img)                        return imgs

train_img_names,valid_img_names,train_labels,valid_labels = load_data()

print(train_img_names[:5])print(train_labels[:5])print(len(train_img_names)+len(valid_img_names))

['train/dog.12105.jpg', 'train/cat.10129.jpg', 'train/dog.11009.jpg', 'train/dog.9346.jpg', 'train/dog.1599.jpg'][[1], [0], [1], [1], [1]]25000

数据准备之后，接下来就是准备开始训练:

预先步骤：

• 分别初始化三个Generator(train,valid,test)
• 加载预训练网络
• 进行微调（迁移学习）
• 调参

# 定义keras的generator方法# custom keras generatorclass MOGenerator(keras.utils.Sequence):    def __init__(self, data, n, des_size=(224, 224), means=None, stds=None,                 is_directory=True, batch_size=32, shuffle=True, seed=0):        '''        data: tuple of (x,y)        n: data size        des_size: standard size        means: the dataset mean of RGB,default is imagenet means [103.939, 116.779, 123.68]        batch_size: default is 32        shuffle: random the data,default is True        '''        self.x = np.array(data[0])        if len(data) >= 2:            self.y = np.array(data[1])        else:            self.y = None        self.n = n        self.des_size = des_size        self.is_directory = is_directory        self.batch_size = batch_size        self.shuffle = shuffle        self.lock = threading.Lock()        self.index_array = self._set_index_array()        self.means = means        self.stds = stds    def reset_index(self):        self.batch_index = 0    def _set_index_array(self):        self.index_array = np.arange(self.n)        if self.shuffle:            np.random.shuffle(self.index_array)    def on_epoch_end(self):        # 重置索引数组        self._set_index_array()    def __len__(self):        # 计算batch的总数量        return int(np.ceil(self.n / self.batch_size))    def __getitem__(self, idx):        if self.index_array is None:            self._set_index_array()        index_array = self.index_array[self.batch_size * idx:                                       self.batch_size * (idx + 1)]        return self._data_generate(index_array)    def _data_generate(self, index_array):        # read from path        # request the memory        imgs = np.zeros((len(index_array), self.des_size[0], self.des_size[1], 3), dtype=np.uint8)        # read the data        if self.is_directory:            img_names = self.x[index_array]            for name_index in range(len(img_names)):                 img = cv2.imread(img_names[name_index])                if img is not None:                    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)                    img = cv2.resize(img, self.des_size)                    imgs[name_index] = img        else:            for i in range(len(index_array)):                img = self.x[index_array[i]]                img = cv2.resize(img, self.des_size)                imgs[i] = img        if self.y is not None:            labels = self.y[index_array]        if labels is None:            return imgs        else:            return imgs, labels

我们会使用3个模型去迁移学习，它们的对输入图片的大小要求不同，所以我们会初始化不同大小的 Generator

batch_size = 32train_img_names,valid_img_names,train_labels,valid_labels = load_data()test_img_names = load_data(load_type="test")train_generator_224 = MOGenerator((train_img_names,train_labels), len(train_img_names), des_size=(224,224),                                  batch_size=batch_size, shuffle=True)train_generator_299 = MOGenerator((train_img_names,train_labels), len(train_img_names), des_size=(299,299),                                  batch_size=batch_size, shuffle=True)valid_generator_299 = MOGenerator((valid_img_names,valid_labels), len(valid_img_names), des_size=(299,299),                                  batch_size=batch_size, shuffle=False)valid_generator_224 = MOGenerator((valid_img_names,valid_labels), len(valid_img_names), des_size=(224,224),                                  batch_size=batch_size, shuffle=True)test_generator_299 = MOGenerator((test_img_names), len(test_img_names), des_size=(299,299),                                  batch_size=batch_size, shuffle=False)test_generator_224 = MOGenerator((test_img_names), len(test_img_names), des_size=(224,224),                                  batch_size=batch_size, shuffle=False)

第三步:迁移学习

我们要完成三个模型的迁移(Resnet,Inception,Xception)

下面开始第一个模型的迁移(Resnet)

# 加载Resnet50网络, Include_top: 是否包含卷积之后的全连接层.base_model = ResNet50(input_tensor=Lambda(resnet50.preprocess_input)(Input(shape=(224,224,3))),                       weights="imagenet", include_top=False)# 遍历所有层, 将预训练模型的卷积层设置为不可训练, 这样它们的参数就不会被改变了.for layers in base_model.layers:    layers.trainable = False# 重新设置输出层, 我们的类别是两类, 只需要一个神经元即可.x = GlobalAveragePooling2D()(base_model.output)x = Dropout(0.25)(x)x = Dense(1, activation="sigmoid")(x)# 实例化模型model = Model(base_model.input, x)# 设置优化器, 损失函数, 展示参数信息model.compile(optimizer="adam",              loss="binary_crossentropy",              metrics=["accuracy"])# 开始训练, 通过设置迭代器模式model.fit_generator(train_generator_224,len(train_img_names)//batch_size,epochs=5,                    validation_data=valid_generator_224,validation_steps=len(valid_img_names)//batch_size,shuffle=False)

Epoch 1/5625/625 [==============================] - 101s 162ms/step - loss: 0.1142 - acc: 0.9540 - val_loss: 0.0467 - val_acc: 0.9840Epoch 2/5625/625 [==============================] - 97s 155ms/step - loss: 0.0671 - acc: 0.9747 - val_loss: 0.0397 - val_acc: 0.9873Epoch 3/5625/625 [==============================] - 98s 156ms/step - loss: 0.0633 - acc: 0.9752 - val_loss: 0.0371 - val_acc: 0.9875Epoch 4/5625/625 [==============================] - 98s 157ms/step - loss: 0.0607 - acc: 0.9773 - val_loss: 0.0479 - val_acc: 0.9847Epoch 5/5625/625 [==============================] - 98s 157ms/step - loss: 0.0582 - acc: 0.9769 - val_loss: 0.0403 - val_acc: 0.9873
   

实现Inception模型的迁移

## inceptioninception = inception_v3.InceptionV3(include_top=False,        weights="imagenet",input_tensor=Lambda(inception_v3.preprocess_input)(Input(shape=(299,299,3))),pooling="avg")output = inception.outputoutput = Dropout(0.25)(output)prediction = Dense(1,activation="sigmoid")(output)inception_model = Model(inputs=inception.input,outputs=prediction)for layer in inception.layers: #[:-res_global_pool_index]    layer.trainable = Falseinception_model.compile(optimizer="adam",loss="binary_crossentropy",metrics=["accuracy"])inception_model.fit_generator(train_generator_299,(len(train_img_names) + batch_size - 1)//batch_size,epochs=5,                       validation_data=valid_generator_299,validation_steps=len(valid_img_names)//batch_size)

W0812 06:20:46.242835 139830584244096 deprecation_wrapper.py:119] From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:3980: The name tf.nn.avg_pool is deprecated. Please use tf.nn.avg_pool2d instead.Downloading data from https://github.com/fchollet/deep-learning-models/releases/download/v0.5/inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h587916544/87910968 [==============================] - 1s 0us/stepEpoch 1/5625/625 [==============================] - 125s 200ms/step - loss: 0.1636 - acc: 0.9425 - val_loss: 0.0436 - val_acc: 0.9894Epoch 2/5625/625 [==============================] - 118s 189ms/step - loss: 0.0878 - acc: 0.9687 - val_loss: 0.0647 - val_acc: 0.9817Epoch 3/5625/625 [==============================] - 118s 188ms/step - loss: 0.0818 - acc: 0.9692 - val_loss: 0.0571 - val_acc: 0.9851Epoch 4/5625/625 [==============================] - 118s 188ms/step - loss: 0.0756 - acc: 0.9715 - val_loss: 0.0531 - val_acc: 0.9863Epoch 5/5625/625 [==============================] - 118s 189ms/step - loss: 0.0780 - acc: 0.9715 - val_loss: 0.0611 - val_acc: 0.9833
   

实现XCeption的迁移学习

## xceptionxcep = Xception(include_top=False, weights="imagenet",                 input_tensor=Lambda(xception.preprocess_input)(Input(shape=(299,299,3))),pooling="avg")output = xcep.outputoutput = Dropout(0.25)(output)prediction = Dense(1,activation="sigmoid")(output)xcep_model = Model(inputs=xcep.input,outputs=prediction)for layer in xcep.layers:    layer.trainable = Falsexcep_model.compile(optimizer="adam",loss="binary_crossentropy",metrics=["accuracy"])xcep_model.fit_generator(train_generator_299,(len(train_img_names) + batch_size - 1)//batch_size,epochs=5,                       validation_data=valid_generator_299,validation_steps=len(valid_img_names)//batch_size)

Downloading data from https://github.com/fchollet/deep-learning-models/releases/download/v0.4/xception_weights_tf_dim_ordering_tf_kernels_notop.h583689472/83683744 [==============================] - 1s 0us/stepEpoch 1/5625/625 [==============================] - 280s 447ms/step - loss: 0.1085 - acc: 0.9721 - val_loss: 0.0816 - val_acc: 0.9796Epoch 2/5625/625 [==============================] - 274s 439ms/step - loss: 0.0508 - acc: 0.9847 - val_loss: 0.0775 - val_acc: 0.9783Epoch 3/5625/625 [==============================] - 275s 440ms/step - loss: 0.0452 - acc: 0.9851 - val_loss: 0.0530 - val_acc: 0.9869Epoch 4/5625/625 [==============================] - 275s 440ms/step - loss: 0.0392 - acc: 0.9868 - val_loss: 0.0516 - val_acc: 0.9871Epoch 5/5625/625 [==============================] - 274s 438ms/step - loss: 0.0411 - acc: 0.9857 - val_loss: 0.0785 - val_acc: 0.9775
   

第四步：模型保存

训练完成后，需要将模型保存，方便下次调用和二次训练

model.save_weights("resnet.h5")model.save_weights("xcep.h5")model.save_weights("incep.h5")

第五步:模型融合

导出特征向量

由于数据集的文件名是type.num.jpg这样的方式命名的，但是使用keras的ImageDataGenerator需要将不同种类的图片分在不同的文件中，因此我们需要对数据集进行处理。

这里采取的思路是创建符号链接，这样的好处是不用复制一遍图片，占用不必要的空间。

from keras.preprocessing.image import *# 获取所有训练集的图片名train_filenames = os.listdir("train")test_filenames = os.listdir("test")# 文件名是特殊命名形式的, 所以直接获取分类后的文件train_cat = list(filter(lambda x:x[:3] == 'cat', train_filenames))train_dog = list(filter(lambda x:x[:3] == 'dog', train_filenames))def rmrf_mkdir(dirname):    if os.path.exists(dirname):        shutil.rmtree(dirname)    os.mkdir(dirname)# 创建目录rmrf_mkdir('train2')os.mkdir('train2/cat')os.mkdir('train2/dog')rmrf_mkdir('valid2')os.mkdir('valid2/cat')os.mkdir('valid2/dog')rmrf_mkdir('test2')os.mkdir("test2/test")for filename in test_filenames:  # 建立软链（不会从创建文件, 有点类似快捷方式）  os.symlink("/content/test/"+filename, "/content/test2/test/"+filename)for filename in train_cat[:-2500]:  os.symlink("/content/train/"+filename, "/content/train2/cat/"+filename)for filename in train_dog[:-2500]:  os.symlink("/content/train/"+filename, "/content/train2/dog/"+filename)for filename in train_cat[-2500:]:  os.symlink("/content/train/"+filename, "/content/valid2/cat/"+filename)    for filename in train_dog[-2500:]:  os.symlink("/content/train/"+filename, "/content/valid2/dog/"+filename)    # 使用Keras默认的生成器, 因为我们已经生成对应的目录了# 224 是 resnet的处理方式, 299是xception, inception的处理大小gen = ImageDataGenerator()train_generator_224 = gen.flow_from_directory("train2", (224,224), shuffle=False,                                               batch_size=batch_size,class_mode='binary')valid_generator_224 = gen.flow_from_directory("valid2", (224,224), shuffle=False,                                               batch_size=batch_size,class_mode='binary')test_generator_224 = gen.flow_from_directory("test2", (224,224), shuffle=False,                                              batch_size=batch_size, class_mode=None)train_generator_299 = gen.flow_from_directory("train2", (299,299), shuffle=False,                                               batch_size=batch_size,class_mode='binary')valid_generator_299 = gen.flow_from_directory("valid2", (299,299), shuffle=False,                                               batch_size=batch_size,class_mode='binary')test_generator_299 = gen.flow_from_directory("test2", (299,299), shuffle=False,                                              batch_size=batch_size, class_mode=None)

Found 20000 images belonging to 2 classes.Found 5000 images belonging to 2 classes.Found 12500 images belonging to 1 classes.Found 20000 images belonging to 2 classes.Found 5000 images belonging to 2 classes.Found 12500 images belonging to 1 classes.

保存特征向量到本地

import h5py# 特征向量的保存方法def write_feature(model_name,model,train_generator,train_labels,valid_generator,valid_labels,test_generator,batch_size=32):    # 通过模型名字来加载不同的权重    if model_name == 'resnet_feature':        model.load_weights('resnet.h5',by_name=True)    elif model_name == 'inception_feature':        model.load_weights('incep.h5',by_name=True)    else:        model.load_weights('xcep.h5',by_name=True)    # 转换为numpy数组    train_labels = np.array(train_labels)    valid_labels = np.array(valid_labels)    # 直接进行输出, 得到特征向量    train_feature = model.predict_generator(train_generator,int(np.ceil(train_generator.samples/batch_size)),verbose=1)    valid_feature = model.predict_generator(valid_generator,int(np.ceil(valid_generator.samples/batch_size)),verbose=1)    test_feature  = model.predict_generator(test_generator,int(np.ceil(test_generator.samples/batch_size)),verbose=1)    print("train_feature.shape:",train_feature.shape)    print("valid_feature.shape:",valid_feature.shape)    # 保存到本地    with h5py.File(model_name+'.h5','w') as file:        file.create_dataset("train",data=train_feature,dtype="float32")        file.create_dataset('trian_labels',data=np.array(train_generator.classes),dtype="uint8")        file.create_dataset("valid",data=valid_feature,dtype="float32")        file.create_dataset("valid_labels",data=np.array(valid_generator.classes),dtype="uint8")        file.create_dataset("test",data=test_feature,dtype="float32")

# resnet50write_feature('resnet_feature',Model(inputs=model.input,outputs=model.layers[-3].output),              train_generator_224,train_labels,valid_generator_224,valid_labels,test_generator_224)

625/625 [==============================] - 85s 136ms/step157/157 [==============================] - 21s 132ms/step391/391 [==============================] - 53s 136ms/steptrain_feature.shape: (20000, 2048)valid_feature.shape: (5000, 2048)

# inceptionwrite_feature('inception_feature',Model(inputs=inception_model.input,outputs=inception_model.layers[-3].output),              train_generator_299,train_labels, valid_generator_299,valid_labels,test_generator_299)

625/625 [==============================] - 96s 154ms/step157/157 [==============================] - 24s 152ms/step391/391 [==============================] - 60s 155ms/steptrain_feature.shape: (20000, 2048)valid_feature.shape: (5000, 2048)

# xceptionwrite_feature('xception_feature',Model(inputs=xcep_model.input,outputs=xcep_model.layers[-3].output),              train_generator_299,train_labels,valid_generator_299,valid_labels,test_generator_299)

625/625 [==============================] - 228s 364ms/step157/157 [==============================] - 57s 360ms/step391/391 [==============================] - 142s 364ms/steptrain_feature.shape: (20000, 2048)valid_feature.shape: (5000, 2048)

搭建融合的模型

feature_files = ['resnet_feature.h5','inception_feature.h5','xception_feature.h5']X_train = []y_train = []X_valid = []y_valid = []X_test = []for file_name in feature_files:    with h5py.File(file_name, 'r') as h:        X_train.append(np.array(h['train']))        X_valid.append(np.array(h['valid']))        X_test.append(np.array(h['test']))        y_train = np.array(h['trian_labels'])        y_valid = np.array(h['valid_labels'])        print(np.array(h['train']).shape,np.array(h['valid']).shape,np.array(h['test']).shape)X_train = np.concatenate(X_train, axis=1)X_valid = np.concatenate(X_valid, axis=1)X_test = np.concatenate(X_test, axis=1)print("last:",X_train.shape,X_valid.shape,X_test.shape)

(20000, 2048) (5000, 2048) (12500, 2048)(20000, 2048) (5000, 2048) (12500, 2048)(20000, 2048) (5000, 2048) (12500, 2048)last: (20000, 6144) (5000, 6144) (12500, 6144)

训练融合模型

直接在特征向量上进行训练

from sklearn.utils import shuffle# 打乱数据，模拟现实中的随机效果X_train, y_train = shuffle(X_train, y_train)

import keras.utilsinput_tensor = Input(X_train.shape[1:])x = input_tensorx = Dropout(0.5)(x)x = Dense(1, activation='sigmoid')(x)concatenate_model = Model(inputs=input_tensor, outputs=x)concatenate_model.compile(optimizer='adam',              loss='binary_crossentropy',              metrics=['accuracy'])concatenate_model.fit(X_train,y_train,batch_size=128, epochs=5,validation_data=(X_valid,y_valid))#validation_split=0.2

Train on 20000 samples, validate on 5000 samplesEpoch 1/520000/20000 [==============================] - 4s 176us/step - loss: 0.0430 - acc: 0.9850 - val_loss: 0.0093 - val_acc: 0.9978Epoch 2/520000/20000 [==============================] - 1s 45us/step - loss: 0.0109 - acc: 0.9967 - val_loss: 0.0067 - val_acc: 0.9980Epoch 3/520000/20000 [==============================] - 1s 46us/step - loss: 0.0085 - acc: 0.9970 - val_loss: 0.0053 - val_acc: 0.9980Epoch 4/520000/20000 [==============================] - 1s 46us/step - loss: 0.0065 - acc: 0.9982 - val_loss: 0.0051 - val_acc: 0.9982Epoch 5/520000/20000 [==============================] - 1s 45us/step - loss: 0.0057 - acc: 0.9983 - val_loss: 0.0052 - val_acc: 0.9986
   

结果预测

hint：这里我们使用了 clip 函数，这个是一个比赛中的一个非常有效的 Trick（注意，这里强调了比赛，实际项目是没有什么效果的），将我们的输出限制住范围，，如果输出是绝对的，就可以减少损失，提高排名

import pandas as pdy_pred = concatenate_model.predict(X_test, verbose=1)y_pred = y_pred.clip(min=0.005, max=0.995)df = pd.read_csv("sample_submission.csv")image_size = (224, 224)gen = ImageDataGenerator()test_generator = gen.flow_from_directory("/content/test2/", image_size, shuffle=False,                                          batch_size=16, class_mode=None)for i, fname in enumerate(test_generator.filenames):    index = int(fname[fname.rfind('/')+1:fname.rfind('.')])    df.set_value(index-1, 'label', y_pred[i])df.to_csv('sample_submission.csv', index=None)print(df.head(20))

12500/12500 [==============================] - 1s 69us/stepFound 12500 images belonging to 1 classes.    id     label0    1  0.9868341    2  0.9950002    3  0.9950003    4  0.9950004    5  0.0050005    6  0.0050006    7  0.0050007    8  0.0050008    9  0.0050009   10  0.00500010  11  0.00500011  12  0.99500012  13  0.00500013  14  0.00500014  15  0.00500015  16  0.00500016  17  0.99500017  18  0.99500018  19  0.00500019  20  0.005000/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py:14: FutureWarning: set_value is deprecated and will be removed in a future release. Please use .at[] or .iat[] accessors instead

提交结果

!kaggle competitions submit -c dogs-vs-cats-redux-kernels-edition -f sample_submission.csv -m "Message"

100% 306k/306k [00:01<00:00, 238kB/s]Successfully submitted to Dogs vs. Cats Redux: Kernels Edition

最终得分:0.07584

转载地址：https://codingchaozhang.blog.csdn.net/article/details/99309528 如侵犯您的版权，请留言回复原文章的地址，我们会给您删除此文章，给您带来不便请您谅解！