모두를 위한 대규모 언어 모델 LLM(Large Language Model) Part 1 - Llama 2 Fine-Tuning 해보기
AISchool
LLM(Large Language Model)의 기초 개념부터 고성능 LLM인 Llama 2 모델을 내가 원하는 데이터셋에 Fine-Tuning하는 방법까지 차근차근 학습합니다.
중급이상
LLM, Llama, 딥러닝
BEST
All-in-one deep learning image recognition with vehicle license plate recognition project and TensorFlow
This is an all-in-one lecture where you can learn the entire process from the basics of deep learning/TensorFlow/computer vision to practical applications through a practical vehicle license plate recognition project. Through various practical exercises, you can develop practical skills to apply the latest deep learning models to custom datasets.
Reviews from Early Learners
What you will gain after the course
How to proceed with a deep learning practical project rather than a basic example such as MNIST, CIFAR-10
How to apply the latest deep learning models to your custom dataset
Step-by-step learning from basic concepts of deep learning/machine learning to practical applications
Deep understanding of deep learning model architectures proposed in recent papers (EfficientNet, CenterNet, EAST, ...)
Principles and usage of the latest deep learning models used in various computer vision problem areas such as Object Detection, Text Detection, OCR, Image Captioning, and Generative Models.
How to improve the performance of deep learning models
Through various practical projects and learning from the latest papers
Become a Deep Learning/Computer Vision Expert . 😀
Please check before taking the class!
- This lecture is based on the existing
, Some classes overlap with the lectures. Please check the curriculum before taking the class.
List of relevant curriculum
- Introduction to Object Detection Problem Domain
- Object Detection Metrics - IoU, mAP
- Object Detection Datasets – Pascal VOC, MS COCO, KITTI, Open Images
- Introduction to TensorFlow Object Detection API
- R-CNN(Regions with CNN)
- Fast R-CNN
- Faster R-CNN
- Non-Maximum Suppression (NMS)
- SSD(Single Shot MultiBox Detector)
- RetinaNet
- CenterNet
- Object Detection using Pre-Trained Model
< Introduction to Deep Learning with TensorFlow 2.0 > Section 1
- Artificial Intelligence, Machine Learning, Deep Learning & Supervised Learning, Unsupervised Learning, Reinforcement Learning
- Deep Learning, TensorFlow Applications
- A brief history of deep learning
< Introduction to Deep Learning with TensorFlow 2.0 > Section 3
- Basic process of machine learning - defining hypothesis, defining loss function, defining optimization
- Implementing a Linear Regression Algorithm Using TensorFlow 2.0
- Batch Gradient Descent, Stochastic Gradient Descent, Mini-Batch Gradient Descent
- Training Data, Validation Data, Test Data & Overfitting
- Softmax Regression & Cross-Entropy Loss Function & One-hot Encoding & MNIST
- TensorFlow 2.0 Keras Subclassing
- Implementing MNIST Digit Classifier Using TensorFlow 2.0 and Softmax Regression
< Introduction to Deep Learning with TensorFlow 2.0 > Section 4
- Multilayer Perceptron MLP
- Implementing MNIST Digit Classifier Using TensorFlow 2.0 and ANN
< Introduction to Deep Learning with TensorFlow 2.0 > Section 5
- Concept of AutoEncoder
- Reconstructing MNIST data using TensorFlow 2.0 and autoencoders
< Introduction to Deep Learning with TensorFlow 2.0 > Section 6
- The Difficulty of Computer Vision Problems and the Advent of the CNN-Based Computer Vision Era
- Core concepts of convolutional neural networks - Convolution, Pooling
- CNN implementation for MNIST digit classification using TensorFlow 2.0
- Dropout
- CNN implementation for CIFAR-10 image classification using TensorFlow 2.0
< Introduction to Deep Learning with TensorFlow 2.0 > Section 7
- Recurrent Neural Network (RNN)
- Vanishing Gradient Problem & LSTM & GRU
- Concept of Embedding & Char-RNN
- Char-RNN implementation using TensorFlow 2.0
< Introduction to Deep Learning with TensorFlow 2.0 > Section 8
- Saving and loading parameters using tf.train.CheckpointManager API
- Visualizing the learning process using TensorBoard
< Introduction to Deep Learning with TensorFlow 2.0 > Section 9
- Introduction to various computer vision problem areas
- Introduction to various natural language processing (NLP) problem areas
Learn how to use the latest deep learning models actually used by Naver (CRAFT) and Kakao (EAST).
All-in-One course to become a Deep Learning Computer Vision expert!
- We've compiled everything you need to learn to become a deep learning computer vision expert into one course.
- Essential theoretical knowledge for understanding the latest deep learning models : Learn the essential theories and knowledge required step by step, starting from the basics of machine learning and deep learning (ANN, CNN) to the principles of the latest deep learning models (EfficientNet, CenterNet).
- Code Implementation Skills Using Python/TensorFlow 2.0 : Learn step-by-step implementation skills for actual projects using Python and TensorFlow 2.0.
- Various practical projects for applying Custom Datasets : Rather than basic examples like MNIST, we will proceed with various practical projects for applying the latest deep learning models to various Custom Datasets .
Recommended for
these people
Who is this course right for?
Anyone who wants to seriously study deep learning/computer vision
Anyone who wants to work on a practical project using deep learning/computer vision
Need to know before starting?
Basic Python knowledge
9,339
Learners
706
Reviews
353
Answers
4.6
Rating
30
Courses
- AISchool ( http://aischool.ai/ )
- AISchool 유튜브 채널 운영 ( https://www.youtube.com/@aischool_ai )
- 서울대학교 인공지능 및 컴퓨터 비전 연구실 석사
- [솔라리스의 인공지능 연구실] 블로그 운영
- [텐서플로로 배우는 딥러닝] 집필
- S전자 컴퓨터 비전 관련 프로젝트 수행
- 기업대상 [AI 컨설팅 서비스] 제공
- 에이아이스쿨 [TensorFlow와 실습 프로젝트로 배우는 딥러닝-컴퓨터비전 Basic 코스] 강의 진행
Curriculum
All
126 lectures ∙ (20hr 51min)
Course Materials:
Lecture resources
7. Deep Learning
06:01
28. Dropout
05:06
31. AlexNet
17:08
32. VGGNet
07:18
Published:
Last updated:
Reviews
All
73 reviews
4.8
73 reviews
$110.00
AISchool's other courses
Check out other courses by the instructor!
Similar courses
Explore other courses in the same field!
![[OpenCV] 파이썬 딥러닝 영상처리 프로젝트 2 - 불량사과를 찾아라!강의 썸네일](https://cdn.inflearn.com/public/courses/325290/course_cover/0f6dc5fe-e6e6-414a-af6d-10f589e50788/openCV-dnn2-rotten-apple-eng.jpg?f=avif&w=420)
![[텐서플로2] 파이썬 머신러닝 완전정복 - 마라톤 기록예측 프로젝트강의 썸네일](https://cdn.inflearn.com/public/courses/324207/course_cover/1a79c7dc-1624-4d3a-95ff-79ba1e9c4025/python_machine_learning.png?f=avif&w=420)
![처음하는 딥러닝과 파이토치(Pytorch) 부트캠프 (쉽게! 기본부터 챗GPT 핵심 트랜스포머까지) [데이터분석/과학 Part3]강의 썸네일](https://cdn.inflearn.com/public/courses/329540/cover/1be7b8cb-800f-48cb-a30c-b7d78996c075/329540-eng.png?f=avif&w=420)
![[AI 실무] AI Research Engineer를 위한 논문 구현 시작하기 with PyTorch강의 썸네일](https://cdn.inflearn.com/public/courses/334289/cover/b8885796-1e67-4983-9432-bcda0daae927/334289.png?f=avif&w=420)
![[모바일] 딥러닝 Computer Vision 실전 프로젝트강의 썸네일](https://cdn.inflearn.com/public/courses/324985/course_cover/6bedded2-1f32-4d11-be03-6e5bf5a3b488/sjh-mobile-cv.png?f=avif&w=420)
![[7일 완성] 한 번에 합격하는 MS AI-900 자격증강의 썸네일](https://cdn.inflearn.com/public/files/courses/338854/cover/01k4caartf5v7x2e574pq0wnp8?f=avif&w=420)
