ml-lab Goto Github PK

portrait-demo

Portrait Segmentation Demo

portrait_matting

Implementation of "Automatic Portrait Segmentation" and "Deep Automatic Portrait Matting" with Chainer.

pose-aligned-deep-networks

Pose Aligned Networks for Deep Attribute Modeling matlab code used for the publication here: http://arxiv.org/abs/1311.5591

pose-gan

pose-hg-train

Training and experimentation code used for "Stacked Hourglass Networks for Human Pose Estimation"

pose-interpreter-networks

Code release for "Real-Time Object Pose Estimation with Pose Interpreter Networks"

pose-residual-network

Code for 'MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network' paper

pose-tensorflow

Human Pose estimation with TensorFlow framework

pose-transfer

Code for the paper Progressive Pose Attention for Person Image Generation in CVPR19 (Oral).

pose-with-style

[SIGGRAPH Asia 2021] Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN

pose2pose

This is a pix2pix demo that learns from pose and translates this into a human. A webcam-enabled application is also provided that translates your pose to the trained pose. Everybody dance now !

posecnn

A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes

posefix_release

Official TensorFlow implementation of "PoseFix: Model-agnostic General Human Pose Refinement Network", CVPR 2019

poseflow

PoseFlow: Efficient Online Pose Tracking

posetrack-cvpr2017

poseval

Evaluation of multi-person pose estimation and tracking

posewarp-cvpr2018

posos-challenge

code for the challenge

postgresml

PostgresML is an end-to-end machine learning system. It enables you to train models and make online predictions using only SQL, without your data ever leaving your favorite database.

posture-and-fall-detection-system-using-3d-motion-sensors

This work presents a supervised learning approach for training a posture detection classifier, and implementing a fall detection system using the posture classification results as inputs with a Microsoft Kinect v2 sensor. The Kinect v2 skeleton tracking provides 3D depth coordinates for 25 body parts. We use these depth coordinates to extract seven features consisting of the height of the subject and six angles between certain body parts. These features are then fed into a fully connected neural network that outputs one of three considered postures for the subject: standing, sitting, or lying down. An average classification rate of over 99.30% for all three postures was achieved on test data consisting of multiple subjects where the subjects were not even facing the Kinect depth camera most of the time and were located in different locations. These results show the feasibility to classify human postures with the proposed setup independently of the location of the subject in the room and orientation to the 3D sensor.

ppgn

Code for paper "Plug and Play Generative Networks"

ppi-with-stacked-autoencoders

pqg-pytorch

practical_rl

A course in reinforcement learning in the wild

practical_seq2seq

A simple, minimal wrapper for tensorflow's seq2seq module, for experimenting with datasets rapidly

practicalai

A practical approach to learning machine learning.

predicting-cat-5-damage-to-buildings

predicting-nlpgt

Predicting Strategic Behavior from Free Text

prediction_gan

PyTorch Impl. of Stabilizing Adversarial Nets with Prediction Methods (https://openreview.net/pdf?id=Skj8Kag0Z)

predictron

WIP implementation of "The Predictron: End-To-End Learning and Planning" (http://arxiv.org/abs/1612.08810) in Chainer