Image Segmentation
Transformers
PyTorch
pixdlm
cvpr-2026
compute-transparency
reasoning-segmentation
uav
remote-sensing
vision-language
Instructions to use WhynotHug/PixDLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use WhynotHug/PixDLM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="WhynotHug/PixDLM")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("WhynotHug/PixDLM", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| # Release Checklist | |
| Before uploading a public release: | |
| 1. Run the private-path scanner: | |
| ```bash | |
| python scripts/check_release.py . | |
| ``` | |
| 2. Confirm no large local artifacts are included: | |
| ```bash | |
| find . -type f -size +50M | |
| ``` | |
| 3. Confirm auth tokens are not present: | |
| ```bash | |
| grep -R "hf_" . --exclude-dir=.git --exclude-dir=.cache | |
| ``` | |
| 4. Upload to HuggingFace with a token stored only in the environment: | |
| ```bash | |
| export HF_TOKEN=... | |
| python scripts/upload_to_hf.py --namespace WhynotHug | |
| unset HF_TOKEN | |
| ``` | |
| 5. Review the public pages: | |
| - https://huggingface.co/WhynotHug/PixDLM | |
| - https://huggingface.co/datasets/WhynotHug/DRSeg | |
| The upload script updates cards, scripts, docs, and metadata without committing | |
| local `data/`, `checkpoints/`, `outputs/`, or `logs/`. | |