murufeng / awesome_lightweight_networksView external linksLinks
The implementation of various lightweight networks by using PyTorch. such as：MobileNetV2，MobileNeXt，GhostNet，ParNet，MobileViT、AdderNet，ShuffleNetV1-V2，LCNet，ConvNeXt，etc. ⭐⭐⭐⭐⭐
☆907May 16, 2022Updated 3 years ago
Alternatives and similar repositories for awesome_lightweight_networks
Users that are interested in awesome_lightweight_networks are comparing it to the libraries listed below
Sorting:
- Unofficial PyTorch implementation of MobileViT based on paper "MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Trans…☆128Apr 26, 2022Updated 3 years ago
- A PyTorch implementation of "MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer"☆563Jan 16, 2022Updated 4 years ago
- Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.☆4,383Mar 15, 2025Updated 11 months ago
- [ECCV 2022] Source code of "EdgeFormer: Improving Light-weight ConvNets by Learning from Vision Transformers"☆357Dec 14, 2022Updated 3 years ago
- RepVGG: Making VGG-style ConvNets Great Again☆3,453Feb 10, 2023Updated 3 years ago
- RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization☆183Aug 15, 2023Updated 2 years ago
- ☆276Oct 6, 2022Updated 3 years ago
- 🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.…☆12,159Dec 6, 2024Updated last year
- micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantiz…☆2,271May 6, 2025Updated 9 months ago
- CVNets: A library for training computer vision networks☆1,965Oct 30, 2023Updated 2 years ago
- NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone…☆6,159Aug 8, 2024Updated last year
- 🔥🔥🔥 专注于YOLO11，YOLOv8、TYOLOv12、YOLOv10、RT-DETR、YOLOv7、YOLOv5改进模型，Support to improve backbone, neck, head, loss, IoU, NMS and other modu…☆2,913Dec 15, 2025Updated 2 months ago
- The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights --…☆36,351Updated this week
- [CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.☆3,255Sep 7, 2025Updated 5 months ago
- Official repo of RepOptimizers and RepOpt-VGG☆268Feb 10, 2023Updated 3 years ago
- 🍅🍅🍅YOLOv5-Lite: Evolved from yolov5 and the size of model is only 900+kb (int8) and 1.7M (fp16). Reach 15 FPS on the Raspberry Pi 4B~☆2,470Jun 22, 2024Updated last year
- YOLOv5 Series Multi-backbone(TPH-YOLOv5, Ghostnet, ShuffleNetv2, Mobilenetv3Small, EfficientNetLite, PP-LCNet, SwinTransformer YOLO), Mod…☆1,019Apr 29, 2022Updated 3 years ago
- Pytorch implementation of cnn network☆2,053Oct 11, 2025Updated 4 months ago
- Pytorch and ncnn implementation of PPYOLOE、YOLOX、PPYOLO、PPYOLOv2、PicoDet and so on.☆309Jul 20, 2025Updated 6 months ago
- ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting (ICCV 2021)☆300Dec 1, 2022Updated 3 years ago
- Summary of related papers on visual attention. Related code will be released based on Jittor gradually.☆2,847Oct 20, 2024Updated last year
- [CVPR 2023] Code for PConv and FasterNet☆811May 16, 2023Updated 2 years ago
- 🛠A lite C++ AI toolkit: 100+ models with MNN, ORT and TRT, including Det, Seg, Stable-Diffusion, Face-Fusion, etc.🎉☆4,372Jan 18, 2026Updated 3 weeks ago
- ☆338Jul 18, 2022Updated 3 years ago
- PyTorch implementation of PP-LCNet☆81Oct 21, 2023Updated 2 years ago
- 🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥☆3,121Nov 18, 2023Updated 2 years ago
- Based on yolo's ultra-lightweight universal target detection algorithm, the calculation amount is only 250mflops, the ncnn model size is…☆2,088Aug 11, 2021Updated 4 years ago
- Code release for ConvNeXt model☆6,292Jan 8, 2023Updated 3 years ago
- Code for our CVPR2021 paper coordinate attention☆1,123Jun 8, 2021Updated 4 years ago
- Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Py…☆24,993Updated this week
- A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by …☆850Mar 16, 2023Updated 2 years ago
- YOLOv6: a single-stage object detection framework dedicated to industrial applications.☆5,874Aug 7, 2024Updated last year
- YOLOv3、YOLOv4、YOLOv5、YOLOv5-Lite、YOLOv6-v1、YOLOv6-v2、YOLOv7、YOLOX、YOLOX-Lite、PP-YOLOE、PP-PicoDet-Plus、YOLO-Fastest v2、FastestDet、YOLOv5-S…☆764Oct 25, 2022Updated 3 years ago
- This repository contains the official implementation of the research paper, "An Improved One millisecond Mobile Backbone" CVPR 2023.☆819Jul 25, 2022Updated 3 years ago
- Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs (CVPR 2022)☆939Apr 24, 2024Updated last year
- This is a collection of our NAS and Vision Transformer work.☆1,826Jul 25, 2024Updated last year
- OpenMMLab Model Compression Toolbox and Benchmark.☆1,661Jun 11, 2024Updated last year
- YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documenta…☆10,328Jun 8, 2025Updated 8 months ago
- yolov3 with mobilenet v2 and ASFF☆1,083Jul 24, 2021Updated 4 years ago