sungjun lee's repositories
vision-transformer-tf
Reproduction of Vision Transformer in Tensorflow2. Train from scratch and Finetune.
Big-Interleaved-Dataset
Big-Interleaved-Dataset
ChatGPT
Reverse engineered ChatGPT API
coyo-dataset
COYO-700M: Large-scale Image-Text Pair Dataset
cs231n_assignment
cs231n assignment
datatrove
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
generative-inpainting-pytorch
A PyTorch reimplementation for paper Generative Image Inpainting with Contextual Attention (https://arxiv.org/abs/1801.07892)
GL_Image_Inapinting_pytorch
Implementation of "Globally and Locally Consistent Image Completion"
img2dataset
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
laion-datasets
Description and pointers of laion datasets
mcdowell-cv
A Nice-looking CV template made into LaTeX
newspaper4k
📰 Newspaper4k a fork of the beloved Newspaper3k. Extraction of articles, titles, and metadata from news websites.
PyTorch-Universal-Docker-Template
Template repository to build PyTorch projects from source on any version of PyTorch/CUDA/cuDNN.
s3fs
S3 Filesystem
so-vits-svc-5.0
Core Engine of Singing Voice Conversion & Singing Voice Clone
text-clustering
Easily embed, cluster and semantically label text datasets
webdataset
A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.