Peijie Dong

awesome-attention-mechanism-in-cv. Awesome List of Attention Modules and Plug&Play Modules in Computer Vision

SimpleCVReproduction. Replication of simple CV Projects including attention, classification, detection, keypoint detection, etc.

Awesome-LLM-Quantization. Awesome list for LLM quantization

SimpleCVPaperReading. :smile:博客论文列表：分系列整理

Awesome-LLM-Prune. Awesome list for LLM pruning.

deep_sort_yolov3_pytorch. Replication of MOT project - DeepSort with attention blocks.

voc2007_for_yolo_torch. :punch: Prepare VOC format datasets for ultralytics/yolov3 & yolov5

Awesome-Efficient-MoE. Efficient Mixture of Experts for LLM Paper List

ultrascale-playbook-zh. UltraScale Playbook 中文版

captcha.Pytorch. 验证码识别比赛code，针对数字，大小写字母能达到97-99%的准确率

landmark_annotation. :punch: Keypoint/Landmark Annotation Software 关键点标注软件

captcha_identify.pytorch. 基于torch进行验证码识别,识别率达94%

Pruner-Zero. [ICML24] Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs

PyTorch-CIFAR-Model-Hub. Implementation of Conv-based and Vit-based networks designed for CIFAR.

timm. PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

GoodsRecognition.MindSpore. 基于MindSpore AI框架实现零售商品识别 top1方案

datawhale_cv_competition. 布匹缺陷识别练习赛

QPainter. CPP intern,Sotfware,Painter

Vision-Mamba-CIFAR10. Python

reid_for_deepsort. simple reid for deep sort

CVPR2022-NAS-competition-Track1-3th-solution. Implementation of PGONAS for CVPR22W and RD-NAS for ICASSP23

STBLLM. [ICLR25] STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs

ACBench. [ICML25] Agentic Compression Benchmark (ACBench)

darknet-loss-Drawer. This repository is developed on the basis of pyqt5, mainly through the log files generated during the running of Darknet, and then draw loss files.

faster-rcnn.Supernova. 基于faster-rcnn.pytorch改进，超新星识别比赛code

LPZero. [EMNLP24]LPZero: Language Model Zero-Cost Proxy Search from Zero

PicoNAS. Modularized NAS Framework

yolo_deep_sort_pytorch. attention, cbam, se

CUDA_NMS. Use cuda to speed up the implementation of nms algorithm

ofa-cifar. :star: Make Once for All support CIFAR10 dataset.

yolov3.keras. yolov3.keras for VOC2007

mixed_precision_imagenet_benchmark. ResNet50在ImageNet上混合精度

ClipLLM. Clipboard-Centric LLM conversation tools

lightllm-gradio. Based on LightLLM, we provide interface using Gradio. Feel free to use!

52RL. Reforcement Learning in DataWhale

simple_deep_sort. deep sort with yolov3. Modify darknet based yolov3 to pytorch based yolov3.

Mnc-javacc. Implementing the Minic compiler with javacc

ArchVizD3. zero-cost proxy visualization on NAS-Bench-201 using d3.js

AutoRF. AutoRF: Learning Receptive Fields with Spatial Pooling

MAE-CIFAR. PyTorch implementation of Masked Autoencoder on CIFAR

BitNet. Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

Paper2Blog. Convert academic paper to blog

pprp.

ChatPaper. Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文总结+润色+审稿+审稿回复

mmrazor. OpenMMLab Model Compression Toolbox and Benchmark.

Paper-Writing-Tips. MLNLP社区用来帮助大家避免论文投稿小错误的整理仓库。 Paper Writing Tips

NASLib. NASLib is a Neural Architecture Search (NAS) library for facilitating NAS research for the community by providing interfaces to several state-of-the-art NAS search spaces and optimizers.

NAS-Bench-201-refactor. Original version of NAS-Bench-201 from AngleNAS

aw_nas. aw_nas: A Modularized and Extensible NAS Framework

LMFlow. An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

Awesome-Efficient-LLM. A curated list for Efficient Large Language Models