Instructions to use mmkuznecov/SynthOccPredModels with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- stable-baselines3
How to use mmkuznecov/SynthOccPredModels with stable-baselines3:
from huggingface_sb3 import load_from_hub checkpoint = load_from_hub( repo_id="mmkuznecov/SynthOccPredModels", filename="{MODEL FILENAME}.zip", ) - Notebooks
- Google Colab
- Kaggle
SynthOccPred / voxel_car models
This repository contains two trained artifacts for the voxel_car project:
| Artifact | Hub path |
|---|---|
| Occupancy predictor checkpoint | occupancy/ckpt_best.pt |
| PPO policy for RL planner | rl/ppo_voxel_car_final.zip |
Use from Python
from voxel_car.hub import load_occnet_from_hf, load_ppo_from_hf
model, ego_cfg, cam_cfg, image_hw, device = load_occnet_from_hf(
repo_id="mmkuznecov/SynthOccPredModels",
)
ppo = load_ppo_from_hf(
repo_id="mmkuznecov/SynthOccPredModels",
)
Use in the Gradio demo
export VOXEL_CAR_HF_REPO="mmkuznecov/SynthOccPredModels"
python app.py
The demo can run closed-loop scenarios with either:
- standard A* planner over OccNet occupancy predictions
- PPO-RL planner over OccNet occupancy predictions