google/tipsv2-g14-dpt

Use relative imports for sibling modules (fixes local loading, save_pretrained, pickling)

Update files for transformers integration (#1)

Add arXiv tag to link the paper

Add arXiv paper link to citation

Update example image URL to use HF-hosted ADE20K image

Add navigation table linking all variants and DPT heads

Revert "Use device-agnostic code instead of hardcoded .cuda()"

Use device-agnostic code instead of hardcoded .cuda()

Add print statements with descriptive comments to code examples

Use cat photo, add print statements to code examples

Fix zero-shot segmentation section, use public example image

Fix backbone link in Model details

Update README

Upload README.md with huggingface_hub

Upload model.safetensors with huggingface_hub

Upload README.md with huggingface_hub

Upload config.json with huggingface_hub

Upload dpt_head.py with huggingface_hub

Upload modeling_dpt.py with huggingface_hub

Upload configuration_dpt.py with huggingface_hub

initial commit