cbn001012

Real-ESRGAN

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

DeepClustering

Methods and Implements of Deep Clustering

awesome-machine-learning-1

Learning Resources And Links Of Machine Learning（updating）

awesome-machine-learning-1

Learning Resources And Links Of Machine Learning（updating）

EDA_NLP_for_Chinese

An implement of the paper of EDA for Chinese corpus.中文语料的EDA数据增强工具。NLP数据增强。论文阅读笔记。

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

TinySAM

Official PyTorch implementation of "TinySAM: Pushing the Envelope for Efficient Segment Anything Model"

bert_score

BERT score for text generation

SAM_WSSS

SAM Enhance Mask Quality for WSSS: This repository provides tools for generating, evaluating, and visualizing enhanced pseudo masks for Weakly Supervised Semantic Segmentation (WSSS) using the Segment Anything Model (SAM).

slowllama

Finetune llama2-70b and codellama on MacBook Air without quantization

FINCH-Clustering

Source Code for FINCH Clustering Algorithm

text-clustering

Easily embed, cluster and semantically label text datasets

code-bert-score

CodeBERTScore: an automatic metric for code generation, based on BERTScore

few-shot-clustering

BERT-pytorch

Google AI 2018 BERT pytorch implementation

FMA-WSSS

This repo is a implementation of the Foundation Model Assisted Weakly Supervised Semantic Segmentation. The code is developed based on the Pytorch framework.

eda_nlp

Data augmentation for NLP, presented at EMNLP 2019

Geo-Hgan-Unsupervised-anomaly-detection-in-geochemical-data-via-latent-space-learning

Geo-Hgan: Unsupervised anomaly detection in geochemical data via latent space learning

codellama

Inference code for CodeLlama models

Lbl2Vec

Lbl2Vec learns jointly embedded label, document and word vectors to retrieve documents with predefined topics from an unlabeled document corpus.

trulens

Evaluation and Tracking for LLM Experiments

app-builder

appbuilder-sdk, 千帆AppBuilder-SDK帮助开发者灵活、快速的搭建AI原生应用

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

CNSPN

code of CNSPN

LOCATION-SENSITIVE-LOCAL-PROTOTYPE-NETWORK

For ISBI 2021 paper "A LOCATION-SENSITIVE LOCAL PROTOTYPE NETWORK FOR FEW-SHOT MEDICAL IMAGE SEGMENTATION"

PANet

Code for our ICCV 2019 paper PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment

CCAM

[CVPR 2022] C2AM: Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation

Swin-Transformer

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

Cherry_LLM

[NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other models

Superfiltering

[ACL'24] Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning