35% Off Finance Skills That Get You Hired - Code CFI35
Get 50% Off Udacity Nanodegrees — Code CC50
Overview
Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore DeepSeek OCR, an innovative approach that goes beyond traditional optical character recognition by using images to compress text representations more effectively. Examine the DeepSeek OCR paper and understand how this experimental technology leverages visual processing to achieve better text compression. Learn about the underlying architecture including Transformers and Vision Transformers (ViT) that power this system. Discover how to access DeepSeek-OCR through GitHub and Hugging Face platforms, and compare it with other OCR solutions like Nanonets and PaddleOCR-VL to understand the broader landscape of optical character recognition technologies.
Syllabus
00:00 Intro
00:30 DeepSeek OCR: Contexts Optical Compression Paper
03:37 Transformer
04:12 Vision Transformer ViT
10:11 DeepSeek-OCR GitHub and Hugging Face
10:32 Nanonets and PaddleOCR-VL
Taught by
Sam Witteveen