This repository contains the official implementation of the research paper, "An Improved One millisecond Mobile Backbone" CVPR 2023.
☆821Jul 25, 2022Updated 3 years ago
Alternatives and similar repositories for ml-mobileone
Users that are interested in ml-mobileone are comparing it to the libraries listed below
Sorting:
- An Improved One millisecond Mobile Backbone☆147Aug 20, 2022Updated 3 years ago
- A PyTorch implementation of MobileOne☆82Jul 21, 2022Updated 3 years ago
- CVNets: A library for training computer vision networks☆1,966Oct 30, 2023Updated 2 years ago
- This repository contains the official implementation of the research paper, "FastViT: A Fast Hybrid Vision Transformer using Structural R…☆1,991Nov 30, 2023Updated 2 years ago
- RepViT: Revisiting Mobile CNN From ViT Perspective [CVPR 2024] and RepViT-SAM: Towards Real-Time Segmenting Anything☆1,075Jun 14, 2024Updated last year
- RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization☆182Aug 15, 2023Updated 2 years ago
- RepVGG: Making VGG-style ConvNets Great Again☆3,464Feb 10, 2023Updated 3 years ago
- Official repo of RepOptimizers and RepOpt-VGG☆268Feb 10, 2023Updated 3 years ago
- EfficientFormerV2 [ICCV 2023] & EfficientFormer [NeurIPs 2022]☆1,111Aug 13, 2023Updated 2 years ago
- Mobile vision models and code☆918Feb 11, 2026Updated last month
- [CVPR 2023] Code for PConv and FasterNet☆819May 16, 2023Updated 2 years ago
- [ICCV - 2023] Official repository of paper SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applic…☆313Jul 18, 2025Updated 8 months ago
- [ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention☆910Jul 22, 2025Updated 8 months ago
- Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.☆4,393Mar 15, 2025Updated last year
- ☆68Mar 19, 2024Updated 2 years ago
- Code release for ConvNeXt model☆6,319Jan 8, 2023Updated 3 years ago
- ☆821Oct 19, 2023Updated 2 years ago
- This repository contains the official implementation of the research papers, "MobileCLIP" CVPR 2024 and "MobileCLIP2" TMLR August 2025☆1,461Oct 9, 2025Updated 5 months ago
- This is an official pytorch implementation of Lite-HRNet: A Lightweight High-Resolution Network.☆900Jun 3, 2022Updated 3 years ago
- The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights --…☆36,504Mar 13, 2026Updated last week
- [CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.☆3,267Sep 7, 2025Updated 6 months ago
- Efficient vision foundation models for high-resolution generation and perception.☆3,265Sep 5, 2025Updated 6 months ago
- NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone…☆6,176Aug 8, 2024Updated last year
- This is a collection of our NAS and Vision Transformer work.☆1,824Jul 25, 2024Updated last year
- Simplify your onnx model☆4,309Feb 26, 2026Updated 3 weeks ago
- ☆23Sep 1, 2022Updated 3 years ago
- ☆276Oct 6, 2022Updated 3 years ago
- ☆587Jul 23, 2023Updated 2 years ago
- [ECCV 2022] Source code of "EdgeFormer: Improving Light-weight ConvNets by Learning from Vision Transformers"☆357Dec 14, 2022Updated 3 years ago
- 🛠A lite C++ AI toolkit: 100+ models with MNN, ORT and TRT, including Det, Seg, Stable-Diffusion, Face-Fusion, etc.🎉☆4,387Feb 25, 2026Updated 3 weeks ago
- [ECCV 2022] EdgeViT: Competing Light-weight CNNs on Mobile Devices with Vision Transformers☆117Mar 14, 2023Updated 3 years ago
- YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documenta…☆10,376Jun 8, 2025Updated 9 months ago
- YOLOv6: a single-stage object detection framework dedicated to industrial applications.☆5,875Aug 7, 2024Updated last year
- This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!☆5,651Dec 19, 2025Updated 3 months ago
- ☆371Nov 3, 2023Updated 2 years ago
- AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.☆2,566Mar 14, 2026Updated last week
- ☆338Jul 18, 2022Updated 3 years ago
- Code release for ConvNeXt V2 model☆1,991Aug 14, 2024Updated last year
- A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by …☆854Mar 16, 2023Updated 3 years ago