伏龙阁资源网

完美解决keras 读取多个hdf5文件进行训练的问题
站长资源 2024/11/24 佚名
2 0

用keras进行大数据训练，为了加快训练，需要提前制作训练集。

由于HDF5的特性，所有数据需要一次性读入到内存中，才能保存。

为此，我采用分批次分为2个以上HDF5进行存储。

1、先读取每个标签下的图片，并设置标签

def load_dataset(path_name,data_path):
 images = []
 labels = []
 train_images = []
 valid_images = [] 
 train_labels = []
 valid_labels = []
 counter = 0
 allpath = os.listdir(path_name)
 nb_classes = len(allpath)
 print("label_num: ",nb_classes)
 
 for child_dir in allpath:
 child_path = os.path.join(path_name, child_dir)
 for dir_image in os.listdir(child_path):
  if dir_image.endswith('.jpg'):
  img = cv2.imread(os.path.join(child_path, dir_image))  
  image = misc.imresize(img, (IMAGE_SIZE, IMAGE_SIZE), interp='bilinear')
  #resized_img = cv2.resize(img, (IMAGE_SIZE, IMAGE_SIZE))
  images.append(image)
  labels.append(counter)

2、该标签下的数据集分割为训练集（train images），验证集（val images），训练标签（train labels），验证标签

（val labels）

def split_dataset(images, labels): 

 train_images, valid_images, train_labels, valid_labels = train_test_split(images, labels, test_size = 0.2, random_state = random.randint(0, 100)) 
  
 #print(train_images.shape[0], 'train samples')
 #print(valid_images.shape[0], 'valid samples') 
 return train_images, valid_images, train_labels ,valid_labels

3、分割后的数据分别添加到总的训练集，验证集，训练标签，验证标签。

其次，清空原有的图片集和标签集，目的是节省内存。假如一次性读入多个标签的数据集与标签集，进行数据分割后，会占用大于单纯进行上述操作两倍以上的内存。

images = np.array(images) 
t_images, v_images, t_labels ,v_labels = split_dataset(images, labels) 
for i in range(len(t_images)):
 train_images.append(t_images[i])
 train_labels.append(t_labels[i]) 
for j in range(len(v_images)):
 valid_images.append(v_images[j])
 valid_labels.append(v_labels[j])
if counter%50== 49:
 print( counter+1 , "is read to the memory!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!") 
 
images = []
labels = [] 
counter = counter + 1 

print("train_images num: ", len(train_images), " ", "valid_images num: ",len(valid_images))

4、进行判断，直到读到自己自己分割的那个标签。

开始进行写入。写入之前，为了更好地训练模型，需要把对应的图片集和标签打乱顺序。

if ((counter % 4316 == 4315) or (counter == nb_classes - 1)): 
  
  print("start write images and labels data...................................................................")  
  num = counter // 5000
  dirs = data_path + "/" + "h5_" + str(num - 1)
  if not os.path.exists(dirs):
  os.makedirs(dirs)
  data2h5(dirs, t_images, v_images, t_labels ,v_labels)

对应打乱顺序并写入到HDF5

def data2h5(dirs_path, train_images, valid_images, train_labels ,valid_labels):
 
 TRAIN_HDF5 = dirs_path + '/' + "train.hdf5"
 VAL_HDF5 = dirs_path + '/' + "val.hdf5"
 
 #shuffle
 state1 = np.random.get_state()
 np.random.shuffle(train_images)
 np.random.set_state(state1)
 np.random.shuffle(train_labels)
 
 state2 = np.random.get_state()
 np.random.shuffle(valid_images)
 np.random.set_state(state2)
 np.random.shuffle(valid_labels)
 
 datasets = [
 ("train",train_images,train_labels,TRAIN_HDF5),
 ("val",valid_images,valid_labels,VAL_HDF5)]
 
 for (dType,images,labels,outputPath) in datasets:
 # HDF5 initial
 f = h5py.File(outputPath, "w")
 f.create_dataset("x_"+dType, data=images)
 f.create_dataset("y_"+dType, data=labels)
 #f.create_dataset("x_"+dType, data=images, compression="gzip", compression_opts=9)
 #f.create_dataset("y_"+dType, data=labels, compression="gzip", compression_opts=9)
 f.close()

5、判断文件全部读入

def read_dataset(dirs):
 
 files = os.listdir(dirs)
 print(files)
 for file in files:
 path = dirs+'/' + file
 dataset = h5py.File(path, "r")
 file = file.split('.')
 set_x_orig = dataset["x_"+file[0]].shape[0]
 set_y_orig = dataset["y_"+file[0]].shape[0]

 print(set_x_orig)
 print(set_y_orig)

6、训练中，采用迭代器读入数据

 def generator(self, datagen, mode):
 
 passes=np.inf
 aug = ImageDataGenerator(
  featurewise_center = False,  
  samplewise_center = False,  
  featurewise_std_normalization = False, 
  samplewise_std_normalization = False, 
  zca_whitening = False,   
  rotation_range = 20,   
  width_shift_range = 0.2,  
  height_shift_range = 0.2,  
  horizontal_flip = True,  
  vertical_flip = False)  
 
 epochs = 0  
 # 默认是无限循环遍历
 
 while epochs < passes:
  # 遍历数据
  file_dir = os.listdir(self.data_path)
  for file in file_dir:
  #print(file)
  file_path = os.path.join(self.data_path,file)
  TRAIN_HDF5 = file_path +"/train.hdf5"
  VAL_HDF5 = file_path +"/val.hdf5"
  #TEST_HDF5 = file_path +"/test.hdf5"
  
  db_t = h5py.File(TRAIN_HDF5)
  numImages_t = db_t['y_train'].shape[0] 
  db_v = h5py.File(VAL_HDF5)
  numImages_v = db_v['y_val'].shape[0] 
  
  if mode == "train":  
   for i in np.arange(0, numImages_t, self.BS):
   
   images = db_t['x_train'][i: i+self.BS]
   labels = db_t['y_train'][i: i+self.BS]
   
   if K.image_data_format() == 'channels_first':
   
    images = images.reshape(images.shape[0], 3, IMAGE_SIZE,IMAGE_SIZE) 
   else:
    images = images.reshape(images.shape[0], IMAGE_SIZE, IMAGE_SIZE, 3) 
   
   images = images.astype('float32')
   images = images/255   
      
   if datagen :
    (images,labels) = next(aug.flow(images,labels,batch_size = self.BS))   
      
   # one-hot编码
   if self.binarize:
    labels = np_utils.to_categorical(labels,self.classes)   
   
   yield ({'input_1': images}, {'softmax': labels})
    
  elif mode == "val":
   for i in np.arange(0, numImages_v, self.BS):
   images = db_v['x_val'][i: i+self.BS]
   labels = db_v['y_val'][i: i+self.BS] 
   
   if K.image_data_format() == 'channels_first':
   
    images = images.reshape(images.shape[0], 3, IMAGE_SIZE,IMAGE_SIZE) 
   else:
    images = images.reshape(images.shape[0], IMAGE_SIZE, IMAGE_SIZE, 3) 
   
   images = images.astype('float32')
   images = images/255   
   
   if datagen :
    (images,labels) = next(aug.flow(images,labels,batch_size = self.BS))   

   #one-hot编码
   if self.binarize:
    labels = np_utils.to_categorical(labels,self.classes) 
    
   yield ({'input_1': images}, {'softmax': labels})
     
  epochs += 1

7、至此，就大功告成了

完整的代码：

# -*- coding: utf-8 -*-
"""
Created on Mon Feb 12 20:46:12 2018

@author: william_yue
"""
import os
import numpy as np
import cv2
import random
from scipy import misc
import h5py
from sklearn.model_selection import train_test_split
from keras import backend as K
K.clear_session()
from keras.utils import np_utils

IMAGE_SIZE = 128
 
# 加载数据集并按照交叉验证的原则划分数据集并进行相关预处理工作
def split_dataset(images, labels): 
 # 导入了sklearn库的交叉验证模块，利用函数train_test_split()来划分训练集和验证集
 # 划分出了20%的数据用于验证，80%用于训练模型
 train_images, valid_images, train_labels, valid_labels = train_test_split(images, labels, test_size = 0.2, random_state = random.randint(0, 100)) 
 return train_images, valid_images, train_labels ,valid_labels
 
def data2h5(dirs_path, train_images, valid_images, train_labels ,valid_labels):
 
#def data2h5(dirs_path, train_images, valid_images, test_images, train_labels ,valid_labels, test_labels):
 
 TRAIN_HDF5 = dirs_path + '/' + "train.hdf5"
 VAL_HDF5 = dirs_path + '/' + "val.hdf5"
 
 #采用标签与图片相同的顺序分别打乱训练集与验证集
 state1 = np.random.get_state()
 np.random.shuffle(train_images)
 np.random.set_state(state1)
 np.random.shuffle(train_labels)
 
 state2 = np.random.get_state()
 np.random.shuffle(valid_images)
 np.random.set_state(state2)
 np.random.shuffle(valid_labels)
 
 datasets = [
 ("train",train_images,train_labels,TRAIN_HDF5),
 ("val",valid_images,valid_labels,VAL_HDF5)]
 
 for (dType,images,labels,outputPath) in datasets:
 # 初始化HDF5写入
 f = h5py.File(outputPath, "w")
 f.create_dataset("x_"+dType, data=images)
 f.create_dataset("y_"+dType, data=labels)
 #f.create_dataset("x_"+dType, data=images, compression="gzip", compression_opts=9)
 #f.create_dataset("y_"+dType, data=labels, compression="gzip", compression_opts=9)
 f.close()

def read_dataset(dirs):
 files = os.listdir(dirs)
 print(files)
 for file in files:
 path = dirs+'/' + file 
 file_read = os.listdir(path)
 for i in file_read:
  path_read = os.path.join(path, i)
  dataset = h5py.File(path_read, "r")
  i = i.split('.')
  set_x_orig = dataset["x_"+i[0]].shape[0]
  set_y_orig = dataset["y_"+i[0]].shape[0]
  print(set_x_orig)
  print(set_y_orig)

#循环读取每个标签集下的所有图片
def load_dataset(path_name,data_path):
 images = []
 labels = []
 train_images = []
 valid_images = []
 train_labels = []
 valid_labels = []
 counter = 0
 allpath = os.listdir(path_name)
 nb_classes = len(allpath)
 print("label_num: ",nb_classes)
 
 for child_dir in allpath:
 child_path = os.path.join(path_name, child_dir)
 for dir_image in os.listdir(child_path):
  if dir_image.endswith('.jpg'):
  img = cv2.imread(os.path.join(child_path, dir_image))  
  image = misc.imresize(img, (IMAGE_SIZE, IMAGE_SIZE), interp='bilinear')
  #resized_img = cv2.resize(img, (IMAGE_SIZE, IMAGE_SIZE))
  images.append(image)
  labels.append(counter)
   
 images = np.array(images) 
 t_images, v_images, t_labels ,v_labels = split_dataset(images, labels) 
 for i in range(len(t_images)):
  train_images.append(t_images[i])
  train_labels.append(t_labels[i]) 
 for j in range(len(v_images)):
  valid_images.append(v_images[j])
  valid_labels.append(v_labels[j])
 if counter%50== 49:
  print( counter+1 , "is read to the memory!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!") 
  
 images = []
 labels = [] 
 
 if ((counter % 4316 == 4315) or (counter == nb_classes - 1)): 
  print("train_images num: ", len(train_images), "  ", "valid_images num: ",len(valid_images)) 
  print("start write images and labels data...................................................................")  
  num = counter // 5000
  dirs = data_path + "/" + "h5_" + str(num - 1)
  if not os.path.exists(dirs):
  os.makedirs(dirs)
  data2h5(dirs, train_images, valid_images, train_labels ,valid_labels)
  #read_dataset(dirs)
  print("File HDF5_%d "%num, " id done!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!") 
  train_images = []
  valid_images = []
  train_labels = []
  valid_labels = [] 
 counter = counter + 1 
 print("All File HDF5 done!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!") 
 read_dataset(data_path) 

#读取训练数据集的文件夹，把他们的名字返回给一个list
def read_name_list(path_name):
 name_list = []
 for child_dir in os.listdir(path_name):
 name_list.append(child_dir)
 return name_list

if __name__ == '__main__':
 path = "data"
 data_path = "data_hdf5_half"
 if not os.path.exists(data_path):
 os.makedirs(data_path)
 load_dataset(path,data_path)

以上这篇完美解决keras 读取多个hdf5文件进行训练的问题就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持。

广告合作：本站广告合作请联系QQ：858582 申请时备注：广告合作（否则不回）
免责声明：本站资源来自互联网收集,仅供用于学习和交流,请遵循相关法律法规,本站一切资源不代表本站立场,如有侵权、后门、不妥请联系本站删除！
www.wwsws.com 伏龙阁资源网
39,976影音资源
44,792技术资源
21,817软件资源
651,128站长资源

《魔兽世界》大逃杀！60人新游玩模式《强袭风暴》3月21日上线

暴雪近日发布了《魔兽世界》10.2.6 更新内容，新游玩模式《强袭风暴》即将于3月21 日在亚服上线，届时玩家将前往阿拉希高地展开一场 60 人大逃杀对战。

艾泽拉斯的冒险者已经征服了艾泽拉斯的大地及遥远的彼岸。他们在对抗世界上最致命的敌人时展现出过人的手腕，并且成功阻止终结宇宙等级的威胁。当他们在为即将于《魔兽世界》资料片《地心之战》中来袭的萨拉塔斯势力做战斗准备时，他们还需要在熟悉的阿拉希高地面对一个全新的敌人──那就是彼此。在《巨龙崛起》10.2.6 更新的《强袭风暴》中，玩家将会进入一个全新的海盗主题大逃杀式限时活动，其中包含极高的风险和史诗级的奖励。

《强袭风暴》不是普通的战场，作为一个独立于主游戏之外的活动，玩家可以用大逃杀的风格来体验《魔兽世界》，不分职业、不分装备（除了你在赛局中捡到的），光是技巧和战略的强弱之分就能决定出谁才是能坚持到最后的赢家。本次活动将会开放单人和双人模式，玩家在加入海盗主题的预赛大厅区域前，可以从强袭风暴角色画面新增好友。游玩游戏将可以累计名望轨迹，《巨龙崛起》和《魔兽世界：巫妖王之怒 经典版》的玩家都可以获得奖励。

更新日志

友情链接

杰晶网络 DDR爱好者之家 桃源资源网 杰网资源 富贵资源网 南强小屋 铁雪资源网 幽灵资源网 万梅资源网 狼山资源网 白云岛资源网 昆仑资源网 相思资源网 明霞山资源网 内蒙古资源网 黑松山资源网 茶园资源网 饿虎岗资源网 大旗谷资源网 常春岛资源网 岱庙资源网 兴国资源网 快活林资源网 蝙蝠岛资源网 帝王谷资源网 白云城资源网 伏龙阁资源网 清风细雨楼 天枫庄资源网 圆月山庄资源网 无争山庄资源网 神水资源网 移花宫资源网 神剑山庄资源网 无为清净楼资源网 金钱帮资源网 丐帮资源网 华山资源网 极乐门资源网 小李飞刀资源网 凤求凰客栈 风云阁资源网 金狮镖局 鸳鸯亭资源网 千金楼资源网 更多链接