Skip to content

Deep learning on computational accelerators course final project

License

Notifications You must be signed in to change notification settings

ilaychen/CS236605-final-project

Repository files navigation

CS236605 Final Project

You can find our project report at report.pdf

Under pose/models/hourglass.py you can find our improvements.

To run an experiment:

python ./example/main.py --dataset mpii --arch hg --stack 1 --block 1 --features 256 --checkpoint checkpoint/s1/ 

notice that the MPII dataset must be located in /data/mpii/

checkpoint/ - saves the model after each epoch when increasing accuracy data/ - should contain the datasets pose/ - the model's code

screenshot

Installation

PyTorch (>= 0.4.1): Please follow the installation instruction of PyTorch.

Download annotation file: (MPII) Download mpii_annotations.json and save it to data/mpii

About

Deep learning on computational accelerators course final project

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published