Daniil-Osokin/fully-learnable-group-convolution.pytorch

Stars
33
Rank 783,877 (Top 16 %)
Language
Python
Created over 5 years ago
Updated over 4 years ago

Daniil-Osokin/fully-learnable-group-convolution.pytorch

Daniil-Osokin

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Implementation of "Fully Learnable Group Convolution for Acceleration of Deep Neural Networks", CVPR'19

lightweight-human-pose-estimation.pytorch

Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.

lightweight-human-pose-estimation-3d-demo.pytorch

Real-time 3D multi-person pose estimation demo in PyTorch. OpenVINO backend can be used for fast inference on CPU.

gccpm-look-into-person-cvpr19.pytorch

Fast and accurate single-person pose estimation, ranked 10th at CVPR'19 LIP challenge. Contains implementation of "Global Context for Convolutional Pose Machines" paper.

projects

Repository for all side projects