liuguoyou Goto Github PK

mobile_detect

This is a tensorflow implement mobilenetv3-ssd framework, which can be easily deployeed on both Android(MNN) and IOS(CoreML) mobile devices end to end.

mobile_phone_human_matting

human matting on mobile phone

mobilenet

This is an implementation of "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications"

mobilenet-caffe

Caffe Implementation of Google's MobileNets (v1 and v2)

mobilenetssdface

Caffe implementation of Mobilenet-SSD face detector (NCS compatible)

mobilenetv2.pytorch

72.2% MobileNetV2 1.0 model on ImageNet and a spectrum of pre-trained MobileNetV2 models

mobilenetv3-pytorch

Implementation of MobileNetV3 in pytorch

mobilenext

mobilepose-pytorch

Light-weight Single Person Pose Estimator

mobilepydnet_v2

Pydnet on mobile devices

mobilesr

mobilesr-ntire2022

Pytorch code for MobileSR: A Mobile-friendly Transformer for Efficient Image Super-Resolution

mobilestylegan.pytorch

An official implementation of MobileStyleGAN in PyTorch

mocap4face

A free, multiplatform SDK for real-time facial motion capture using blendshapes, and rigid head pose in 3D space from any RGB camera, photo, or video.

mocapnet

We present MocapNET, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance

moco

Unofficial implementation with pytorch DistributedDataParallel for "MoCo: Momentum Contrast for Unsupervised Visual Representation Learning"

moco-v3

PyTorch implementation of MoCo v3 https//arxiv.org/abs/2104.02057

model-compression

model compression based on pytorch (1、quantization: 8/4/2bits(dorefa)、ternary/binary value(twn/bnn/xnor-net)；2、 pruning: normal、regular and group convolutional channel pruning；3、 group convolution structure；4、batch-normalization folding for binary value of feature(A))

model_compression

Implementation of model compression with knowledge distilling method.

models

Models and examples built with TensorFlow

modest-museum-dataset

MOnocular Depth Estimation and SegmenTation (MODEST) Museum Dataset

modified-crunet-and-residual-attention-network.mxnet

A MXNet implementation of Modified CRUNet & Residual Attention Network

modified_refinedet

Modified RefineDet

modnet

A Trimap-Free Solution for Portrait Matting in Real Time under Changing Scenes

moire_detection

moire detection using Haar transform

moltenvk

MoltenVK is an implementation of the high-performance, industry-standard Vulkan graphics and compute API, that runs on Apple's Metal graphics framework, bringing Vulkan to iOS and macOS.

mono3d

Source code for "Mononizing Binocular Videos" (SIGGRAPH Asia 2020)

monoculardepth-inference

Inference pipeline for the CVPR paper entitled "Real-Time Monocular Depth Estimation using Synthetic Data with Domain Adaptation via Image Style Transfer."

monoculartotalcapture

Code for CVPR19 paper "Monocular Total Capture: Posing Face, Body and Hands in the Wild"

monodepth-fpn-pytorch

Single Image Depth Estimation with Feature Pyramid Network