https://github.com/catalyst-team/dl-course
Deep Learning with Catalyst
https://github.com/catalyst-team/dl-course
Last synced: over 1 year ago
JSON representation
Deep Learning with Catalyst
- Host: GitHub
- URL: https://github.com/catalyst-team/dl-course
- Owner: catalyst-team
- License: mit
- Created: 2020-09-12T08:21:48.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2021-09-28T13:25:34.000Z (almost 5 years ago)
- Last Synced: 2024-10-29T18:49:46.656Z (over 1 year ago)
- Language: Jupyter Notebook
- Size: 1.24 MB
- Stars: 290
- Watchers: 23
- Forks: 71
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Deep Learning with Catalyst [](https://stepik.org/course/83344/syllabus) [](https://join.slack.com/t/catalyst-team-devs/shared_invite/zt-d9miirnn-z86oKDzFMKlMG4fgFdZafw)
[](https://github.com/catalyst-team/dl-course)
This is an open deep learning course made by [Deep Learning School](https://dlschool.org), [Tinkoff](https://tinkoff.ru), and [Catalyst team](https://github.com/catalyst-team).
Lectures and practice notebooks located in ```./week*``` folders. Homeworks are in ```./homework*``` folders.
> *Note: the course is under update:
> weeks with colab barge are ready to go, weeks with [WIP] label are still in progress.
> You could use the `v20.12` branch for the earlier version of the full course.*
## Syllabus
- [](https://colab.research.google.com/github/catalyst-team/dl-course/blob/master/week-01/seminar.ipynb) week 1: Deep learning intro
- Deep learning – introduction, backpropagation algorithm. Optimization methods.
- Neural Network in numpy.
- [](https://colab.research.google.com/github/catalyst-team/dl-course/blob/master/week-02/seminar.ipynb) week 2: Deep learning frameworks
- Regularization methods and deep learning frameworks.
- Pytorch basics & extras.
- [](https://colab.research.google.com/github/catalyst-team/dl-course/blob/master/week-03/seminar.ipynb) week 3: Convolutional Neural Network
- CNN. Model Zoo.
- Convolutional kernels. ResNet. Simple Noise Attack.
- [](https://colab.research.google.com/github/catalyst-team/dl-course/blob/master/week-04/seminar_done.ipynb) week 4: Object Detection, Image Segmentation
- Object Detection. (One, Two)-Stage methods. Anchors.
- Image Segmentation. Up-scaling. FCN, U-net, FPN. DeepMask.
- [](https://colab.research.google.com/github/catalyst-team/dl-course/blob/master/week-05/seminar_done.ipynb) week 5: Metric Learning
- Metric Learning. Contrastive and Triplet Loss. Samplers.
- Cross Entropy Loss modifications. SphereFace, CosFace, ArcFace.
- [](https://colab.research.google.com/github/catalyst-team/dl-course/blob/master/week-06/seminar_done.ipynb) week 6: Autoencoders
- AutoEncoders. Denoise, Sparse, Variational.
- Generative Models. Autoregressive models.
- [](https://colab.research.google.com/github/catalyst-team/dl-course/blob/master/week-07/seminar_done.ipynb) week 7: Generative Adversarial Models
- Generative Adversarial Networks. VAE-GAN. AAE.
- Energy based model.
- [](https://colab.research.google.com/github/catalyst-team/dl-course/blob/master/week-08/seminar_done.ipynb) week 8: Natural Language Processing
- Embeddings.
- RNN. LSTM, GRU.
- [](https://colab.research.google.com/github/catalyst-team/dl-course/blob/master/week-09/seminar_done.ipynb) week 9: Attention and transformer model
- Attention Mechanism.
- Transformer Model.
- [](https://colab.research.google.com/github/catalyst-team/dl-course/blob/master/week-10/seminar_done.ipynb) week 10: Transfer Learning in NLP
- Pretrained Transformers. BERT. GPT.
- Data Augmentation in Texts. Domain Adaptation.
- [](https://colab.research.google.com/github/catalyst-team/dl-course/blob/master/week-11/seminar_done.ipynb) week 11: Recommender Systems
- Collaborative Filtering. FunkSVD.
- Neural Collaborative Filtering.
- week 12: Reinforcement Learning for RecSys
- [](https://colab.research.google.com/github/catalyst-team/dl-course/blob/master/week-12/Catalyst_RL_DQN_done.ipynb) DQN Algorithm.
- [](https://colab.research.google.com/github/catalyst-team/dl-course/blob/master/week-12/Catalyst_RL_DDPG_done.ipynb) DDPG Algorithm.
- [](https://colab.research.google.com/github/catalyst-team/dl-course/blob/master/week-12/Catalyst_RL_RecSim_done.ipynb) RecSim with Wolpertinger.
- *[WIP] week 13: Extras*
- Research & Deploy.
- Config API. Reaction.
## Environment
### Anaconda setup
```bash
# setup - env
conda create -n catalyst-dl python=3.7 anaconda
source activate catalyst-dl
conda remove nb_conda_kernels -y
conda install -c conda-forge nb_conda_kernels -y
conda install notebook jupyter nb_conda -y
conda remove nbpresent -y
# setup - jupyter
jupyter notebook password
# jupyter run
jupyter notebook --no-browser --ip 0.0.0.0 --port 8888
```
### Requirements
```bash
pip install -U catalyst==21.04.2 torch==1.8.0 albumentations==0.5.0
```
## Course staff & contributors
- [@AlexeySh](https://github.com/AlekseySh)
- [@artek0chumak](https://github.com/artek0chumak)
- [@elephantmipt](https://github.com/elephantmipt)
- [@Inkln](https://github.com/Inkln)
- [@Fulldis](https://github.com/Fulldis)
- [@lordofprograms](https://github.com/lordofprograms)
- [@Scitator](https://github.com/Scitator)
- [@zelcookie](https://github.com/zelcookie)