Simple Keypoints

Description

Author： @2120140200@mail.nankai.edu.cn

It is a simple keypoints detector model. The model predict a score heatmap and an encoded location map. The result in wflw achieves 3.94 NME.

Usage

Prerequisites

• Python 3.7
• PyTorch 1.6 or higher
• MIM v0.33 or higher
• MMPose v1.0.0rc0 or higher

All the commands below rely on the correct configuration of PYTHONPATH, which should point to the project's directory so that Python can locate the module files. In example_project/ root directory, run the following line to add the current directory to PYTHONPATH:

export PYTHONPATH=`pwd`:$PYTHONPATH

Data Preparation

Prepare the COCO dataset according to the instruction.

Training commands

To train with single GPU:

mim train mmpose configs/td-hm_hrnetv2-w18_skps-1xb64-80e_wflw-256x256.py

To train with multiple GPUs:

mim train mmpose configs/td-hm_hrnetv2-w18_skps-1xb64-80e_wflw-256x256.py --launcher pytorch --gpus 8

To train with multiple GPUs by slurm:

mim train mmpose configs/td-hm_hrnetv2-w18_skps-1xb64-80e_wflw-256x256.py --launcher slurm \
    --gpus 16 --gpus-per-node 8 --partition $PARTITION

Testing commands

To test with single GPU:

mim test mmpose configs/td-hm_hrnetv2-w18_skps-1xb64-80e_wflw-256x256.py -C $CHECKPOINT

To test with multiple GPUs:

mim test mmpose configs/td-hm_hrnetv2-w18_skps-1xb64-80e_wflw-256x256.py -C $CHECKPOINT --launcher pytorch --gpus 8

To test with multiple GPUs by slurm:

mim test mmpose configs/td-hm_hrnetv2-w18_skps-1xb64-80e_wflw-256x256.py -C $CHECKPOINT --launcher slurm \
    --gpus 16 --gpus-per-node 8 --partition $PARTITION

Results

WFLW

Arch	Input Size	NMEtest	NMEpose	NMEillumination	NMEocclusion	NMEblur	NMEmakeup	NMEexpression	ckpt	log
skps	256x256	3.88	6.60	3.81	4.57	4.44	3.75	4.13	ckpt	log

COFW

Arch	Input Size	NME	ckpt	log
skps	256x256	3.20	ckpt	log