search

OSU-NLP-Group / LLM-Planner

[ICCV'23] LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models
https://osu-nlp-group.github.io/LLM-Planner/
MIT License
129 stars 11 forks source link

[Query] Minimum Requirements to visualise the learnt model #11

Closed Acejoy closed 4 months ago

Acejoy commented 5 months ago

Hello all, I am interested in this project and want to run it on my local machine. I wanted to know what was the minimum hardware requirements for running this code? I have 16GB RAM, 4GB Nvidia Geforce 1650Ti and running on Ubuntu 22.04 LTS.

thanks

chanhee-luke commented 5 months ago

This doesn’t need GPU to run. I’ve only tested on MacOS and Ubuntu 20.04 but should work on 22.04.

Acejoy commented 5 months ago

Sorry, If I understand correctly: We use semantic segmentation for visual understanding and LLM as an action planner, so the leanrt models do not require GPU? Please correct me if I am wrong.

Sorry, if my questions are too trivial, I am still learning.

chanhee-luke commented 5 months ago

The model can be run on CPU. GPU makes the inference faster but it is not required.

Acejoy commented 4 months ago

The model can be run on CPU. GPU makes the inference faster but it is not required.

Thanks again for the reply.