使用vgg16模型進行圖片預測

使用vgg16模型進行圖片預測 #

前面我們學習了使用cifra10來判斷圖片的類別，今天我們使用更加強大的已經訓練好的模型來預測圖片的類別，那就是vgg16,對應的供keras使用的模型人家已經幫我們訓練好，我可不想賣腎來買一個gpu。。。
對應的模型在 ‘vgg16’ 可以下載。估計被牆了，附上鍊接(http://pan.baidu.com/s/1qX0CJSC)
附上我的github(https://github.com/HadXu/machine-learning)

導入必要的庫

from keras.models import Sequential
from keras.layers.core import Flatten, Dense, Dropout
from keras.layers.convolutional import Convolution2D, MaxPooling2D, ZeroPadding2D
from keras.optimizers import SGD
import cv2, numpy as np

Using Theano backend.
D:\Anaconda\lib\site-packages\theano-0.8.0.dev0-py2.7.egg\theano\tensor\signal\downsample.py:5: UserWarning: downsample module has been moved to the pool module.
  warnings.warn("downsample module has been moved to the pool module.")

使用keras建立vgg16模型

def VGG_16(weights_path=None):
    model = Sequential()
    model.add(ZeroPadding2D((1,1),input_shape=(3,224,224)))
    model.add(Convolution2D(64, 3, 3, activation='relu'))
    model.add(ZeroPadding2D((1,1)))
    model.add(Convolution2D(64, 3, 3, activation='relu'))
    model.add(MaxPooling2D((2,2), strides=(2,2)))

    model.add(ZeroPadding2D((1,1)))
    model.add(Convolution2D(128, 3, 3, activation='relu'))
    model.add(ZeroPadding2D((1,1)))
    model.add(Convolution2D(128, 3, 3, activation='relu'))
    model.add(MaxPooling2D((2,2), strides=(2,2)))

    model.add(ZeroPadding2D((1,1)))
    model.add(Convolution2D(256, 3, 3, activation='relu'))
    model.add(ZeroPadding2D((1,1)))
    model.add(Convolution2D(256, 3, 3, activation='relu'))
    model.add(ZeroPadding2D((1,1)))
    model.add(Convolution2D(256, 3, 3, activation='relu'))
    model.add(MaxPooling2D((2,2), strides=(2,2)))

    model.add(ZeroPadding2D((1,1)))
    model.add(Convolution2D(512, 3, 3, activation='relu'))
    model.add(ZeroPadding2D((1,1)))
    model.add(Convolution2D(512, 3, 3, activation='relu'))
    model.add(ZeroPadding2D((1,1)))
    model.add(Convolution2D(512, 3, 3, activation='relu'))
    model.add(MaxPooling2D((2,2), strides=(2,2)))

    model.add(ZeroPadding2D((1,1)))
    model.add(Convolution2D(512, 3, 3, activation='relu'))
    model.add(ZeroPadding2D((1,1)))
    model.add(Convolution2D(512, 3, 3, activation='relu'))
    model.add(ZeroPadding2D((1,1)))
    model.add(Convolution2D(512, 3, 3, activation='relu'))
    model.add(MaxPooling2D((2,2), strides=(2,2)))

    model.add(Flatten())
    model.add(Dense(4096, activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(4096, activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(1000, activation='softmax'))

    if weights_path:
        model.load_weights(weights_path)

    return model

model = VGG_16('vgg16_weights.h5')

sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(optimizer=sgd, loss='categorical_crossentropy')

現在我們開始來預測了

首先寫一個方法來加載並處理圖片

def load_image(imageurl):
    im = cv2.resize(cv2.imread(imageurl),(224,224)).astype(np.float32)
    im[:,:,0] -= 103.939
    im[:,:,1] -= 116.779
    im[:,:,2] -= 123.68
    im = im.transpose((2,0,1))
    im = np.expand_dims(im,axis=0)
    return im

讀取vgg16的類別文件

f = open('synset_words.txt','r')
lines = f.readlines()
f.close()

def predict(url):
    im = load_image(url)
    pre = np.argmax(model.predict(im))
    print lines[pre]

%pylab inline

Populating the interactive namespace from numpy and matplotlib

from IPython.display import Image

Image('cat1.jpg')

開始預測

predict('cat1.jpg')

n02123045 tabby, tabby cat

Image('zebra.jpg')

predict('zebra.jpg')

n02391049 zebra

Image('airplane.jpg')

predict('airplane.jpg')

n02690373 airliner

Image('pig.jpg')

predict('pig.jpg')

n02395406 hog, pig, grunter, squealer, Sus scrofa

可見，判斷率還是很高的。。。。

總結

通過這次學習，學會了使用keras來搭建模型，使用vgg16這個模型。