我爱编程pytorch学习

图片转换成HDF5文件(加载,保存)

2018-04-15  本文已影响1191人  听风1996

翻译http://machinelearninguru.com/deep_learning/data_preparation/hdf5/hdf5.html
当我们谈论深度学习时,通常首先想到的是大量数据或大量图像(例如ImageNet中数百万幅图像)。在这种情况下,从硬盘单独加载每个图像并应用图像预处理,然后将其传递到网络进行训练,验证或测试,这并不是非常明智和高效。尽管应用预处理需要时间,但从硬盘读取多个图像要花费更多的时间,而不是将它们全部放在单个文件中,并将它们作为单个数据组读取。我们希望有不同的数据模型和库,如HDF5和TFRecord。希望我们有不同的数据模型和库,如HDF5和TFRecord。在这篇文章中,我们将学习如何将大量图像保存在单个HDF5文件中,然后以批处理方式从文件中加载它们。数据的大小并不重要,或者它大于或小于内存大小。HDF5提供了管理,操作,查看,压缩和保存数据的工具。我们将关注相同的主题,但在我们的使用TFRecord 下一篇文章

在这篇文章中,我们加载,调整大小并将所有图像保存在着名的Dogs vs. Cats 数据集的train文件夹中 。按照这篇文章的其余部分,你需要下载Dogs vs. Cats数据集的训练部分。

列出图像及其标签

首先,我们需要列出所有图像并标注它们。我们给每个猫图像一个标签= 0,每个狗图像一个标签= 1.下面的代码列出所有图像,给它们适当的标签,然后洗牌数据。我们还将数据集分为三列(%60),验证(%20)和测试部分(%20)。

列出图像并标记它们
from random import shuffle
import glob

shuffle_data = True
# shuffle the addresses before saving

hdf5_path ='Cat vs Dog/dataset.hdf5' # address to where you want to save the hdf5 file
cat_dog_train_path ='Cat vs Dog/train/*.jpg'


#read addresses and labels from the 'train' folder
addrs = glob.glob(cat_dog_train_path)
labels =[0 if 'cat' in addr else 1 for addr in addrs] # 0 = Cat, 1 = Dog


#to shuffle data
if shuffle_data:
    c =list(zip(addrs,labels))
    shuffle(c)
    addrs, labels =zip(*c)

#Divide the hata into 60% train, 20% validation, and 20% test
train_addrs = addrs[0:int(0.6*len(addrs))]
train_labels = labels[0:int(0.6*len(labels))]

val_addrs = addrs[int(0.6*len(addrs)):int(0.8*len(addrs))]
val_labels = labels[int(0.6*len(addrs)):int(0.8*len(addrs))]

test_addrs = addrs[int(0.8*len(addrs)):]
test_labels = labels[int(0.8*len(labels)):]

创建一个HDF5文件

有两个主要的库让你使用HDF5格式,即 h5py 和 tables(PyTables)。我们将在下面解释如何与他们一起工作。第一步是创建一个HDF5文件。为了存储图像,我们应该为每一个训练集,验证集和测试集定义一个数组并按照 Tensorflow older(number of data, image_height, image_width, image_depth)或按照Theano older (number of data, image_height, image_width, image_depth)。对于标签,我们还需要一个数组,用于每个训练,验证和测试集,大小为 (number of data)。最后,我们计算训练集组的像素平均值,并将其保存为(1,image_height,image_width,image_depth)大小的数组 。请注意,当您想为其创建数组时,您总是应该确定数据的类型(dtype)。

使用tables案例
import numpy as np
import tables

data_order ='tf'
# 'th' for Theano,'tf' for Tensorflow
img_dtype = tables.UInt8Atom() # dtype in which the images will be saved


#check the order of data and chose proper data shape to save images
if data_order == 'th':
    data_shape =(0,3,224,224)
elif data_order == 'tf':
    data_shape =(0,224,224,3)

#open a hdf5 file and create earrays
hdf5_file = tables.open_file(hdf5_path,mode='w')

train_storage = hdf5_file.create_earray(hdf5_file.root,'train_img',
 img_dtype, shape=data_shape)
val_storage = hdf5_file.create_earray(hdf5_file.root,'val_img',
 img_dtype, shape=data_shape)
test_storage = hdf5_file.create_earray(hdf5_file.root,'test_img',
 img_dtype, shape=data_shape)


mean_storage = hdf5_file.create_earray(hdf5_file.root,'train_mean',
 img_dtype, shape=data_shape)


#create the label arrays and copy the labels data in them

hdf5_file.create_array(hdf5_file.root,'train_labels',train_labels)
hdf5_file.create_array(hdf5_file.root,'val_labels',val_labels)
hdf5_file.create_array(hdf5_file.root,'test_labels',test_labels)

现在,是时候逐一读取图像,应用预处理(只调整我们的代码)然后保存。

# a numpy array to save the mean of the images

mean = np.zeros(data_shape[1:],np.float32)
#loop over train addresses

for i in range(len(train_addrs)):

# print how many images are saved every 1000 images

if i % 1000 == 0 and i > 1:

print'Train data: {}/{}'.format(i,len(train_addrs))


#read an image and resize to (224, 224)

#cv2 load images as BGR, convert it to RGB

addr = train_addrs[i]
img = cv2.imread(addr)
img = cv2.resize(img,(224,224),interpolation=cv2.INTER_CUBIC)

img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)


# add any image pre-processing here


#if the data order is Theano, axis orders should change
if data_order == 'th':
img = np.rollaxis(img,2)


#save the image and calculate the mean so far

train_storage.append(img[None])
mean += img /float(len(train_labels))

#loop over validation addresses
for i in range(len(val_addrs)): 
    #print how many images are saved every 1000 images
    if i % 1000 == 0 and i> 1:
        print'Validation data: {}/{}'.format(i,len(val_addrs))


#read an image and resize to (224, 224)

#cv2 load images as BGR, convert it to RGB

addr = val_addrs[i]
img = cv2.imread(addr)
img = cv2.resize(img,(224,224),interpolation=cv2.INTER_CUBIC)
img = cv2.cvtColor(img,cv2.COLOR_BGR2RGB)


#add any image pre-processing here

# if the data order is Theano, axis orders should change

if data_order == 'th':
    img = np.rollaxis(img,2)

#save the image
val_storage.append(img[None])

#loop over test addresses

for i in range(len(test_addrs)):

#print how many images are saved every 1000 images

if i % 1000 == 0 and i> 1:
print'Test data: {}/{}'.format(i,len(test_addrs))


#read an image and resize to (224, 224)
#cv2 load images as BGR, convert it to RGB

addr = test_addrs[i]
img = cv2.imread(addr)
img = cv2.resize(img,(224,224),interpolation=cv2.INTER_CUBIC)
img = cv2.cvtColor(img,cv2.COLOR_BGR2RGB)

#add any image pre-processing here
#if the data order is Theano, axis orders should change

if data_order == 'th':
    img = np.rollaxis(img,2)

#save the image
test_storage.append(img[None])
#save the mean and close the hdf5 file
mean_storage.append(mean[None])
hdf5_file.close()

阅读HDF5文件

是时候检查数据是否正确保存在HDF5文件中。为此,我们以任意大小的批次加载数据并绘制前5批次的第一张图片。我们也检查每张图片的标签。我们定义了一个变量 subtract_mean,它指示我们是否想在显示图像之前减去训练集的平均值。在 表中 ,我们访问每个阵列调用其名称其数据组之后(这样 hdf5_file。组。arrayName中)。您可以将它索引为一个numpy数组。然而,在 h5py中, 我们使用它的名字像字典名称(hdf5_file [ “arrayname” “ ]]来访问数组)。无论哪种情况,您都可以访问数组的形状 。形状 像一个numpy阵列。

import tables
import numpy as np

hdf5_path ='Cat vs Dog/dataset.hdf5'
subtract_mean =False

#open the hdf5 file
hdf5_file = tables.open_file(hdf5_path,mode='r')

#subtract the training mean
if subtract_mean:
    mm = hdf5_file.root.train_mean[0]
    mm = mm[np.newaxis,...]

#Total number of samples
data_num = hdf5_file.root.train_img.shape[0]

现在我们创建一个批量的列表并对其进行洗牌。现在,我们遍历批次并一次读取每批中的所有图像。

from random import shuffle
from math import ceil
import matplotlib.pyplot as plt

#create list of batches to shuffle the data

batches_list =list(range(int(ceil(float(data_num)/batch_size))))

shuffle(batches_list)

#loop over batches

for n, i in enumerate(batches_list):

i_s = i * batch_size
# index of the first image in this batch

i_e =min([(i+ 1)* batch_size, data_num])
# index of the last image in this batch


#read batch images and remove training mean

images = hdf5_file.root.train_img[i_s:i_e]
if subtract_mean:
    images -= mm


#read labels and convert to one hot encoding

labels = hdf5_file.root.train_labels[i_s:i_e]
labels_one_hot = np.zeros((batch_size,nb_class))

labels_one_hot[np.arange(batch_size),labels]= 1


print n+1,'/',len(batches_list)
print labels[0],labels_one_hot[0,:]

plt.imshow(images[0])
plt.show()

if n == 5:
    break 
hdf5_file.close()
上一篇下一篇

猜你喜欢

热点阅读