<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Ai on Semonan Book</title><link>https://semonan.com/en/tags/ai/</link><description>Recent content in Ai on Semonan Book</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Wed, 03 Dec 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://semonan.com/en/tags/ai/rss.xml" rel="self" type="application/rss+xml"/><item><title>Face Analysis based on Deep Learning</title><link>https://semonan.com/en/book/ai/face-processing/face-analysis-deep-learning/</link><pubDate>Wed, 16 Oct 2024 00:00:00 +0000</pubDate><guid>https://semonan.com/en/book/ai/face-processing/face-analysis-deep-learning/</guid><description>&lt;h1 id="face-analysis-based-on-deep-learning"&gt;Face Analysis based on Deep Learning&lt;a class="anchor" href="#face-analysis-based-on-deep-learning"&gt;#&lt;/a&gt;&lt;/h1&gt;
&lt;p&gt;With the advancement of deep learning technology, the performance of face analysis has also improved.&lt;br&gt;
I will introduce a high-performing open-source face analysis library and explain how to use it.&lt;/p&gt;
&lt;h2 id="insightface-2d-and-3d-face-analysis-project"&gt;InsightFace: 2D and 3D Face Analysis Project&lt;a class="anchor" href="#insightface-2d-and-3d-face-analysis-project"&gt;#&lt;/a&gt;&lt;/h2&gt;
&lt;ul&gt;
&lt;li&gt;&lt;a href="https://github.com/deepinsight/insightface" rel="noopener noreferrer" target="_blank"&gt;&lt;code&gt;https://github.com/deepinsight/insightface&lt;/code&gt;&lt;/a&gt;&lt;/li&gt;
&lt;/ul&gt;
&lt;p&gt;※ License : Please refer to the above site !&lt;/p&gt;
&lt;p&gt;Here, we share various models, and I would like to introduce the &lt;code&gt;buffalo_l&lt;/code&gt; model pack.&lt;br&gt;
&lt;code&gt;buffalo_l&lt;/code&gt; provides blob box, key points, detection score, landmark 2D/3D, gender, age, embedding, and pose information.&lt;br&gt;
 &lt;br&gt;
I will demonstrate the process of face analysis using Python.&lt;/p&gt;</description></item><item><title>Pay-as-you-go ChatGPT</title><link>https://semonan.com/en/book/ai/usage-tips/chatgpt-pay-as-you-go/</link><pubDate>Sun, 14 Jul 2024 00:00:00 +0000</pubDate><guid>https://semonan.com/en/book/ai/usage-tips/chatgpt-pay-as-you-go/</guid><description>&lt;h1 id="using-the-paid-version-of-chatgpt-affordably-via-api"&gt;Using the Paid Version of ChatGPT Affordably via API&lt;a class="anchor" href="#using-the-paid-version-of-chatgpt-affordably-via-api"&gt;#&lt;/a&gt;&lt;/h1&gt;
&lt;h2 id="backgroundproblem"&gt;Background/Problem&lt;a class="anchor" href="#backgroundproblem"&gt;#&lt;/a&gt;&lt;/h2&gt;
&lt;p&gt;To use the paid version of Chat GPT offered by OpenAI, a monthly subscription fee of $20 is required.&lt;br&gt;
(As of June 2024, this amounts to approximately 30,000 KRW when applying the exchange rate for South Korea.)&lt;br&gt;
Paying $20 every month can feel expensive for those with low usage.&lt;/p&gt;
&lt;h2 id="improvement"&gt;Improvement&lt;a class="anchor" href="#improvement"&gt;#&lt;/a&gt;&lt;/h2&gt;
&lt;p&gt;To address this issue, I will explain a simple coding method that allows for pay-as-you-go usage.&lt;br&gt;
OpenAI provides an API for the Chat Bot, which operates on a pay-as-you-go basis.&lt;br&gt;
Therefore, if your monthly usage is low, using the API can be more cost-effective than subscribing.&lt;/p&gt;</description></item><item><title>LoRA</title><link>https://semonan.com/en/book/ai/fine-tuning/lora/</link><pubDate>Sun, 07 Jul 2024 00:00:00 +0000</pubDate><guid>https://semonan.com/en/book/ai/fine-tuning/lora/</guid><description>&lt;link rel="stylesheet" href="https://semonan.com/katex/katex.min.css" /&gt;&lt;script defer src="https://semonan.com/katex/katex.min.js"&gt;&lt;/script&gt;&lt;script defer src="https://semonan.com/katex/auto-render.min.js" onload="renderMathInElement(document.body, {&amp;#34;delimiters&amp;#34;:[{&amp;#34;left&amp;#34;:&amp;#34;$$&amp;#34;,&amp;#34;right&amp;#34;:&amp;#34;$$&amp;#34;,&amp;#34;display&amp;#34;:true},{&amp;#34;left&amp;#34;:&amp;#34;$&amp;#34;,&amp;#34;right&amp;#34;:&amp;#34;$&amp;#34;,&amp;#34;display&amp;#34;:false},{&amp;#34;left&amp;#34;:&amp;#34;\\[&amp;#34;,&amp;#34;right&amp;#34;:&amp;#34;\\]&amp;#34;,&amp;#34;display&amp;#34;:true},{&amp;#34;left&amp;#34;:&amp;#34;\\(&amp;#34;,&amp;#34;right&amp;#34;:&amp;#34;\\)&amp;#34;,&amp;#34;display&amp;#34;:false}]});"&gt;&lt;/script&gt;
&lt;h1 id="lora-low-rank-adaptation"&gt;LoRA (Low-Rank Adaptation)&lt;a class="anchor" href="#lora-low-rank-adaptation"&gt;#&lt;/a&gt;&lt;/h1&gt;
&lt;p&gt;LoRA is one of the PEFT (Parameter-Efficient Fine-Tuning) techniques.&lt;br&gt;
This technique efficiently fine-tunes large pre-trained models for specific tasks.&lt;/p&gt;
&lt;p&gt;(The following content is referenced from the paper &amp;ldquo;LoRA: Low-Rank Adaptation of Large Language Models.&amp;rdquo;)&lt;/p&gt;
&lt;h2 id="backgroundproblem"&gt;Background/Problem&lt;a class="anchor" href="#backgroundproblem"&gt;#&lt;/a&gt;&lt;/h2&gt;
&lt;p&gt;Models like LLM (Large Language Models) have an extremely large number of parameters.&lt;br&gt;
For example, the llama3 model, released in April 2024, has about 70 billion parameters and a file size of over 40GB, with many models being even larger.&lt;br&gt;
Full fine-tuning of such large models requires high-performance GPUs and considerable training time.&lt;br&gt;
Additionally, fully fine-tuning the base model may potentially degrade the fundamental performance learned during pretraining.&lt;/p&gt;</description></item><item><title>Surging DRAM Demand</title><link>https://semonan.com/en/book/life-engineering/computer/surging-dram-demand/</link><pubDate>Wed, 03 Dec 2025 00:00:00 +0000</pubDate><guid>https://semonan.com/en/book/life-engineering/computer/surging-dram-demand/</guid><description>&lt;h1 id="memory-manufacturers-are-raking-in-money"&gt;Memory Manufacturers Are Raking In Money&lt;a class="anchor" href="#memory-manufacturers-are-raking-in-money"&gt;#&lt;/a&gt;&lt;/h1&gt;
&lt;p&gt;Samsung Electronics, SK Hynix, and Micron are the world&amp;rsquo;s three largest memory manufacturers.
They generate huge operating profits by producing and selling DRAM.
As of December 2025, DRAM demand has surged so much that they reportedly cannot keep up with supply.
In other words, DRAM makers are raking in money, and this trend is expected to continue for the foreseeable future.
What exactly is DRAM, and why has its demand suddenly skyrocketed?
Let me explain why.&lt;/p&gt;</description></item><item><title>Image editing</title><link>https://semonan.com/en/book/ai/usage-tips/image-editing/</link><pubDate>Sun, 23 Nov 2025 00:00:00 +0000</pubDate><guid>https://semonan.com/en/book/ai/usage-tips/image-editing/</guid><description>&lt;h1 id="letting-ai-edit-images"&gt;Letting AI Edit Images&lt;a class="anchor" href="#letting-ai-edit-images"&gt;#&lt;/a&gt;&lt;/h1&gt;
&lt;h2 id="is-ai-good-at-editing-images"&gt;Is AI good at editing images?&lt;a class="anchor" href="#is-ai-good-at-editing-images"&gt;#&lt;/a&gt;&lt;/h2&gt;
&lt;p&gt;Editing images, such as removing specific objects or changing their colors, has become an area where AI excels.&lt;br&gt;
Let&amp;rsquo;s take a look at how well it performs.&lt;br&gt;
The image on the left is the original, and the one on the right has been modified by AI.&lt;/p&gt;
&lt;ul&gt;
&lt;li&gt;Sample 1&lt;br&gt;
Prompt : &amp;ldquo;Please remove the apple from the picture.&amp;rdquo;&lt;/li&gt;
&lt;/ul&gt;
&lt;p&gt;The AI smoothly erased the apple as follows.&lt;br&gt;
&lt;img src="https://semonan.com/images/book/ai/usage-tips/image-editing/sample1.webp" alt="AI image editing sample 1 - removing an apple" width="370"&gt;&lt;/p&gt;</description></item></channel></rss>