A lightweight Stacked Hourglass Network for Human Pose Estimation arxiv
Code based on Pytorch implementation of Stacked Hourglass paper here
Environment setup
conda env create -f environment.yml
conda activate hourglass
pip install -r requirements.txt
For training and evaluation
Set the path to images and checkpoint in train.sh and eval.sh
The model is setup using config.py. The best model is as described in poster below.
