Description
In this video, we take a look at Swin Transformers. What is it? Why do we have it? How does it look?
ABOUT ME
⭕ Subscribe: https://www.youtube.com/c/CodeEmporium?sub_confirmation=1
📚 Medium Blog: https://medium.com/@dataemporium
💻 Github: https://github.com/ajhalthor
👔 LinkedIn: https://www.linkedin.com/in/ajay-halthor-477974bb/
RESOURCES
[1 📚] Main Paper: https://arxiv.org/pdf/2103.14030
[2 📚] Slides: https://link.excalidraw.com/p/readonly/GDnU1EEBGfAyUoEtVyj8
[3 📚] Feature Pyramid Networks: https://youtu.be/i4GKvPGoGxY?si=fgWUV1DYQH3YeU-6
[4 📚] Playlist of Transformers from scratch: https://youtu.be/QCJQG4DuHT0?si=UllVN6odQKC-nsvb
[5 📚] Faster R-CNN: https://youtu.be/ws0nlxCWWI8?si=om9yCa-mKWxTtFmQ
[6 📚] DETR: https://youtu.be/r3lDNWYDGF4?si=N4XehrgljW0A7XPQ
PLAYLISTS FROM MY CHANNEL
⭕ Reinforcement Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd9kS--NgVz0EPNyEmygV1Ha&si=AuThDZJwG19cgTA8
Natural Language Processing: https://youtube.com/playlist?list=PLTl9hO2Oobd_bzXUpzKMKA3liq2kj6LfE&si=LsVy8RDPu8jeO-cc
⭕ Transformers from Scratch: https://youtube.com/playlist?list=PLTl9hO2Oobd_bzXUpzKMKA3liq2kj6LfE
⭕ ChatGPT Playlist: https://youtube.com/playlist?list=PLTl9hO2Oobd9coYT6XsTraTBo4pL1j4HJ
⭕ Convolutional Neural Networks: https://youtube.com/playlist?list=PLTl9hO2Oobd9U0XHz62Lw6EgIMkQpfz74
⭕ The Math You Should Know : https://youtube.com/playlist?list=PLTl9hO2Oobd-_5sGLnbgE8Poer1Xjzz4h
⭕ Probability Theory for Machine Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd9bPcq0fj91Jgk_-h1H_W3V
⭕ Coding Machine Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd82vcsOnvCNzxrZOlrz3RiD
MATH COURSES (7 day free trial)
📕 Mathematics for Machine Learning: https://imp.i384100.net/MathML
📕 Calculus: https://imp.i384100.net/Calculus
📕 Statistics for Data Science: https://imp.i384100.net/AdvancedStatistics
📕 Bayesian Statistics: https://imp.i384100.net/BayesianStatistics
📕 Linear Algebra: https://imp.i384100.net/LinearAlgebra
📕 Probability: https://imp.i384100.net/Probability
OTHER RELATED COURSES (7 day free trial)
📕 ⭐ Deep Learning Specialization: https://imp.i384100.net/Deep-Learning
📕 Python for Everybody: https://imp.i384100.net/python
📕 MLOps Course: https://imp.i384100.net/MLOps
📕 Natural Language Processing (NLP): https://imp.i384100.net/NLP
📕 Machine Learning in Production: https://imp.i384100.net/MLProduction
📕 Data Science Specialization: https://imp.i384100.net/DataScience
📕 Tensorflow: https://imp.i384100.net/Tensorflow
CHAPTERS
00:00 What is the Swin Transformer?
01:30 Historical context to understand why Swin Transformers exist
04:45 Problems with vanilla transformer architectures with images
08:23 Swin Transformer architecuture at a high level
09:40 What is the “Swin Transformer Block”
10:14 Deep dive into the Swin Transformer block architecture
11:06 Windowed-Multi-head Self Attention
16:10 Shifted Window Multi-head self attention
21:43 Patch Merging
22:36 Swin Transformer + Feature Pyramid Network as backbone
23:46 Performance
24:51 Quiz Time
26:05 Summary