BiliSakura / DOFA-transformers

DOFA Transformers Models

Self-contained HuggingFace model checkpoints for DOFA .

Each checkpoint subfolder ships remote code for model, processor, and pipeline loading with trust_remote_code=True .

Sentinel-2 9-band defaults ( default_wavelengths , default_image_mean , default_image_std ) are baked into config.json and preprocessor_config.json .

Available checkpoints

Usage

from transformers import pipeline

MODEL = "/path/to/DOFA-transformers/dofa-base-patch16-224"

pipe = pipeline(
    task="dofa-feature-extraction",
    model=MODEL,
    trust_remote_code=True,
)

features = pipe(image_array, pool=True, return_tensors=True)

Override Sentinel-2 defaults for other sensors:

features = pipe(
    image_array,
    wavelengths=[...],
    image_mean=[...],
    image_std=[...],
    pool=True,
    return_tensors=True,
)

Test CLI

conda activate rsgen
python test_dofa.py
python test_dofa.py --model dofa-large-patch16-224
python test_dofa.py --model dofa-base-patch16-224 --no-pool

Dependencies

• transformers
• timm
• torch
• opencv-python (only when resizing inputs with more than 4 channels)