yoloonme Goto Github PK

aspp_depth

基于pytorch框架的无监督单目图像深度估计算法，在Monodepth2基础上改进了网络框架以及训练算法，未经本人禁止转载或商用，谢谢合作！

cameracalibration

Python&OpenCV实现单目相机标定和双目相机标定

coordattention

Code for our CVPR2021 paper coordinate attention

data-augmentation

Data Augmentation for Object Detection with Python and OpenCV

data_augmentation_zoo_for_object_detection

Includes: Learning data augmentation strategies for object detection | GridMask data augmentation | Augmentation for small object detection in Numpy. Use RetinaNet with ResNet-18 to test these methods on VOC and KITTI.

ema-attention-module

Implementation Code for the ICCASSP 2023 paper " Efficient Multi-Scale Attention Module with Cross-Spatial Learning" and is available at: https://arxiv.org/abs/2305.13563v2

face-detector-1mb-with-landmark

1M人脸检测模型(含关键点)

face_classification

Real-time face detection and emotion/gender classification using fer2013/imdb datasets with a keras CNN model and openCV.

falldetection_openpifpaf

Fall Detection using OpenPifPaf's Human Pose Estimation model

hybirdsort

Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking

insight_face_pro

tf 和 mxnet 的 insightface 人脸识别项目

insightface

State-of-the-art 2D and 3D Face Analysis Project

labelme2coco-keypoints

Tool to convert all labelme keypoints file to one single coco keypoints file

labelme2coco_keypoints

Convert labelme format keypoints .json to MSCOCO format keypoints for human detection

mobilenet-mnn

MobileNet训练、测试以及转换为MNN

mobilenetv2-yolov3

yolov3 with mobilenetv2 and efficientnet

mobilenetv2.pytorch

72.8% MobileNetV2 1.0 model on ImageNet and a spectrum of pre-trained MobileNetV2 models

monodepth2

[ICCV 2019] Monocular depth estimation from a single image

peppa-facial-landmark-pytorch

Facial Landmark Detection based on PyTorch

person_search

Just a demo base on YOLO and ReId

pytorch-cifar

95.47% on CIFAR10 with PyTorch

pytorch-image-models

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

pytorch_face_landmark

Fast and accurate face landmark detection library using PyTorch; Support 68-point semi-frontal and 39-point profile landmark detection; Support both coordinate-based and heatmap-based inference; Up to 100 FPS landmark inference speed with SOTA face detector on CPU.

rtm3d

The official PyTorch Implementation of RTM3D and KM3D for Monocular 3D Object Detection

rtm3d-1

Perform 3d object detection base on anchor free rtm3d(master), somke(somke)

smoke

SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation

srs

SRS is a simple, high efficiency and realtime video server, supports RTMP, WebRTC, HLS, HTTP-FLV, SRT, MPEG-DASH and GB28181.

test_websocket

tornado_websocket_pratice

towsclient