keras使用Sequence类调用大规模数据集进行训练的实现

class SequenceData(Sequence):
  def __init__(self, path, batch_size=32):
    self.path = path
    self.batch_size = batch_size
    f = open(path)
    self.datas = f.readlines()
    self.L = len(self.datas)
    self.index = random.sample(range(self.L), self.L)
  #返回长度，通过len(<你的实例 )调用
  def __len__(self):
    return self.L - self.batch_size
  #即通过索引获取a[0],a[1]这种
  def __getitem__(self, idx):
    batch_indexs = self.index[idx:(idx+self.batch_size)]
    batch_datas = [self.datas[k] for k in batch_indexs]
    img1s,img2s,audios,labels = self.data_generation(batch_datas)
    return ({'face1_input_1': img1s, 'face2_input_2': img2s, 'input_3':audios},{'activation_7':labels})

  def data_generation(self, batch_datas):
    #预处理操作
    return img1s,img2s,audios,labels

D = SequenceData('train.csv')
model_train.fit_generator(generator=D,steps_per_epoch=int(len(D)), 
          epochs=2, workers=20, #callbacks=[checkpoint],
          use_multiprocessing=True, validation_data=SequenceData('vali.csv'),validation_steps=int(20000/32)) 

#coding=utf-8
'''
Created on 2018-7-10
'''
import keras
import math
import os
import cv2
import numpy as np
from keras.models import Sequential
from keras.layers import Dense

class DataGenerator(keras.utils.Sequence):
  
  def __init__(self, datas, batch_size=1, shuffle=True):
    self.batch_size = batch_size
    self.datas = datas
    self.indexes = np.arange(len(self.datas))
    self.shuffle = shuffle

  def __len__(self):
    #计算每一个epoch的迭代次数
    return math.ceil(len(self.datas) / float(self.batch_size))

  def __getitem__(self, index):
    #生成每个batch数据，这里就根据自己对数据的读取方式进行发挥了
    # 生成batch_size个索引
    batch_indexs = self.indexes[index*self.batch_size:(index+1)*self.batch_size]
    # 根据索引获取datas集合中的数据
    batch_datas = [self.datas[k] for k in batch_indexs]

    # 生成数据
    X, y = self.data_generation(batch_datas)

    return X, y

  def on_epoch_end(self):
    #在每一次epoch结束是否需要进行一次随机，重新随机一下index
    if self.shuffle == True:
      np.random.shuffle(self.indexes)

  def data_generation(self, batch_datas):
    images = []
    labels = []

    # 生成数据
    for i, data in enumerate(batch_datas):
      #x_train数据
      image = cv2.imread(data)
      image = list(image)
      images.append(image)
      #y_train数据 
      right = data.rfind("\",0)
      left = data.rfind("\",0,right)+1
      class_name = data[left:right]
      if class_name=="dog":
        labels.append([0,1])
      else: 
        labels.append([1,0])
    #如果为多输出模型，Y的格式要变一下，外层list格式包裹numpy格式是list[numpy_out1,numpy_out2,numpy_out3]
    return np.array(images), np.array(labels)
  
# 读取样本名称，然后根据样本名称去读取数据
class_num = 0
train_datas = [] 
for file in os.listdir("D:/xxx"):
  file_path = os.path.join("D:/xxx", file)
  if os.path.isdir(file_path):
    class_num = class_num + 1
    for sub_file in os.listdir(file_path):
      train_datas.append(os.path.join(file_path, sub_file))

# 数据生成器
training_generator = DataGenerator(train_datas)

#构建网络
model = Sequential()
model.add(Dense(units=64, activation='relu', input_dim=784))
model.add(Dense(units=2, activation='softmax'))
model.compile(loss='categorical_crossentropy',
       optimizer='sgd',
       metrics=['accuracy'])
model.compile(optimizer='sgd', loss='categorical_crossentropy', metrics=['accuracy'])
model.fit_generator(training_generator, epochs=50,max_queue_size=10,workers=1)