caffe事儿真多,数据必须得lmdb或者leveldb什么的才行,若是数据是图片的话,那用caffe自带的convert_image.cpp就行,但若是不是图片,就得本身写程序了。我也不是计算机专业的,我哪看得懂源码,遂奋发而百度之,然无甚结果,遂google之,尝闻“内事不决问百度,外事不决问google”,古人诚不我欺。在caffe的google group里我找到了这个网址:http://deepdish.io/2015/04/28/creating-lmdb-in-python/python
代码以下:git
import numpy as np import lmdb import caffe N = 1000 # Let's pretend this is interesting data X = np.zeros((N, 3, 32, 32), dtype=np.uint8) y = np.zeros(N, dtype=np.int64) # We need to prepare the database for the size. We'll set it 10 times # greater than what we theoretically need. There is little drawback to # setting this too big. If you still run into problem after raising # this, you might want to try saving fewer entries in a single # transaction. map_size = X.nbytes * 10 env = lmdb.open('mylmdb', map_size=map_size) with env.begin(write=True) as txn: # txn is a Transaction object 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]) str_id = '{:08}'.format(i) # The encode is only essential in Python 3 txn.put(str_id.encode('ascii'), datum.SerializeToString())
这是用python将数据转为lmdb的代码,可是我用这个处理完数据再使用caffe会出现std::bad_alloc错误,后来通过艰苦地奋斗,查阅了大量资料,我发现了问题所在:github
1.caffe的数据格式默认为四维(n_samples, n_channels, height, width)
.因此必须把个人数据处理成这种格式ui
2.最后一行txn.put(str_id.encode('ascii'), datum.SerializeToString())必定要加上,我一开始一维python2不用写这个,结果总是出错,后来才发现这行必须写!this
3.若是出现mdb_put: MDB_MAP_FULL: Environment mapsize limit reached
的错误,是由于lmdb默认的map_size比较小,我把lmdb/cffi.py里面的map_size默认值改了一下,改为了1099511627776(也就是1Tb),我也不知道是否是这么改,而后我又把上面python程序里map_size = X.nbytes 这句改为了map_size = X.nbytes * 10,而后就成功了!google
找资料的过程当中,我还发现了用python写leveldb的程序,网址在这里:https://github.com/BVLC/caffe/issues/745和http://stackoverflow.com/questions/32707393/whats-caffes-input-formatspa
用python写HDF5的程序在这里:http://stackoverflow.com/questions/31774953/test-labels-for-regression-caffe-float-not-allowed/31808324#31808324rest
参考:code
1.http://stackoverflow.com/questions/30983213/how-to-use-1-dim-vector-as-input-for-caffe/30991590#30991590orm
2.关于lmdb的map_size大小的问题:https://github.com/BVLC/caffe/issues/1298和http://stackoverflow.com/questions/31820976/lmdb-increase-map-size