完美解決keras 讀取多個hdf5文件進行訓練的問題

更新時間：2020年07月01日 14:43:07 作者：William_Yue91

這篇文章主要介紹了完美解決keras 讀取多個hdf5文件進行訓練的問題，具有很好的參考價值，希望對大家有所幫助。一起跟隨小編過來看看吧

用keras進行大數(shù)據(jù)訓練，為了加快訓練，需要提前制作訓練集。

由于HDF5的特性，所有數(shù)據(jù)需要一次性讀入到內(nèi)存中，才能保存。

為此，我采用分批次分為2個以上HDF5進行存儲。

1、先讀取每個標簽下的圖片，并設(shè)置標簽

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、該標簽下的數(shù)據(jù)集分割為訓練集（train images），驗證集（val images），訓練標簽（train labels），驗證標簽

（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、分割后的數(shù)據(jù)分別添加到總的訓練集，驗證集，訓練標簽，驗證標簽。

其次，清空原有的圖片集和標簽集，目的是節(jié)省內(nèi)存。假如一次性讀入多個標簽的數(shù)據(jù)集與標簽集，進行數(shù)據(jù)分割后，會占用大于單純進行上述操作兩倍以上的內(nèi)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、進行判斷，直到讀到自己自己分割的那個標簽。

開始進行寫入。寫入之前，為了更好地訓練模型，需要把對應(yīng)的圖片集和標簽打亂順序。

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)

對應(yīng)打亂順序并寫入到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、判斷文件全部讀入

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、訓練中，采用迭代器讀入數(shù)據(jù)

 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  
 # 默認是無限循環(huán)遍歷
 
 while epochs < passes:
  # 遍歷數(shù)據(jù)
  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編碼
   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編碼
   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

完整的代碼：

# -*- 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
 
# 加載數(shù)據(jù)集并按照交叉驗證的原則劃分數(shù)據(jù)集并進行相關(guān)預(yù)處理工作
def split_dataset(images, labels): 
 # 導入了sklearn庫的交叉驗證模塊，利用函數(shù)train_test_split()來劃分訓練集和驗證集
 # 劃分出了20%的數(shù)據(jù)用于驗證，80%用于訓練模型
 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"
 
 #采用標簽與圖片相同的順序分別打亂訓練集與驗證集
 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寫入
 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)

#循環(huán)讀取每個標簽集下的所有圖片
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) 

#讀取訓練數(shù)據(jù)集的文件夾，把他們的名字返回給一個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)

以上這篇完美解決keras 讀取多個hdf5文件進行訓練的問題就是小編分享給大家的全部內(nèi)容了，希望能給大家一個參考，也希望大家多多支持腳本之家。

您可能感興趣的文章: