Stars
TensorRT implementation of Depth-Anything V1, V2
[ECCV 2022] Source code of "EdgeFormer: Improving Light-weight ConvNets by Learning from Vision Transformers"
A PyTorch implementation of "MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer"
test tensorrt c++/python api, c++/python plugins.
目标检测数据集制作:VOC,COCO,YOLO等常用数据集格式的制作和互相转换脚本
This repo is the codebase for our team to participate in DOTA related competitions, including rotation and horizontal detection.
Code for "Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views" (CVPR 2019, T-PAMI 2021)
DenseNet Pytorch DenseNet121 DenseNet169 DenseNet201 DenseNet161
Ultra Fast Structure-aware Deep Lane Detection (ECCV 2020)
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
Object detection, 3D detection, and pose estimation using center point detection:
ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
FasterRCNN is implemented in VGG, ResNet and FPN base.
Deformable Convolutional Networks
Yolov5 deepsort inference，使用YOLOv5+Deepsort实现车辆行人追踪和计数，代码封装成一个Detector类，更容易嵌入到自己的项目中
Feature Pyramid Network + SSD (loss function is same as SSD, so it's not RetinaNet)
Qt编写的一些开源的demo，预计会有100多个，一直持续更新完善，代码简洁易懂注释详细，每个都是独立项目，非常适合初学者，代码随意传播使用，拒绝打赏和捐赠，欢迎留言评论！公众号：Qt实战/Qt入门和进阶/Qt教程