mehtadushy Goto Github PK

aisg-ccss

Automatically exported from code.google.com/p/aisg-ccss

assorted-code-dump

Collection of scripts and codes and utilities

deepnetstuff

Bits and bobs from various deepnet experiments

ffnet

graphicsexperiments

Experiments with OpenGL

higher-hrnet-human-pose-estimation

Higher-Resolution Networks (HigherHRNets) for Human Pose Estimation

human-motion-synthesis

human-renderer

Rendering human poses from sequential data using Python3 and MakeHuman

mehtadushy.github.io

Some computer vision and machine learning stuff

opengl-experiments

poseestimation

Experimenting with some ways of solving the 3D-2D pose estimation problem. Uses Eigen for linear algebra

pupiltracking

Experiments with pupil tracking

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

pytorch-image-models

PyTorch image models, scripts, pretrained weights -- (SE)ResNet/ResNeXT, DPN, EfficientNet, MixNet, MobileNet-V3/V2, MNASNet, Single-Path NAS, FBNet, and more

selecsls-pytorch

Reference ImageNet implementation of SelecSLS CNN architecture proposed in the SIGGRAPH 2020 paper "XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera". The repository also includes code for pruning the model based on implicit sparsity emerging from adaptive gradient descent methods, as detailed in the CVPR 2019 paper "On implicit filter level sparsity in Convolutional Neural Networks".

selecsls-pytorch-retinanet

Pytorch implementation of RetinaNet object detection with SelecSLS backbone.

spatialcontext

Master's Thesis: "Encoding Spatial Context in Local Image Descriptors"

tf-simplehumanpose

TensorFlow implementation of "Simple Baselines for Human Pose Estimation and Tracking", ECCV 2018

visdat13

Visualisation and Data Analysis

xml3d-blender-exporter

Blender web-exporter for xml3d.js (beta)