Thanks to visit codestin.com
Credit goes to github.com

Skip to content

zpschang/PIG-Nav

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

PIG-Nav: Key Insights for Pretrained Image-Goal Navigation Models

arXivDemoHuggingFaceDataset

This is the implementations for PIG-Nav: Key Insights for Pretrained Image-Goal Navigation Models.

📖 Overview

PIG-Nav

  • We propose PIG-Nav, a pretrained model for image-goal navigation with diverse indoor and outdoor navigation datasets, featuring an early-fusion network architecture with appropriately pretrained Vision Transformer encoder, and high-level auxiliary tasks designed for navigation agents.
  • On two large 3D game environments (Highrise and Sanctuary), PIG-Nav achieves an average improvement of 22.6% in zero-shot setting and 37.5% improvement in finetuning setting over existing visual navigation models.

🤗 Model Zoo

Model Name HF Path Note
PIG-Nav PIG-Nav The pretrained PIG-Nav model with diverse navigation dataset.
PIG-Nav (w/o early-fuse) PIG-Nav-NoEarlyfuse The pretrained PIG-Nav model without early fuse architecture.
PIG-Nav (w/o aux) PIG-Nav-NoAux The pretrained PIG-Nav model without auxiliary tasks.
PIG-Nav-Highrise-finetuned PIG-Nav-Finetuned-Highrise The PIG-Nav model fine-tuned on Highrise environment.
PIG-Nav-Highrise-finetuned PIG-Nav-Finetuned-Sanctuary The PIG-Nav model fine-tuned on Sanctuary environment.

🔧 Environment Setup

Use uv sync for installing the environment, and use source .venv/bin/activate to activate the environment.

➡️ Getting Started

Dataset Preparation

Pretraining datasets: available at https://huggingface.co/datasets/zpschang/PIG-Nav-Dataset-Pretrain.

Use cat pignav_pretrain_dataset.tar.part-* | tar -xvf - for extracting the pretraining dataset.

Finetuning datasets for Highrise and Sanctuary: available at https://huggingface.co/datasets/zpschang/PIG-Nav-Dataset-Finetune.

Pretraining PIG-Nav

Run bash scripts/pretrain.sh for pretraining PIG-Nav. The config file for pretraining is in configs/pretrain.yaml. Please modify the data_folder and data_split_folder to your pretraining dataset path. The pretrained model checkpoints will be saved under log_dir in scripts/pretrain.sh.

For the full configuration information for PIG-Nav training, see model_config.md.

Fine-tuning PIG-Nav

Run bash scripts/finetune_[env].sh for finetuning PIG-Nav on Highrise and Sanctuary game environments. The config file for finetuning is in configs/finetune_[env].yaml. Please modify the data_folder and data_split_folder to your finetuning dataset path.

For the full configuration information for PIG-Nav finetuning, see model_config.md.

Evaluating PIG-Nav on Highrise and Sanctuary

First, download the ShooterGame environment. To start the environment under Linux, enter Linux/ path, and run ./ShooterGame.sh [port_number] to start the environment with the port number.

Testing PIG-Nav on Custom Data

Run bash scripts/eval_highrise.sh or bash scripts/eval_sanctuary.sh to start evaluate the PIG-Nav under two environments. You should modify the port value to match the port number for starting the environment. The success rates will be saved in logs/, and the video demos will be saved in videos/.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published