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
| set -euo pipefail | |
| BASE_MODEL="${BASE_MODEL:-checkpoints/llava-v1.6-vicuna-7b}" | |
| PIXDLM_WEIGHT="${PIXDLM_WEIGHT:-pretrained/pixdlm-7b/pytorch_model.bin}" | |
| SAVE_PATH="${SAVE_PATH:-pretrained/pixdlm-7b-merged}" | |
| CUDA_VISIBLE_DEVICES="${CUDA_VISIBLE_DEVICES:-}" python merge_lora_weights_and_save_hf_model.py \ | |
| --version="$BASE_MODEL" \ | |
| --weight="$PIXDLM_WEIGHT" \ | |
| --save_path="$SAVE_PATH" \ | |
| --resize_vision_tower \ | |
| --resize_vision_tower_size=448 \ | |
| --vision_tower_for_mask \ | |
| --Three_Level_Multi_Scale_Decoder | |