Deep Learning and PyTorch Bootcamp for Beginners (Easy! From Basics to ChatGPT's Core Transformer) [Data Analysis/Science Part 3]
This is a newly designed course that allows you to gradually learn the mathematics, theory, PyTorch-based implementation, transfer learning, and GPT's core transformer needed to understand deep learning, based on the instructor's own failed experiences when first learning deep learning.
1,676 learners
Level Basic
Course period Unlimited
News
21 articles
Hello. This is Dave Lee from Fun Coding.
I need to translate this Korean text to English while preserving any markers and following the guidelines. The text is: "다름이 아니라 딥러닝 강의에서 수정 사항이 있어서 가볍게 공유를 드립니다." This is a polite, formal Korean sentence. Let me break it down: - "다름이 아니라" - a polite opening phrase meaning "it's nothing special but" or "I'm reaching out because" - "딥러닝 강의에서" - "in the deep learning course/lecture" - "수정 사항이 있어서" - "there are some corrections/modifications" - "가볍게 공유를 드립니다" - "I'm sharing (this) briefly/lightly" (polite form) Translation: I
There was an error in the test_loss calculation part during test evaluation in the "Applying CNN to MNIST Classification Problem" chapter. We apologize for the inconvenience. Therefore, we have updated the related materials with the following context.
nn.NLLLoss() has reduction='mean' applied by default, so it returns the average loss of samples within each mini-batch. Therefore, the test_loss accumulated through the for loop becomes "the sum of mini-batch average values".
In the existing code, this value was divided by the total number of samples (len(test_batches.dataset), e.g., 10000), which results in a much smaller value than the actual loss. For correct calculation, it should be divided by the number of mini-batches (len(test_batches), e.g., 79).
In other words, since it's the sum of mini-batch averages, dividing by the number of mini-batches accurately calculates the overall average loss.
I understand you want me to translate "수정된 파일:" from Korean to English. Modified files:
I understand you want me to translate the content of "12_CNN_MNIST.ipynb". However, I don't see any Korean text content provided to translate.
# Translation Analysis This appears to be a filename for a Jupyter notebook file. According to the translation guidelines: 1. Filenames should generally be preserved as they are technical elements 2. The components are
# Translation Analysis This appears to be a filename for a Jupyter notebook. According to the technical requirements, I should preserve filenames, code elements, and technical terms unchanged. # Translation 12_CNN_MNIST_GPU_DROPOUT.ipynb
I have completed the modifications to the Jupyter Notebook materials, so if you download the course materials again, you can study with the updated code.
Thank you.
Hello. This is Dave Lee from Janjaemi Coding.
The reason is that we have opened a new lecture and are sharing it with you briefly.
This lecture systematically organizes the core of computer engineering (CS knowledge) that developers or data specialists preparing for careers or working in the field must know. Among the various subjects of computer engineering (CS knowledge) , three subjects were organized into one lecture so that you can efficiently learn the important computer structure, operating system, and network . In addition, to prepare for technical interviews, the core technical interview questions for each subject, special answer methods, and model answers were included.
Computer science knowledge is essential foundation knowledge in the development and data fields, but its importance is often overlooked. I also emphasize to my acquaintances and family that if you are preparing to become a developer or data specialist, you should definitely learn this theory, which is absolutely necessary in the mid- to long-term .
However, many people have difficulty organizing it into individual subjects because of the large volume. To solve this difficulty , the content has been neatly organized in the form of online lectures . While covering key concepts in depth, various explanation methods have been used to help with clear understanding .
This is a proven lecture that has been selected by tens of thousands of students and used as a training material for new employees by leading domestic IT companies, after being reworked several times over the past five years. This time, it has been reworked and improved and opened again. I hope it will be helpful.
We've also included a new opening discount.
thank you
Remnant fun coding dream
Hello. This is Dave Lee from Janjaemi Coding.
I am sharing the lectures lightly by renewing them. It is a continuation of the lectures that were renewed just before.
The following lectures have been renewed.
The existing Python Backend and Web Technology Bootcamp course titles have also been changed to match the purpose of the course, which is to organize the core web technology concepts, intermediate Python grammar, and backend basics that must be understood for full-scale development . The course content has been improved to reflect the latest trends and the fastest full-stack development architecture .
Through this course, you can effectively learn Python intermediate grammar (including intermediate object-oriented) essential for practical development, web/app core concepts, and the latest full-stack architecture. Those who have already taken the course can listen to it again. Updated videos are marked with (updated) in the chapter name, so that those who have already learned can check only the updated parts. We will continue to provide a satisfactory learning experience through continuous updates.
Just like this lecture, I will continue to improve other lectures in the future.
I hope the related lectures will be helpful to you.
thank you
Hello. This is Dave Lee from Janjaemi Coding.
I've renewed the lecture and am sharing it with you in a lighter way.
Following the lecture that was just renewed
[Renewal] Python Data Analysis for Beginners (Easy! Learn Preprocessing, Pandas, and Visualization) [Data Analysis/Science Part 1]The following lectures have been renewed.
We have improved the parts that seemed lacking in the existing lectures and improved them to match the latest libraries. We have also improved the lectures by adding stories from a more practical perspective. Those who have already taken the lectures can listen to them again.
Just like this lecture, I will continue to improve other lectures in the future.
I hope the related lectures will be helpful to you.
thank you
Hello. This is Dave Lee from Janjaemi Coding.
I've renewed the lecture and am sharing it with you in a lighter way.
This is a lecture that many people have taken and liked. We have renewed the following lecture, which contains functions for preprocessing, analyzing, and visualizing data based on Python. We have improved the parts that seemed lacking in the existing lecture, and in the data field, there are cases where the grammar is different depending on the library version. We have improved it to match the latest library. We have also improved the lecture by adding stories from a more practical perspective. Those who have already taken the lecture can listen to it again.
Just like this lecture, the next lecture is also scheduled to be renewed by the end of this month, and we will continue to improve other lectures in the future.
I hope this will be helpful to those who are interested in related lectures.
thank youHello. This is Dave Lee from Janjaemi Coding.
Although it's late, Happy New Year. I heard that many non-majors are wondering what direction they should prepare for data-related careers (data analysts, data scientists, etc.).
So, I created a YouTube video on the fastest way to prepare for each situation for non-major workers, college students (new hires, 3rd or 4th year students), and graduates (job seekers).
Personally, I think that the data field is a good field to prepare for not only a data career, but also AI agent-based AI service development, which has recently become a hot topic. If you are interested, I hope the related video will be helpful.
thank you
Hello. This is Dave Lee from Janjaemi Coding.
The reason is that I am sharing this because there are some parts of the code that may behave slightly differently in recent PyTorch versions.
In recent PyTorch versions, when creating a tensor with FloatTensor() , each tensor is initialized to 0, not a random value.
(Because the internal memory is allocated but the values are not initialized to “0” or random values, random-looking values (actually garbage values that were left in the memory) were entered, but the latest version forces them to be initialized to 0.)
Therefore, when creating a simple tensor without arbitrarily specifying a specific value, 0 is specified as the initial value when outputting each tensor, not a random value, so it comes out as 0 when output. This is normal operation, so it would be good to refer to only this part.
We have updated the entire data by including an explanation of this part in the code data today.
thank you
Dave Lee Dream of residual fun coding
Hello, this is Dave Lee from Janjaemi Coding.
This time, we've prepared a new roadmap for learning SQL and are sharing it with you!
SQL Ending (w/Fun Coding) :https://www.inflearn.com/roadmaps/6724
SQL is an essential tool in both data and development. Recently, SQL coding tests are increasing, but many people find it difficult to write the desired query by combining various grammars and concepts as they thought. The fastest way to effectively master SQL is to solve real problems and gain experience writing various queries.
This roadmap covers everything from basic database concepts to basic and intermediate SQL grammar, and is designed to help you systematically organize SQL through 101 practical problems. The following two lectures are bundled together and have a 30% discount, so we recommend them to anyone who wants to solidify their SQL.
[2024 Renewal] Beginner SQL and Database (MySQL) Bootcamp [From Introduction to Utilization]
[2024 New Lecture] Intermediate-Advanced SQL and Practical Data Analysis 101 Problem Solving [Data Analysis/Science Part 1]
I hope this will be helpful to those who want to organize SQL systematically.
thank you
