深度学习猫狗大战 tensorflow 自己的数据集制作

1、数据介绍

这份数据集来源于Kaggle，数据集有12500只猫和12500只狗。在这里简单介绍下整体思路
1、1从图片中直接训练一个小网络（作为基准方法），也就是普通的cnn方法
2、2后面我会用到最新的预训练好的resnet等方法进行训练

2 数据提升与cnn

为了尽量利用我们有限的训练数据，我们将通过一系列随机变换堆数据进行提升，这样我们的模型将看不到任何两张完全相同的图片，这有利于我们抑制过拟合，使得模型的泛化能力更好。
在Keras中，这个步骤可以通过keras.preprocessing.image.ImageGenerator来实现，这个类使你可以：
在训练过程中，设置要施行的随机变换
通过.flow或.flow_from_directory(directory)方法实例化一个针对图像batch的生成器，这些生成器可以被用作keras模型相关方法的输入，如fit_generator，evaluate_generator和predict_generator
2、1 代码与解释

import os  # 处理字符串路径
import glob  # 查找文件
from keras.models import Sequential  # 导入Sequential模型
from keras.layers.core import Flatten, Dense, Dropout
from keras.layers.convolutional import Convolution2D, MaxPooling2D, ZeroPadding2D
from keras.optimizers import SGD
import numpy as np
from pandas import Series, DataFrame
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten
from keras.layers.advanced_activations import PReLU
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.optimizers import SGD, Adadelta, Adagrad
from keras.utils import np_utils, generic_utils
from six.moves import range
#加载数据
model = Sequential()
#第一个卷积层，4个卷积核，每个卷积核大小5*5。1表示输入的图片的通道,灰度图为1通道。
#激活函数用relu
#你还可以在model.add(Activation('relu'))后加上dropout的技巧，防止过拟合
model.add(Dropout(0.5))
model.add(Convolution2D(4, 5, 5,input_shape=(224, 224,3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
#第二个卷积层，8个卷积核，每个卷积核大小3*3。4表示输入的特征图个数，等于上一层的卷积核个数
#激活函数用relu
#采用maxpooling，poolsize为(2,2)
model.add(Convolution2D(8, 3, 3))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
#第三个卷积层，16个卷积核，每个卷积核大小3*3
#激活函数用relu
#采用maxpooling，poolsize为(2,2)
model.add(Convolution2D(16, 3, 3))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
#全连接层，先将前一层输出的二维特征图flatten为一维的。
#全连接有128个神经元节点,初始化方式为normal
model.add(Flatten())
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.5))
#sigmoid分类，输出是2类别
model.add(Dense(1))
model.add(Activation('sigmoid'))

model.compile(loss='binary_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])

train_datagen = ImageDataGenerator(
        rescale=1./255,
        shear_range=0.2,
        zoom_range=0.2,
        horizontal_flip=True)

# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = ImageDataGenerator(rescale=1./255)

# this is a generator that will read pictures found in
# subfolers of 'data/train', and indefinitely generate
# batches of augmented image data
train_generator = train_datagen.flow_from_directory(
        'd:/train2',  # this is the target directory
        target_size=(224, 224),  # all images will be resized to 150x150
        batch_size=32,
        class_mode='binary')  # since we use binary_crossentropy loss, we need binary labels

# this is a similar generator, for validation data
validation_generator = test_datagen.flow_from_directory(
        'd:/validation',
        target_size=(224, 224),
        batch_size=32,
        class_mode='binary')
model.fit_generator(
        train_generator,
        samples_per_epoch=2000,
        nb_epoch=50,
        validation_data=validation_generator,
        nb_val_samples=800)

from keras.utils import plot_model
plot_model(model, to_file='d:/model.png')

3、resnet及其他方法融合

从知乎看到的一种方法，在这里介绍给大家，通过已训练好的imagenet权重对我们的数据进行特征提取，然后再用提取的特征做一个简单的全连接。代码如下：

from keras.models import *
from keras.layers import *
from keras.applications import *
from keras.preprocessing.image import *

import h5py

def write_gap(MODEL, image_size, lambda_func=None):
    width = image_size[0]
    height = image_size[1]
    input_tensor = Input((height, width, 3))
    x = input_tensor
    if lambda_func:
        x = Lambda(lambda_func)(x)

    base_model = MODEL(input_tensor=x, weights='imagenet', include_top=False)
    model = Model(base_model.input, GlobalAveragePooling2D()(base_model.output))

    gen = ImageDataGenerator()
    train_generator = gen.flow_from_directory("d:/train2", image_size, shuffle=False,
                                              batch_size=16)
    test_generator = gen.flow_from_directory("d:/test2", image_size, shuffle=False,
                                             batch_size=16, class_mode=None)

    train = model.predict_generator(train_generator, train_generator.nb_sample)
    test = model.predict_generator(test_generator, test_generator.nb_sample)
    with h5py.File("d:/mymodel/gap_%s.h5"%MODEL.func_name) as h:
        h.create_dataset("train", data=train)
        h.create_dataset("test", data=test)
        h.create_dataset("label", data=train_generator.classes)

write_gap(ResNet50, (224, 224))
write_gap(InceptionV3, (299, 299), inception_v3.preprocess_input)
write_gap(Xception, (299, 299), xception.preprocess_input)



import h5py
import numpy as np
from sklearn.utils import shuffle
np.random.seed(2017)

X_train = []
X_test = []

for filename in ["gap_ResNet50.h5", "gap_Xception.h5", "gap_InceptionV3.h5"]:
    with h5py.File(filename, 'r') as h:
        X_train.append(np.array(h['train']))
        X_test.append(np.array(h['test']))
        y_train = np.array(h['label'])

X_train = np.concatenate(X_train, axis=1)
X_test = np.concatenate(X_test, axis=1)

X_train, y_train = shuffle(X_train, y_train)





from keras.models import *
from keras.layers import *

np.random.seed(2017)

input_tensor = Input(X_train.shape[1:])
x = Dropout(0.5)(input_tensor)
x = Dense(1, activation='sigmoid')(x)
model = Model(input_tensor, x)

model.compile(optimizer='adadelta',
              loss='binary_crossentropy',
              metrics=['accuracy'])



model.fit(X_train, y_train, batch_size=128, nb_epoch=8, validation_split=0.2)

y_pred = model.predict(X_test, verbose=1)
y_pred = y_pred.clip(min=0.005, max=0.995)

import pandas as pd
from keras.preprocessing.image import *

df = pd.read_csv("sample_submission.csv")

gen = ImageDataGenerator()
test_generator = gen.flow_from_directory("test2", (224, 224), 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('pred.csv', index=None)
df.head(10)