深度学习去雨论文代码_将深度学习研究论文转换为有用的代码

深度学习去雨论文代码

If deep learning is a super power, then turning theories from a paper to usable code is a hyper power

如果深度学习是一种超级力量，那么将理论从论文转变为可用代码就是一种超级力量

为什么要学习实施机器学习研究论文？ (Why should I learn to implement machine learning research papers?)

As I’ve said, being able to convert a paper to code is definitely a hyper power, especially in a field like machine learning which is moving faster and faster each day.

正如我已经说过的，能够将纸张转换为代码绝对是一种强大的功能，尤其是在机器学习这样的领域中，它每天都在越来越快地发展。

Most research papers come from people within giant tech companies or universities who may be PhD holders or the ones who are working on the cutting edge technologies.

大多数研究论文来自可能是博士学位持有者或从事尖端技术研究的巨型技术公司或大学中的人员。

What else can be more cool than being able to reproduce the research done by these top notch professionals. Another thing to note is that the ones who can reproduce research papers as code is in huge demand.

还有什么比能够复制这些顶尖专业人士所做的研究更酷的了。需要注意的另一件事是，能够以代码形式复制研究论文的人员需求巨大。

Once you get the knack of implementing research papers, you will be in a state on par with these researchers.

一旦掌握了实施研究论文的技巧，您将处在与这些研究人员同等的状态。

These researchers too has acquired these skills through the practice of reading and implementing research papers.

这些研究人员也通过阅读和实施研究论文的实践获得了这些技能。

如何阅读和实施论文？ (How do I read and implement papers?)

You might say, “Hm, I have a general understanding of the deep learning algorithms like fully connected networks, convolutional neural networks, recurrent neural networks, but the problem is that I would like to develop SOTA(state of the art) voice cloning AI but I know nothing about voice cloning :( ”.

您可能会说：“嗯，我对深度学习算法(例如全连接网络，卷积神经网络，递归神经网络)有一般的了解，但问题是我想开发SOTA(最先进的)语音克隆AI但我对语音克隆:()一无所知。

Okay, here is your answer(some parts of my method is taken from Andrew Ng’s advice on reading papers).

好的，这是您的答案(我的方法的某些部分摘自Andrew Ng关于阅读论文的建议 )。

If you want to learn about a specific topic:

如果您想了解特定主题：

Collect 5–6 papers related to the specific topic(you can simply search arxiv or similar websites to get papers related to a topic).收集与特定主题相关的5至6篇论文(您可以简单地在arxiv或类似网站上搜索以获取与该主题相关的论文)。
Don’t read a single paper completely, instead skim through all of the papers and pick a paper that interests you or if you had a specific paper in mind, go pick it up, no one can stop you.不要完全阅读一份论文，而是浏览所有论文并选择一份您感兴趣的论文，或者如果您有特定的论文，那就去捡起来，没人能阻止您。
Read the abstract carefully and understand the idea from a high level and see whether your interest still persists, if so continue to skim through the images and see whether you can make assumptions on what the paper might be about.仔细阅读摘要，从高水平理解该想法，看看您的兴趣是否仍然存在，如果继续如此，则继续浏览图像，看看您是否可以对论文的内容做出假设。
Now read the introduction carefully line by line because most of what the paper contains will be explained here in the most simplest manner with minimal math.现在，请逐行仔细阅读介绍，因为本文将以最简单的方式用最少的数学方法来解释本文所含的大部分内容。
If you wish, you can skip the math equations in the first pass, don’t skip the math if the Greek letters are familiar.如果愿意，您可以在第一遍跳过数学方程式，如果希腊字母熟悉，请不要跳过数学方程式。
At any situation, if you get stuck or some words are confusing, never hesitate to google it. No one is born as master of everything ;)在任何情况下，如果您遇到困难或某些单词令人困惑，请立即使用google搜索。没有人天生就是一切的主人；)
After completing the first pass, you will be in a state where you understand the high level view of what the paper is trying prove or improve.完成第一遍后，您将处于一种状态，在这种状态下，您可以了解纸张在尝试证明或改进的内容。
In the second pass, try to understand almost everything in the paper and if you encounter any pseudo-code, try to convert it into your python library of choice(PyTorch, TensorFlow…)在第二遍中，尝试理解本文中的几乎所有内容，如果遇到任何伪代码，请尝试将其转换为您选择的python库(PyTorch，TensorFlow…)
You can get more papers to read and get a better understanding of the field by going to the references section of each paper(same as connecting the dots).通过转到每篇论文的参考部分(与连接点一样)，您可以获取更多的文章来阅读并更好地了解该领域。