Caffe均值文件binaryproto转npy

之前做过点项目，整理一下小细节。

mean.binaryproto转mean.npy

首先是生成binaryproto的sh文件

#!/usr/bin/env sh
# Compute the mean image from the imagenet training lmdb
# N.B. this is available in data/ilsvrc12
EXAMPLE=.
DATA=/data/model_train/trainSet
TOOLS=/data/cuda+digits3.0+cudnnv5+opencv/caffe-master/build/tools

$TOOLS/compute_image_mean $EXAMPLE/train_lmdb \
  $EXAMPLE/train_lmdb/trainset_mean.binaryproto

$TOOLS/compute_image_mean $EXAMPLE/test_lmdb \
  $EXAMPLE/test_lmdb/testset_mean.binaryproto

echo "Done."

然后调用python脚本转换为npy数据

#!/usr/bin/env python
#coding=gbk
import numpy as np
import os
import sys
import argparse
import glob
import time,datetime
import scipy.io as scio

caffe_root = '/data/cuda+digits3.0+cudnnv5+opencv/caffe-master/' #caffe-master			
import sys
pycaffe_dir=sys.path.insert(0, caffe_root + 'python')
import caffe
caffe.set_mode_gpu();

if len(sys.argv)!=3:
    print "Usage: python convert_mean.py mean.binaryproto mean.npy"
    sys.exit()

blob = caffe.proto.caffe_pb2.BlobProto()
bin_mean = open( sys.argv[1] , 'rb' ).read()
blob.ParseFromString(bin_mean)
arr = np.array( caffe.io.blobproto_to_array(blob) )
npy_mean = arr[0]
np.save( sys.argv[2] , npy_mean )

在终端使用方法

python convert_mean.py mean.binaryproto mean.npy