Stars
🚀🚀🚀 A collection of some awesome public YOLO object detection series projects and the related object detection datasets.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Run Segment Anything Model 2 on a live video stream
High-resolution models for human tasks.
Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
Inpaint anything using Segment Anything and inpainting models.
RobustSAM: Segment Anything Robustly on Degraded Images (CVPR 2024 Highlight)
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
😎 A Collection of Awesome NCNN-based Projects
a Android demo of depth_anything_v1 and depth_anything_v2
Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation
EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
A central hub for gathering and showcasing amazing projects that extend OpenMMLab with SAM and other exciting features.
Code for DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning
A curated list of awesome self-supervised methods
Codebase for Image Classification Research, written in PyTorch.
implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)
The training program for libfacedetection for face detection and 5-landmark detection.
The minimal opencv for Android, iOS, ARM Linux, Windows, Linux, MacOS, HarmonyOS, WebAssembly, watchOS, tvOS, visionOS
Slimmable Networks, AutoSlim, and Beyond, ICLR 2019, and ICCV 2019
End-to-End Object Detection with Fully Convolutional Network
Retinaface get 80.99% in widerface hard val using mobilenet0.25.
Darknet2ncnn converts the darknet model to the ncnn model
yolov3 yolov4 channel and layer pruning, Knowledge Distillation 层剪枝，通道剪枝，知识蒸馏
geoffzhang / pycls
Forked from facebookresearch/pyclsCodebase for Image Classification Research, written in PyTorch.
A paper list of object detection using deep learning.
SOGNet: Scene Overlap Graph Network for Panoptic Segmentation
Implementation EfficientDet: Scalable and Efficient Object Detection in PyTorch
OPT v2 "Gnocchi" - adding object tracking and pose recognition