Caffe学习：使用pycaffe生成mean_file.py文件

最新推荐文章于 2020-03-25 16:34:30 发布

jiarenyf

最新推荐文章于 2020-03-25 16:34:30 发布

阅读量4.4k

点赞数 1

本文链接：https://blog.csdn.net/u011762313/article/details/48215621

版权

machine-learning 同时被 3 个专栏收录

34 篇文章 0 订阅

订阅专栏

caffe

29 篇文章 2 订阅

订阅专栏

python

27 篇文章 0 订阅

订阅专栏

利用build/tools/compute_image_mean产生mean.binaryproto文件后，利用如下代码产生mean.npy文件，给pycaffe调用：

#!/usr/bin/env python

MEAN_BIN = 'mean.binaryproto'
MEAN_NPY = 'mean.npy'

from caffe.proto import caffe_pb2
from caffe.io import blobproto_to_array

print('generating mean file...')

mean_blob = caffe_pb2.BlobProto()
mean_blob.ParseFromString(open(MEAN_BIN, 'rb').read())

import numpy as np
mean_npy = blobproto_to_array(mean_blob)
mean_npy_shape = mean_npy.shape
mean_npy = mean_npy.reshape(mean_npy_shape[1], mean_npy_shape[2], mean_npy_shape[3])

np.save(file(MEAN_NPY, 'wb'), mean_npy)

print('done...')