moyans Goto Github PK

reid-strong-baseline

Bag of Tricks and A Strong Baseline for Deep Person Re-identification

rfsong-779

重新设计的RFBNet300,模型参数量只有0.99MB，AP达到0.78，200FPS

scene-text-image-transformer

Scene Text Image Transformer

segment-anything-hu-po

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

segmentron

Support PointRend, Fast_SCNN, HRNet, Deeplabv3_plus(xception, resnet, mobilenet), ContextNet, FPENet, DABNet, EdaNet, ENet, Espnetv2, RefineNet, UNet, DANet, HRNet, DFANet, HardNet, LedNet, OCNet, EncNet, DuNet, CGNet, CCNet, BiSeNet, PSPNet, ICNet, FCN, deeplab)

ssd_mobiledet

目标检测模型 SSD MobileDet 训练与部署

stable-diffusion-webui

Stable Diffusion web UI

tablecell

在TableBank的基础上，进一步标注到单元格精度，利用目标检测/分割实现单元格定位。

third_party

Third-party source packages that are modified for use in Triton.

towards-realtime-mot

Joint Detection and Embedding for fast multi-object tracking

transformer-ocr

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

triton-ensemble-for-bert

This repository contains an ensemble for serving Bert with triton

triton-inference-server

The Triton Inference Server provides a cloud inferencing solution optimized for NVIDIA GPUs.

udop

Custom Implementation of UDOP based on T5 Model

ultra-light-fast-generic-face-detector-1mb

💎1MB lightweight face detection model (1MB轻量级人脸检测模型)

vgg-or-mobilenet-ssd

Caffe implementation of Google VGG/MobileNet/ShuffleNet SSD detection network. Ref: (https://github.com/chuanqi305/MobileNet-SSD) (https://github.com/weiliu89/caffe) SSD QQ交流群：581437405

wide-residual-networks

3.8% and 18.3% on CIFAR-10 and CIFAR-100

yolov3-channel-and-layer-pruning

yolov3 channel and layer pruning, Knowledge Distillation 层剪枝，通道剪枝，知识蒸馏

yolov3-channel-pruning

yolov3-model-pruning

对 YOLOv3 做模型剪枝（network slimming），对于 oxford hand 数据集（因项目需要），模型剪枝后的参数量减少 80%，Infer 的速度达到原来 2 倍，mAP 基本不变

yolov3-network-slimming

yolov3 network slimming剪枝的一种实现

yolov5-rt-stack

yolort / yet another yolov5, with its runtime stack for libtorch, onnx, tvm, ncnn and specialized accelerators.

yolov5prune

yolov5s_android

Run yolov5s on Android device!

zcls2

More Faster Object Classification Training Framework

zqcnn

一款比mini-caffe更快的Forward库，觉得好用请点星啊，400星公布快速人脸检测模型，500星公布106点landmark，600星公布人头检测模型，700星公布人脸检测套餐（六种pnet,两种rnet随意混合使用满足各种速度/精度要求），800星公布更准的106点模型