The code and training command of the stage-1: vector representation pre-training stage

wayveai / Driving-with-LLMs

PyTorch implementation for the paper "Driving with LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Driving"

Apache License 2.0

453 stars 39 forks source link

The code and training command of the stage-1: vector representation pre-training stage #3

Open Phoebe-ovo opened 1 year ago

Phoebe-ovo commented 1 year ago

Can you provide the code and training command of the first stage: vector representation pre-training stage?

lipeng1a commented 9 months ago

+1, just don't know how to train and get the weight of first stage from models/weights/stage1_pretrained_model. Did you get it from the dataset (160k QA pairs derived from 10k driving scenarios) as mentioned in the abstract?