Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/yandexdataschool/deep_vision_and_graphics
Course about deep learning for computer vision and graphics co-developed by YSDA and Skoltech.
https://github.com/yandexdataschool/deep_vision_and_graphics
computer-vision course course-materials deep-learning pytorch
Last synced: 6 days ago
JSON representation
Course about deep learning for computer vision and graphics co-developed by YSDA and Skoltech.
- Host: GitHub
- URL: https://github.com/yandexdataschool/deep_vision_and_graphics
- Owner: yandexdataschool
- License: mit
- Created: 2021-09-08T14:22:50.000Z (about 3 years ago)
- Default Branch: fall24
- Last Pushed: 2024-10-30T17:21:01.000Z (14 days ago)
- Last Synced: 2024-10-30T17:35:13.305Z (14 days ago)
- Topics: computer-vision, course, course-materials, deep-learning, pytorch
- Language: Jupyter Notebook
- Homepage:
- Size: 52.4 MB
- Stars: 301
- Watchers: 23
- Forks: 93
- Open Issues: 6
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Deep Vision and Graphics
This repo supplements course "Deep Vision and Graphics" taught at YSDA @fall'24.
The course is the successor of ["Deep Learning"](https://github.com/yandexdataschool/Practical_DL/tree/spring21/) course taught at YSDA in 2015-2021. New course focuses more on applications of deep learning for computer vision.
Lecture and seminar materials for each week are in ./week* folders. Homeworks are in ./homework* folders.
# General info
* Telegram [chat room](https://t.me/+rGY82guWzqI1YTky) (russian).
* YSDA deadlines & admin stuff can be found at the YSDA LMS (ysda students only).
* Any technical issues, ideas, bugs in course materials, contribution ideas - add an [issue](https://github.com/yandexdataschool/deep_vision_and_graphics/issues)
# Syllabus
- __week01__ Intro, recap of Neural network basics, optimization, backprop, biological networks, images, linear filtering, convolutional networks, batchnorms, augmentations
- __week02__ ConvNet architectures and how to find them, sparse convolutions in 3D, ConvNets for videos, transfer learning
- __week03__ Non-convolutional architectures: transformers (some recap of their use in NLP), mixers, FFT convolutions
- __week04__ Visualizing and understanding deep architectures, adversarial examples
- __week05__ Dense prediction: semantic segmentation, superresolution/image synthesis, perceptual losses
- __week06__ Object detection, instance/panoptic segmentation, 2D/3D human pose estimation
- __week07__ Representation learning: face recognition, verification tasks, self-supervised learning, image captioning
- __week08__ Latent models (GLO, AEs, VQ-VAE). Flow models, CLIP, DALL-E
- __week09__ Generative adversarial networks
- __week10__ Diffusion models, generative transformers
- __week11__ Shape and motion estimation: spatial transformers, optical flow, stereo, monodepth, point cloud generation, implicit and semi-implicit shape representations
- __week12__ New view synthesis: multi-plane images, neural radiance fields, mesh-based and point-based representations for NVS, neural renderers
# Contributors & course staff
Course materials and teaching performed by
- [Victor Yurchenko](https://github.com/simflin) - lectures, seminars, homeworks, admin stuff
- [Fedor Ratnikov](https://github.com/justheuristic/) - lectures, seminars, homeworks, admin staff
- [Viktoriia Checkalina](https://github.com/sayankotor/) - lectures, seminars, homeworks, admin staff
- To be continued