surdarla

Junsu Kim's starred repositories

fastapi

FastAPI framework, high performance, easy to learn, fast to code, ready for production

Language:PythonMIT72276 678 3408

manim

Animation engine for explanatory math videos

Language:PythonMIT58898 881 1122

marktext

📝A simple and elegant markdown editor, available for Linux, macOS and Windows.

Language:JavaScriptMIT45173 413 2730

awesome-deep-learning

A curated list of awesome Deep Learning tutorials, projects and communities.

23096 1211 20

vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Language:PythonMIT18443 144 257

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

Language:PythonApache-2.011836 136 194

fiftyone

The open-source tool for building high-quality datasets and computer vision models

Language:PythonApache-2.06869 53 1457

PyTorch-VAE

A Collection of Variational Autoencoders (VAE) in PyTorch.

Language:PythonApache-2.06130 43 81

videos

Code for the manim-generated scenes used in 3blue1brown videos

Language:Python5702 110 56

tsai

Time series Timeseries Deep Learning Machine Learning Python Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai

Language:Jupyter NotebookApache-2.04834 62 647

github-profile-achievements

A collection listing all Achievements available on the GitHub profile 🏆

Language:MarkdownMIT4619 59 122

BigGAN-PyTorch

The author's officially unofficial PyTorch BigGAN implementation.

Language:PythonMIT2814 52 84

dlbook_notation

LaTeX files for the Deep Learning book notation

Language:TeX1611 70 3

Megatron-DeepSpeed

Ongoing research training transformer language models at scale, including: BERT & GPT-2

Language:PythonNOASSERTION1259 24 143

capsule-render

🌈 Dynamic Coloful Image Render

Language:JavaScriptMIT1158 7 9

wit

WIT (Wikipedia-based Image Text) Dataset is a large multimodal multilingual dataset comprising 37M+ image-text sets with 11M+ unique images across 100+ languages.

NOASSERTION964 39 6