8000 GitHub - dsSarcos/curo-deep-learning-project: Directory containing all the files used in my undergraduate research assistantship at the University of Georgia
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Directory containing all the files used in my undergraduate research assistantship at the University of Georgia

Notifications You must be signed in to change notification settings

dsSarcos/curo-deep-learning-project

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 

Repository files navigation

CURO Deep Learning Project

Summary

This is my project for UGA's Center for Undergraduate Research Opportunities.

To get the training and validation scripts to run properly, the paths to the proper locations need to be updated within the scripts. These include the paths to the datasets in the config files, as well as the paths to the backbone models for DPT, SegNet, and FCN8s. As of now, the code is disorganized because the project is a raw dump of what I used on several of UGA's CUDA servers and my own personal computer. When time allows, I'll clean it up to eliminate the patchwork and increase ease of use.

While the project is currently unstable, I've included logs of my training runs in pytorch-semseg/runs. These runs were completed on UGA's CUDA servers.

Sources

Paper and Dataset

Dataset A fully end-to-end deep learning approach for real-time simultaneous 3D reconstruction and material recognition

Submodules

pytorch-semseg DPT

Environment

  1. Create and activate a python environment.

$python venv env; source env/activate

  1. Install the required packages

$pip install -r requirements.txt

About

Directory containing all the files used in my undergraduate research assistantship at the University of Georgia

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published
0