Instructions to use phi-lab-rice/GRADE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use phi-lab-rice/GRADE with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("phi-lab-rice/GRADE", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Download evaluation_dataset/README.md from phi-lab-rice/GRADE: direct link, hf CLI and curl.
- Browser
- Download file 1.51 kB
-
https://huggingface.co/phi-lab-rice/GRADE/resolve/main/evaluation_dataset/README.md
- Command line
-
hf download hf://phi-lab-rice/GRADE/evaluation_dataset/README.md
-
curl -L -o README.md https://huggingface.co/phi-lab-rice/GRADE/resolve/main/evaluation_dataset/README.md
license: cc-by-nc-4.0
Smoke-Eval evaluation data
The public evaluation dataset
contains 20 held-out Smoke-Eval sequences and Smoke-Eval-RadarCam-Depth.zip.
It is the evaluation input for the GRADE artifact. The Rice/Ti-Zed-Dji and
IQ1M training datasets mentioned in an earlier release-plan README are not
part of this repository and are not needed for the artifact's E1 or E2
evaluation workflows.
Download into the artifact code directory with the Hugging Face CLI:
hf auth login # recommended for the many small files; use a secure local prompt
hf download mypersonalsharingspot11/evaluation_dataset \
--repo-type dataset --local-dir evaluation_dataset
python -m zipfile -e evaluation_dataset/Smoke-Eval-RadarCam-Depth.zip evaluation_dataset
The artifact scripts expect evaluation_dataset/Smoke-Eval/<sequence>/ and
evaluation_dataset/Smoke-Eval-RadarCam-Depth/. Ensure the ZIP does not leave
an extra nested Smoke-Eval-RadarCam-Depth/ directory. Anonymous downloads
may encounter rate limits because the repository contains many small files.
This README describes what is publicly hosted; it does not itself certify consent, anonymization, or redistribution clearance. Those records must be checked by the authors before any long-term archival deposit or expansion of the dataset release. A versioned per-file manifest and permanent archive DOI have not yet been included with this dataset.