인프런 - 라이프타임 커리어 플랫폼

This is a lecture that studies Vision Transformer, one of the latest deep learning technologies, and implements a paper using Pytorch. Come experience the new future of the vision field with me!

This newly designed course, drawing from the instructor's initial deep learning failures, helps you progressively learn deep learning essentials: math, theory, PyTorch-based implementation, transfer learning, and GPT's core Transformer.

When researching AI or conducting a project using it, basic paper implementation is essential. Let's upgrade our practical skills by implementing an actual paper through this lecture!

Still lost on CNN even after studying it? I'll concisely explain CNN's core mechanics.

We implement the latest Transformer-based PixArt and lightweight adaptation SANA step by step from theory to code. Building on DDPM·DDIM·LDM·DiT covered in Parts I·II, we complete hands-on practice including text encoder integration, samplers (DDIM/ODE), v-prediction/CFG tuning, and small-scale data style fine-tuning.

This course conducts hands-on practice related to Diffusion models among generative artificial intelligence models. By reading and implementing the prompt-to-prompt paper, which is a representative Diffusion model application paper, we expect to cultivate the ability to understand the latest artificial intelligence papers.

From core theories of deep learning and CNN to various CNN model implementation methods, and practical deep learning development know-how through real-world problems, If you want to become a deep learning CNN technology expert based on Pytorch, join us in this lecture :)

This course is a step-by-step learning process that covers the principles of image and object recognition using deep learning, from fundamentals to the latest models. - Building Foundations: Understanding tensors and basic neural network structures with PyTorch - Understanding Images: Learning computer vision concepts, image data structures, and augmentation techniques - CNN Model Training: Hands-on image classification practice with Convolutional Neural Networks (CNN) using datasets like CIFAR-10 - Transfer Learning: Leveraging pre-trained models to achieve fast learning with limited data - Object Detection: Understanding and practicing with the latest object detection models including R-CNN, YOLO, SSD, DETR - Segmentation: Experiencing pixel-level object segmentation through U-Net and Mask R-CNN