【 Caffe C++】ubuntu下創建hdf5數據源解決多標籤問題

如何在ubuntu下爲caffe創建HDF5數據源？

hdf5數據源示例

layer{
  name:"data"
  type:"HDF5Data"
  top:"data"
  top:"label"
  hdf5_data_parm{
    source:"examples/hdf5_classification/data/train.txt"
    batch_size:10
  }
}

### hdf5文件label的寫法：
### 假設有三張人臉圖片，要定位圖片中人臉的眼睛、鼻子、嘴的位置
1.jpg 11 78 62 71 84 65 26 51 46 89
2.jpg 13 25 62 53 53 65 26 32 42 13
3.jpg 15 78 66 13 84 65 32 41 51 65

使用python生成數據源：

ipmort hdf5
import os
import cv2
import math
import numpy as np
import random
import re

root_path="/home/lichunlin/caffe_case/HDF5/image"

with open("/home/lichunlin/caffe_case/HDF5/hdf5.txt",'r') as f:
    lines=f.readlines()

num=len(lines)
random.shuffle(lines)

imgAccu = 0
imgs=np.zeros([num,3,224,224])
labels=np.zeros([num,10])
for i in range(num):
    line-lines[i]
    segments=re.split('\s+',line[:-1])
    print segments[0]
    img=cv2.imread(os.path.join(root_path,segments[0]))
    img=cv2.resize(img,(224,224))
    img=img.transpose(2,0,1) #opencv讀到的數據是h*w*c，但是caffe的類型是c×h×w
				#h:heght  w:width  c:channel
    imgs[i,:,:,:]=img.astype(np.float32)	#把相應的數據存儲到相應的位置
    
    for j in range(10):  #當圖片的格式改了以後，相應的位置也發生了變化，得到新的位置
        labels[i,j]=float(segments[j+1]*224/256)

batchSize=1	#將大的文件分成好幾個bathSize，一個bathSize存8000以下
batchNum=int(math.ceil(1.0*num/batchSize))

imgMean=int(math.ceil(1.0*num/batchSize))

imgMean=np.mean(imgs,axis=0)
#imgs=(imgs - ImgsMean)/255.0
labelsMean = np.
mean(labels,axis=0)
labels=(labels - labelsMean)/10

if os.path.exists('trainlist.txt'):
    os.remove('trainlist.txt')
if os.path.exists('testlist.txt'):
    os.remove('testlist.txt')
comp_kwargs={'compression':'gzip','compression_opts':1}
    start=i*batchSize
    end=min((i+1)*batchSize,num)
    if i<batchNum-1:
        filename='/home/lichunlin/caffe_case/HDF5/h5/train{0}.h5,format(i)'
    else:
        filename='/home/lichunlin/caffe_case/HDF5/h5/test{0}.h5,format(i-batchNum+1)'
    print filename
    with h5py.File(filename,'w') as f:
        f.create_dataset('data',data=np.array((imgs[start:end]-imgsMean)/225.0).astype(np.float32), **comp_kwargs)
        f.create_dataset('label',data=np.array(lables[start:end]).astype(np.float32),**comp_kwargs)
    if i<batchNum -1:
        with open('/home/lichunlin/caffe_case/HDF5/h5/trainlist.txt','a') as f:
            f.write(os.pathjoin(os.getcwd(),'train{0}.h5').format(i)+'\n')
    else:
        with open('/home/lichunlin/caffe_case/HDF5/h5/trainlist.txt','a') as f:
            f.write(os.pathjoin(os.getcwd(),'train{0}.h5').format(i-batchNum+1)+'\n')

imgsMean = np.mean(imgsMean,axis=(1,2))
with open('mean.txt','w') as f:
    f.write(str(imgsMean[0])+'\n'+str(imgsMean[1])+'\n'+str(imgsMean[2]))