繼上篇對于Keras的初步探討之后，我將給出一個(gè)例子講解如何利用Keras用于處理圖像分類問題居兆，今天我們先探討一下識(shí)別驗(yàn)證碼的問題覆山。

一、探討內(nèi)容

1泥栖、數(shù)據(jù)來源

2簇宽、模型搭建

3勋篓、優(yōu)化問題

二、數(shù)據(jù)來源

在本文中魏割，我打算對驗(yàn)證碼進(jìn)行識(shí)別譬嚣，有一個(gè)python包——captcha，利用它可生成驗(yàn)證碼钞它。當(dāng)然使用前需要

先導(dǎo)入相關(guān)packages拜银。
```import cv2
import numpy as np
from captcha.image import ImageCaptcha

這里可以設(shè)置驗(yàn)證碼的大小為28*28，字體大小24须揣。比如下面兩張圖片盐股，第一張是5钱豁，第二張是6耻卡。干擾相對較大。

image1_5.jpg

image2_6.jpg

下面給出完整代碼

import cv2
import numpy as np
from captcha.image import ImageCaptcha

def generate_captcha(text):
    
    capt= ImageCaptcha(width=28,height=28,font_sizes = [24])
    image = capt.generate_image(text)
    image = np.array(image,dtype=np.uint8)
    return image

if __name__ == '__main__':
    output_dir = './datasets/images/'
    for i in range(5000):
        label = np.random.randint(0,10)
        image = generate_captcha(str(label))
        image_name = 'image{}_{}.jpg'.format(i+1,label)
        output_path = output_dir +image_name
        cv2.imwrite(output_path,image)

保存文件為gendata.py牲尺，運(yùn)行文件后生成5000張驗(yàn)證碼圖片卵酪。這里只是實(shí)驗(yàn)性質(zhì)，所以驗(yàn)證碼圖片數(shù)量較少谤碳，大家自己做實(shí)驗(yàn)的時(shí)候可以適當(dāng)增加一些圖片數(shù)量溃卡。

三、模型搭建

一開始我們可以搭建一個(gè)非常簡單的LeNet來進(jìn)行驗(yàn)證和測試蜒简。保存下列文件命名為lenet.py

# import the necessary packages
from keras.models import Sequential
from keras.layers.convolutional import Conv2D
from keras.layers.convolutional import MaxPooling2D
from keras.layers.core import Activation
from keras.layers.core import Flatten
from keras.layers.core import Dense
from keras import backend as K
 
class LeNet:
    @staticmethod
    def build(width, height, depth, classes):
        # initialize the model
        model = Sequential()
        inputShape = (height, width, depth)
        # if we are using "channels last", update the input shape
        if K.image_data_format() == "channels_first":   #for tensorflow
            inputShape = (depth, height, width)
        # first set of CONV => RELU => POOL layers
        model.add(Conv2D(20, (5, 5),padding="same",input_shape=inputShape))
        model.add(Activation("relu"))
        model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
        #second set of CONV => RELU => POOL layers
        model.add(Conv2D(50, (5, 5), padding="same"))
        model.add(Activation("relu"))
        model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
        # first (and only) set of FC => RELU layers
        model.add(Flatten())
        model.add(Dense(500))
        model.add(Activation("relu"))

        # softmax classifier
        model.add(Dense(classes))
        model.add(Activation("softmax"))

        # return the constructed network architecture
        return model

接著我們加載數(shù)據(jù)瘸羡，每張圖片對應(yīng)的數(shù)字是放在文件名'_'之后。

def get_data(images_path):
    if not os.path.exists(images_path):
        raise ValueError('images_path is not exist.')

    images = []
    labels = []
    images_path = os.path.join(images_path,'*.jpg')
    count = 0
    for image_file in glob.glob(images_path):
        count +=1
        if count % 100 == 0:
            print('Load{} images .'.format(count))
        image = cv2.imread(image_file)
        image = cv2.cvtColor(image,cv2.COLOR_BGR2RGB)
        image = cv2.resize(image, (norm_size, norm_size))
        label = int(image_file.split('_')[-1].split('.')[0])
        images.append(image)
        labels.append(label)
    images = np.array(images)
    labels = np.array(labels)

    (trainX, testX, trainY, testY) = train_test_split(images,
            labels, test_size=0.25, random_state=42)

    # convert the labels from integers to vectors
    trainY = to_categorical(trainY, num_classes=CLASS_NUM)
    testY = to_categorical(testY, num_classes=CLASS_NUM)   
    return trainX,trainY,testX,testY

經(jīng)過處理我們得到訓(xùn)練集和測試集搓茬。我們先放出來完整代碼train.py犹赖，然后我們在代碼基礎(chǔ)上加以修改。運(yùn)行命令如下

python3 train.py -d images/ -m my.model

其中images/ 為驗(yàn)證碼存放目錄卷仑，my.model為模型保存位置峻村。

import matplotlib
matplotlib.use("Agg")
 
# import the necessary packages
import glob
from keras.preprocessing.image import ImageDataGenerator
from keras.optimizers import Adam
from sklearn.model_selection import train_test_split
from keras.preprocessing.image import img_to_array
from keras.utils import to_categorical
#from imutils import paths
import matplotlib.pyplot as plt
import numpy as np
import argparse
import random
import cv2
import os
import sys
sys.path.append('..')
from lenet import LeNet



def args_parse():
    # construct the argument parse and parse the arguments
    ap = argparse.ArgumentParser()
    ap.add_argument("-d", "--dataset", required=True,
        help="path to input dataset")
    ap.add_argument("-m", "--model", required=True,
        help="path to output model")
    ap.add_argument("-p", "--plot", type=str, default="plot.png",
        help="path to output accuracy/loss plot")
    args = vars(ap.parse_args()) 
    return args


args = args_parse()

# initialize the number of epochs to train for, initial learning rate,
# and batch size
EPOCHS = 200
INIT_LR = 1e-2
BS = 128
CLASS_NUM = 10
norm_size = 32
# initialize the data and labels

def get_data(images_path):
    if not os.path.exists(images_path):
        raise ValueError('images_path is not exist.')

    images = []
    labels = []
    images_path = os.path.join(images_path,'*.jpg')
    count = 0
    for image_file in glob.glob(images_path):
        count +=1
        if count % 100 == 0:
            print('Load{} images .'.format(count))
        image = cv2.imread(image_file)
        image = cv2.cvtColor(image,cv2.COLOR_BGR2RGB)
        image = cv2.resize(image, (norm_size, norm_size))
        label = int(image_file.split('_')[-1].split('.')[0])
        images.append(image)
        labels.append(label)
    images = np.array(images)
    labels = np.array(labels)

    (trainX, testX, trainY, testY) = train_test_split(images,
            labels, test_size=0.25, random_state=42)

    # convert the labels from integers to vectors
    trainY = to_categorical(trainY, num_classes=CLASS_NUM)
    testY = to_categorical(testY, num_classes=CLASS_NUM)   
    return trainX,trainY,testX,testY

def train(aug,trainX,trainY,testX,testY,args):
    # initialize the model
    print("[INFO] compiling model...")
    model = LeNet.build(width=norm_size, height=norm_size, depth=3, classes=CLASS_NUM)
    opt = Adam(lr=INIT_LR, decay=INIT_LR / EPOCHS)
#    opt = Adam(lr=INIT_LR)
    model.compile(loss="categorical_crossentropy", optimizer=opt,
        metrics=["accuracy"])

    # train the network
    print("[INFO] training network...")
    H = model.fit_generator(aug.flow(trainX, trainY, batch_size=BS),
        validation_data=(testX, testY), steps_per_epoch=len(trainX) // BS,
        epochs=EPOCHS, verbose=1)

    # save the model to disk
    print("[INFO] serializing network...")
    model.save(args["model"])
    
    # plot the training loss and accuracy
    plt.style.use("ggplot")
    plt.figure()
    N = EPOCHS
    plt.plot(np.arange(0, N), H.history["loss"], label="train_loss")
    plt.plot(np.arange(0, N), H.history["val_loss"], label="val_loss")
    plt.plot(np.arange(0, N), H.history["acc"], label="train_acc")
    plt.plot(np.arange(0, N), H.history["val_acc"], label="val_acc")
    plt.title("Training Loss and Accuracy on Invoice classifier")
    plt.xlabel("Epoch #")
    plt.ylabel("Loss/Accuracy")
    plt.legend(loc="lower left")
    plt.savefig(args["plot"])
    
#python train.py --dataset ../../invoice_all/train  --model invoice.model
if __name__=='__main__':
    args = args_parse()
    file_path = args["dataset"]
    trainX,trainY,testX,testY = get_data(file_path)
    # construct the image generator for data augmentation
    aug = ImageDataGenerator(rotation_range=30, width_shift_range=0.1,
        height_shift_range=0.1, shear_range=0.2, zoom_range=0.2,
        horizontal_flip=True, fill_mode="nearest")
    train(aug,trainX,trainY,testX,testY,args)

四、優(yōu)化模型

plot.png

4.1 采用BatchNormalization

BatchNormalization()真是非常好用锚扎，把它放在卷積層和池化層之間能非常有效地提升性能吞瞪。

model.add(Conv2D(30, (2, 2), padding="same"))
        model.add(BatchNormalization())
        model.add(Activation("relu"))
        model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))

4.2 學(xué)習(xí)率衰減策略

其實(shí)我們在一開始嘗試的時(shí)候完全沒必要設(shè)置學(xué)習(xí)率衰減策略。我們大可以嘗試使用或大或小的學(xué)習(xí)率觀察結(jié)果工秩。隨后我們可以讓學(xué)習(xí)率隨輪數(shù)衰減尸饺，以達(dá)到微調(diào)的效果进统。

    opt = Adam(lr=INIT_LR, decay=INIT_LR / EPOCHS)
#    opt = Adam(lr=INIT_LR)
    model.compile(loss="categorical_crossentropy", optimizer=opt,
        metrics=["accuracy"])

4.3 dropout

使用了batchnormal再使用dropout效果可能不太明顯。我們可以在最后的全連接層處使用dropout浪听，在卷積層中間使用dropout會(huì)導(dǎo)致結(jié)果不可預(yù)測螟碎。

        model.add(Dense(200))
        model.add(Dropout(droprate))

4.4 數(shù)據(jù)擴(kuò)充

我們把圖片變形扭曲增加數(shù)據(jù)源

aug = ImageDataGenerator(rotation_range=30, width_shift_range=0.1,
        height_shift_range=0.1, shear_range=0.2, zoom_range=0.2,
        horizontal_flip=True, fill_mode="nearest")

現(xiàn)在的結(jié)果如下圖所示，由于訓(xùn)練輪數(shù)（200）不是特別多迹栓，所以效果還不是很好正確率大概在85%掉分。有興趣的朋友可以在此基礎(chǔ)上加以修改一下。

plot.png