Caffe - 创建LMDB/HDF5格式数据

import numpy as np
import lmdb
import caffe

lmdb_file = '/path/to/data_lmdb'
N = 1000 
# 准备 data 和 labels
X = np.zeros((N, 3, 224, 224), dtype=np.uint8) # data
y = np.zeros(N, dtype=np.int64) # labels

env = lmdb.open(lmdb_file, map_size=int(1e12))
txn = env.begin(write=True)

for i in range(N):
    datum = caffe.proto.caffe_pb2.Datum()

    datum.channels = X.shape[1]
    datum.height = X.shape[2]
    datum.width = X.shape[3]
    datum.data = X[i].tobytes()  # or .tostring() if numpy < 1.9
    datum.label = int(y[i])
    # 以上五行也可以直接： datum = caffe.io.array_to_datum(data, label)
    str_id = '{:08}'.format(i)
    txn.put(str_id, datum.SerializeToString())

    # in Python3
    # txn.put(str_id.encode('ascii'), datum.SerializeToString())

import numpy as np
import lmdb
import caffe

env = lmdb.open('data_lmdb', readonly=True)
txn = env.begin()
lmdb_cursor = txn.cursor()
datum = caffe.proto.caffe_pb2.Datum()

for key, value in lmdb_cursor:
    print '{},{}'.format(key, value)
    datum.ParseFromString(value)

    flat_data = np.fromstring(datum.data, dtype=np.uint8)
    data = flat_data.reshape(datum.channels, datum.height, datum.width)
    # 或 data = caffe.io.datum_to_array(datum)
    labels = datum.label

import h5py 
import numpy as np  

# 创建HDF5文件  
imgsData = np.zeros((10,3,224,224)) # Images
labels = range(10)                 # Labels
f = h5py.File('HDF5_FILE.h5','w')  # 创建一个h5文件 
f['data'] = imgsData                # 写入Images数据 
f['labels'] = labels               # 写入Labels数据 
f.close()                          #  

# 读取HDF5文件  
f = h5py.File('HDF5_FILE.h5','r')   # 打开h5文件  
f_keys = f.keys()                   
imgsData = f['data'][:] 
labels = f['labels'][:] 
f.close()