sungjun lee's repositories

vision-transformer-tf

Reproduction of Vision Transformer in Tensorflow2. Train from scratch and Finetune.

Big-Interleaved-Dataset

Big-Interleaved-Dataset

License:Apache-2.0Stargazers:0Issues:0Issues:0

ChatGPT

Reverse engineered ChatGPT API

Language:PythonLicense:GPL-2.0Stargazers:0Issues:0Issues:0
License:Apache-2.0Stargazers:0Issues:0Issues:0

coyo-dataset

COYO-700M: Large-scale Image-Text Pair Dataset

Language:PythonStargazers:0Issues:1Issues:0

cs231n_assignment

cs231n assignment

Language:Jupyter NotebookStargazers:0Issues:1Issues:0

datasets

TFDS is a collection of datasets ready to use with TensorFlow, Jax, ...

Language:PythonLicense:Apache-2.0Stargazers:0Issues:1Issues:0

datatrove

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0
Language:PythonStargazers:0Issues:2Issues:0

generative-inpainting-pytorch

A PyTorch reimplementation for paper Generative Image Inpainting with Contextual Attention (https://arxiv.org/abs/1801.07892)

Language:PythonLicense:MITStargazers:0Issues:1Issues:0

GL_Image_Inapinting_pytorch

Implementation of "Globally and Locally Consistent Image Completion"

Language:PythonLicense:GPL-3.0Stargazers:0Issues:1Issues:0
Language:PythonStargazers:0Issues:2Issues:0

img2dataset

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

Language:PythonLicense:MITStargazers:0Issues:1Issues:0
Stargazers:0Issues:2Issues:0

KoBigBird

🦅 Pretrained BigBird Model for Korean (up to 4096 tokens)

Language:PythonLicense:Apache-2.0Stargazers:0Issues:1Issues:0

laion-datasets

Description and pointers of laion datasets

Language:HTMLLicense:MITStargazers:0Issues:1Issues:0

mcdowell-cv

A Nice-looking CV template made into LaTeX

Language:TeXLicense:MITStargazers:0Issues:1Issues:0

newspaper4k

📰 Newspaper4k a fork of the beloved Newspaper3k. Extraction of articles, titles, and metadata from news websites.

Language:HTMLLicense:MITStargazers:0Issues:0Issues:0

PyTorch-Universal-Docker-Template

Template repository to build PyTorch projects from source on any version of PyTorch/CUDA/cuDNN.

Language:DockerfileStargazers:0Issues:1Issues:0

s3fs

S3 Filesystem

Language:PythonLicense:BSD-3-ClauseStargazers:0Issues:0Issues:0

so-vits-svc-5.0

Core Engine of Singing Voice Conversion & Singing Voice Clone

License:MITStargazers:0Issues:0Issues:0
Language:PythonStargazers:0Issues:2Issues:0

text-clustering

Easily embed, cluster and semantically label text datasets

License:Apache-2.0Stargazers:0Issues:0Issues:0
Language:PythonStargazers:0Issues:2Issues:0
Language:PythonStargazers:0Issues:2Issues:0
Language:PythonStargazers:0Issues:2Issues:0
Language:PythonStargazers:0Issues:2Issues:0
Language:PythonStargazers:0Issues:2Issues:0

webdataset

A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

Language:Jupyter NotebookLicense:BSD-3-ClauseStargazers:0Issues:1Issues:0