Caffe: Reading LMDB from Python

If you have encoded images in lmdb, you'll probably see this error when using @ytrewq's code

ValueError: total size of new array must be unchanged

Use this function instead:

import caffe
import lmdb
import PIL.Image
from io import StringIO
import numpy as np

def read_lmdb(lmdb_file):
    cursor = lmdb.open(lmdb_file, readonly=True).begin().cursor()
    datum = caffe.proto.caffe_pb2.Datum()
    for _, value in cursor:
        datum.ParseFromString(value)
        s = StringIO()
        s.write(datum.data)
        s.seek(0)

        yield np.array(PIL.Image.open(s)), datum.label

Example:

lmdb_dir = '/save/jobs/20160613-125532-958f/train_db/'
for im, label in read_lmdb(lmdb_dir):
    print label, im

Here's the working code I figured out

import caffe
import lmdb

lmdb_env = lmdb.open('directory_containing_mdb')
lmdb_txn = lmdb_env.begin()
lmdb_cursor = lmdb_txn.cursor()
datum = caffe.proto.caffe_pb2.Datum()

for key, value in lmdb_cursor:
    datum.ParseFromString(value)
    label = datum.label
    data = caffe.io.datum_to_array(datum)
    for l, d in zip(label, data):
            print l, d

Tags:

Python

Caffe

Lmdb