pytorch_pose_proposal_network

Pytorch implementation of pose proposal network

Introduction

We train the network on MPII human pose dataset but don't evaluate the performance. I don't think it can match the performance mentioned in paper due to some problems(see below).

Requirements

pytorch 0.4.1
opencv
numpy
tensorboardX

Demo

demo1 demo2 demo3

Speed

The speed depend on numbers of person. More persons there are, a little slower it runs.

example resnet18 resnet50

A

B

Problems

The above figure is iou loss. you can see it that decrease not very better than other losses(under images folder). In fact, when I print it and ground truth, I find relative large error between them, especially when ground truth iou is low. For example while ground truth iou is 0.2, prediction iou is 0.5 or 0.6. So at parse stage, I just use resp instead of resp * iou.

Another problem is that I can't figure out one formula: S E D in the paper. I just use D E D.

Train

First you need to put MPII dataset images in data/images. Then You can train from scratch or download our well trained weights.

train from scratch: download pretrained weights resnet18 weights and resnet50 weights, and put them in src/model/pretrain_weight directory.
well trained weights: download resnet18 weights and resnet50 weights and put them in src/checkpoint directory.

Reference

when I do this project, I mainly refer to this repo: https://github.com/hizhangp/yolo_tensorflow.

example	resnet18	resnet50
A
B