deep-vision icon indicating copy to clipboard operation
deep-vision copied to clipboard

Published 20 hours ago • verified publisher icon ethanyanjiali

How to get your weights?

Open JohnCraigPublic opened this issue 4 years ago • 3 comments

Hello - would like to try our your demo! Where can I find the model weights that you load?

JohnCraigPublic avatar May 11 '20 19:05 JohnCraigPublic

Also, can't find tensorflow_addons -- where does that come from? Thanks!!

JohnCraigPublic avatar May 11 '20 20:05 JohnCraigPublic

You say: "Once you have all the images and annotations, copy tfrecords_mpii.py to the new dataset folder and run it to generate TF Records" But I don't find tfrecords_mpii.py help! Need a hint from you... Thanks...

JohnCraigPublic avatar May 14 '20 23:05 JohnCraigPublic

Hey John, tfrecords_mpii.py is here: https://github.com/ethanyanjiali/deep-vision/tree/master/Datasets/MPII

Unlike COCO or ImageNet, MPII is a relatively small dataset, so you should be able to train it quickly. My implementation in this repo is mostly for study purpose, so it doesn't yield similar PCKh as in the paper. I would recommend this repo if you are looking for pretrained weights: https://github.com/princeton-vl/pytorch_stacked_hourglass I also have a private implementation with comparable metrics, and the main difference is the data augmentation part.

ethanyanjiali avatar May 15 '20 07:05 ethanyanjiali