sieu-n Goto Github PK

3dmppe_posenet_release

Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image", ICCV 2019

awesome-gan-papers

papers and codes about GAN

awesome-modular-pytorch-lightning

LightCollections⚡️: Ready-to-use implementations such as `LightningModules` for various computer vision papers.

awesome-ocr

papers about ocr

basaran

Basaran is an open-source alternative to the OpenAI text completion API. It provides a compatible streaming API for your Hugging Face Transformers-based text generation models.

calibration-framework

Python Framework to calibrate confidence estimates of classifiers like Neural Networks

ciplab-ntire-2020

esrgan

ECCV18 Workshops - Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution. The training codes are in BasicSR.

fe-clone-coding

gptq-for-llama

4 bits quantization of LLaMA using GPTQ

koocr-tensorflow

Korean OCR based on tensorflow deep-learning.

large-scale-lm-tutorials

Large-scale language modeling tutorials with PyTorch

llm-math-benchmark

metagpt-baselines

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

overhaul-distillation

Official PyTorch implementation of "A Comprehensive Overhaul of Feature Distillation" (ICCV 2019) + wandb

pylint

It's not just a linter that annoys you!

pyserini

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

pytorch-cifar

95.47% on CIFAR10 with PyTorch

releasing-research-code

Tips for releasing research code in Machine Learning (with official NeurIPS 2020 recommendations)

repdistiller

[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods

season2-week1-team4

sieu-n.github.io

srflow

Official SRFlow training code: Super-Resolution using Normalizing Flow in PyTorch

streamlit-cloud

ultimate-sr

One-to-many Approach for Improving Super-Resolution implemented in Tensorflow 2.x

ultimate_sr

vissl

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.