hehewang625327 Goto Github PK

deep_sort

Simple Online Realtime Tracking with a Deep Association Metric

deep_sort_yolov3

Real-time Multi-person tracker using YOLO v3 and deep_sort with tensorflow

deep_sort_yolov3-1

yolo做行人检测+deep-sort做匹配，端对端做多目标跟踪

deepstream_python_apps

DeepStream SDK Python bindings and sample applications

deformable-convnets

Deformable Convolutional Networks

densenet

Densely Connected Convolutional Networks, In CVPR 2017 (Best Paper Award).

detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

dev-docs

服务于极市平台开发者的项目，提供SDK接口文件规范与常见问题示例代码。欢迎所有开发者一起参与示例代码编写。

dl_tools

dtfv

Fisher Vector implementation for Dense Trajectory features

ehpi_action_recognition

Simple yet efficient real-time pose based action recognition

face-tracking-usingfairmot

facial-expression-recognition

Facial-Expression-Recognition using tensorflow

fairmot

A simple baseline for one-shot multi-object tracking

fairmot_tensorrt

fall-detection

Human Fall Detection from CCTV camera feed

fall-detection-1

a very simple Fall-detection（摔倒/跌倒检测）using yolo2

fall-detection-with-cnns-and-optical-flow

Repository containing the material required to reproduce the results of the paper "Vision-Based Fall Detection with Convolutional Neural Networks"

falldatasets

junshanshipin

fast-reid

SOTA Re-identification Methods and Toolbox

faster-rcnn.pytorch

A faster pytorch implementation of faster r-cnn

fasterseg

[ICLR 2020] "FasterSeg: Searching for Faster Real-time Semantic Segmentation" by Wuyang Chen, Xinyu Gong, Xianming Liu, Qian Zhang, Yuan Li, Zhangyang Wang

fb.resnet.torch

Torch implementation of ResNet from http://arxiv.org/abs/1512.03385 and training scripts

fishervector

Improved Fisher Vector Implementation

flops-counter.pytorch

Flops counter for convolutional networks in pytorch framework

focal-loss

loss layer of implementation

focal-loss-1

Focal loss for Dense Object Detection

gesture_recognition

Improved dense trajectories for gesture/action recognition

gradient_descent_viz

interactive visualization of 5 popular gradient descent methods with step-by-step illustration and hyperparameter tuning UI

graph-template-library

GTL (Graph Template Library) is a STL based library, which provides necessary classes and algorithms for the work with graphs.