Keras 猫狗二分类

import keras
from keras.models import Sequential
from keras.layers import Dense,MaxPooling2D,Input,Flatten,Convolution2D,Dropout,GlobalAveragePooling2D
from keras.optimizers import SGD
from keras.callbacks import TensorBoard,ModelCheckpoint
from PIL import Image
import os
import numpy  as np
from scipy import misc
root_path = os.getcwd()


def load_data():
    tran_imags = []
    labels = []
    seq_names = ['cat','dog']
    for seq_name in seq_names:
        frames = sorted(os.listdir(os.path.join(root_path,'data','train_data', seq_name)))
        for frame in frames:
            imgs = [os.path.join(root_path, 'data', 'train_data', seq_name, frame)]
            imgs = np.array(Image.open(imgs[0]))
            tran_imags.append(imgs)
            if seq_name=='cat':
                labels.append(0)
            else:
                labels.append(1)
    return np.array(tran_imags), np.array(labels)


def vgg_cat_dog(weights_path=None,has_fc=True):
    model = Sequential()
    model.add(Convolution2D(64,(3,3),activation='relu',padding='same',input_shape=(224,224,3)))
    model.add(Convolution2D(64,(3,3),activation='relu',padding='same'))
    model.add(MaxPooling2D((2,2),strides=(2,2)))

    model.add(Convolution2D(128,(3,3),activation='relu',padding='same'))
    model.add(Convolution2D(128,(3,3),activation='relu',padding='same'))
    model.add(MaxPooling2D((2,2),strides=(2,2)))

    model.add(Convolution2D(256,(3,3),activation='relu',padding='same'))
    model.add(Convolution2D(256,(3,3),activation='relu',padding='same'))
    model.add(Convolution2D(256,(3,3),activation='relu',padding='same'))
    model.add(MaxPooling2D((2,2),strides=(2,2)))

    model.add(Convolution2D(512,(3,3),activation='relu',padding='same'))
    model.add(Convolution2D(512,(3,3),activation='relu',padding='same'))
    model.add(Convolution2D(512,(3,3),activation='relu',padding='same'))
    model.add(MaxPooling2D((2,2),strides=(2,2)))

    model.add(Convolution2D(512,(3,3),activation='relu',padding='same'))
    model.add(Convolution2D(512,(3,3),activation='relu',padding='same'))
    model.add(Convolution2D(512,(3,3),activation='relu',padding='same'))
    model.add(MaxPooling2D((2,2),strides=(2,2)))


    if weights_path:
        model.load_weights(weights_path)
    if has_fc:
        model.add(Flatten())
        model.add(Dense(500,activation='relu'))
        model.add(Dropout(0.5))
        model.add(Dense(100,activation='relu'))
        model.add(Dropout(0.5))
        model.add(Dense(2,activation='softmax'))
    else:
        model.add(GlobalAveragePooling2D())
        model.add(Dense(2,activation='softmax'))
    return model


train_data,train_labs = load_data()
train = True
if train:
 model = vgg_cat_dog('model/vgg_16_without_fc.h5')
 sgd = SGD(lr=1e-6,momentum=0.9,decay=1e-6,nesterov=True)
 model.compile(optimizer=sgd,loss='categorical_crossentropy',metrics=['accuracy'])
 tensorboard = TensorBoard(log_dir='log/cat_dog',histogram_freq=10,write_images=True)
 ckpt = ModelCheckpoint(os.path.join(root_path,'model','cat_dog','vgg.h5'),verbose=1,period=5)
 model.fit(train_data,keras.utils.to_categorical(train_labs),batch_size=32,epochs=50,verbose=1,
          callbacks=[tensorboard,ckpt],validation_split=0.1,shuffle=True)
else:
 model = vgg_cat_dog()
 model.load_weights('model/cat_dog/vgg.h5')
 frames = sorted(os.listdir(os.path.join(root_path,'data','test', 'cat')))
 for frame in frames:
    imgs = [os.path.join(root_path, 'data', 'test', 'cat', frame)]
    im = np.expand_dims(np.array(misc.imresize(Image.open(imgs[0]), [224, 224])), axis=0)
    cal = np.argmax(model.predict(im))
    if cal:
        print('dog')
    else:
        print('cat')

使用在imagenet上的预训练好的前13层的权重进行fine-tune，训练集猫狗各420张左右，进行了50轮训练，效果还不错 ####记： 1. 开始未加dropout.   微调时，参数调的不多，第一次设置的学习率过大（0.1），损失居高不下一条直线，精度也是一条直线（0.1）。 第二次设置的1e-8，网络开始收敛，比较慢，最后选择1e-6,训练集精度达到95左右，验证集只有50左右的精度，过拟合。

1. 添加dropout层，参数不变，验证集精度飙升，由上图可见40轮左右基本稳定下来了，不得不感叹，dropout真是好啊。

附：keras下：1.vgg16带全连接层权重带全连接链接     2.vgg16不带全连接权重不带全连接