【Pytorch】Windows10下配置Pytorch环境

0x00 前言

前言什么的也懒得说了……
总之:
听说你Pytorch很牛,
不乐意让我Windows用,
而我又听说pytorch用来训练模型超好用,
不仅没头脑而且不高兴!我要在我的windows上配一个!

Read More

Generative Adversarial Nets

Problem Restatement

This part mainly introduces the principle and realization method of GAN (Generative Adversarial Nets), GAN is proposed by lan.J et al. In 2014, they propose a new framework for estimating generative models via an adversarial process, in which simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake. This framework corresponds to a minimax two-player game. In the space of arbitrary functions G and D, a unique solution exists, with G recovering the training data distribution and D equal to 1/2 everywhere. In the case where G and D are defined by multilayer perceptron’s, the entire system can be trained with backpropagation. There is no need for any Markov chains or unrolled approximate inference net-works during either training or generation of samples[1].

Read More

【O2OTM】你的搜索透露了你的喜好——跨模态推荐

@(关键词)[跨模态,推荐系统,O2OTM,可解释性,机器学习]

Alt text

论文地址:http://mldm.ict.ac.cn/platform/pweb/academicDetail.htm?id=94

论文翻译:http://blog.csdn.net/okcd00/article/details/51814745

Read More

【Selenium】Windows平台使用python自动登陆网关

0x00 前言

所里开启了两步验证与二级加密(就不说是哪里了);
以前的auto_login用不了了,所以尝试着有没有什么新法子;
看到一个用 Phantomjs + Selenium 的解决方案,着手试试看好了。

Read More

【列表解析式】Python的单行操作秀

0x00 前言

1
items = [line for line in open('test.txt', 'rb')]

通常,我们会在代码中看到一些形似上面的炫目操作(什么你们觉得很正常?好嘛是我菜了QvQ)

我一头猛扎进了python的怀抱,正是因为“人生苦短,我用python”,可能是相似的原因,我第一眼就看上了这种表达方式,并且乐于在自己的代码中使用这种方式来更加精简与清晰地生成所需要的列表。

由于在项目实现过程中产生过大量的问题与需求,在无数次尝试之后决定总结一下如何使用列表解析式(也可称作链表推导式,本文中使用前者,不为什么,因为觉得这很Coooooool呀~)来解决这些类型的问题。

Read More