gwq's repositories
modified_SSD_pytorch
个人复现SSD算法所用，修改自https://github.com/amdegroot/ssd.pytorch
Yolo-Fastest
:zap: Based on yolo's ultra-lightweight universal target detection algorithm, the calculation amount is only 250mflops, the ncnn model size is only 666kb, the Raspberry Pi 3b can run up to 15fps+, and the mobile terminal can run up to 178fps+
deep_sort_pytorch
MOT tracking using deepsort and yolov3 with pytorch
easy_detection
一个简单方便的目标检测框架(PyTorch环境可直接运行，不需要cuda编译)，支持Faster_RCNN、Yolo系列(v2~v5)、EfficientDet、RetinaNet、Cascade-RCNN等经典网络。
faster-rcnn-pytorch
这是一个faster-rcnn的pytorch实现的库，可以利用voc数据集格式的数据进行训练。
I2V-GAN
ACMMM2021 paper "I2V-GAN: Unpaired Infrared-to-Visible Video Translation"
MobileNet-Yolo
MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB:fire::fire::fire:
my_yolox
this is repository of TensorRT accelerate YOLOX
OpenVINO-YOLOV4
This is implementation of YOLOv4,YOLOv4-relu,YOLOv4-tiny,YOLOv4-tiny-3l,Scaled-YOLOv4 and INT8 Quantization in OpenVINO2021.3
PaddleDetection
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
pytorch-doc-zh
Pytorch 中文文档
Pytorch-UNet
PyTorch implementation of the U-Net for image semantic segmentation with high quality images
PytorchNetHub
项目注释+论文复现+算法竞赛+Pytorch指北
ReadMeter
Read the value of the pointer meter
TensorFlow2-Detection
From this repository, you can learn some classic object detection frameworks.
unet-pytorch
这是一个unet-pytorch的源码，可以训练自己的模型
yolo_v2_pytorch
YOLO v2 pytorch implementation
YOLOv1
目前采用保持定位损失高权重的方式进行训练，Avg_Iou已达到0.72，因为定位不准的话，置信度与物体分类的计算就无从谈起。LeakyReLU替代ReLU，ReLU造成了网络退化问题，YOLO V1没有残差无法缓解退化问题。
yolov3-spp-annotations
yolov3-spp的一个中文注释版本，仅供大家参考学习！
yolov5
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
Yolov5-Deepsort
最新版本yolov5+deepsort目标检测和追踪，能够显示目标类别，支持5.0版本可训练自己数据集
yolov5-dnn-cpp-python-v2
用opencv的dnn模块做yolov5目标检测，包含C++和Python两个版本的程序，优化后的
yolov7
🔥🔥🔥🔥 YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥
yolov7-1
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
YOLOX
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
YOLOX-
:fire: :fire: :fire: YOLOX 训练自己的数据集 TensorRT加速 详细教程
yolox-pytorch
这是一个yolox-pytorch的源码，可以用于训练自己的模型。