yahoo鉴黄模型测试

最新推荐文章于 2024-08-07 10:13:02 发布

江说江湖

最新推荐文章于 2024-08-07 10:13:02 发布

阅读量1.5k

点赞数

分类专栏：机器学习深度学习文章标签： CNN鉴黄 yahoo鉴黄鉴黄模型深度学习鉴黄

本文链接：https://blog.csdn.net/a784586/article/details/72914983

版权

在Windows 10环境下，使用Python3和Caffe测试Yahoo的鉴黄模型，参考了https://github.com/yahoo/open_nsfw的资源。

摘要由CSDN通过智能技术生成

yahoo鉴黄模型测试

参看网址：https://github.com/yahoo/open_nsfw
--------------------------------------------------------------------------
环境和平台： python3+win10+caffe
-------------------------------------------------------------------------

#coding=utf-8
"""
#coding=utf-8
Copyright 2016 Yahoo Inc.
Licensed under the terms of the 2 clause BSD license. 
Please see LICENSE file in the project root for terms.
"""

import numpy as np
import os
import sys
import argparse
import glob
import time
import locale
from PIL import Image
#import Image
#from StringIO import StringIO
from io import StringIO
from io import BytesIO
import caffe
import sys
print(sys.getdefaultencoding())
import chardet

fileWrite=open('log.json','w')

def resize_image(data, sz=(256, 256)):
    """
    Resize image. Please use this resize logic for best results instead of the 
    caffe, since it was used to generate training dataset 
    :param str data:
        The image data
    :param sz tuple:
        The resized image dimensions
    :returns bytearray:
        A byte array with the resized image
    """
    print(type(data))
    #im = Image.open(BytesIO(data))
    im = Image.open(BytesIO