metadata
license: apache-2.0
Model: SatMAE++ (https://arxiv.org/abs/2403.05419)
Variant: ViT-L_pretrain_fmow_rgb
Example Usage:
from huggingface_hub import hf_hub_download
import torch
hf_hub_download("MVRL/satmaepp_ViT-L_pretrain_fmow_rgb", "model.py", local_dir=".")
from model import MaskedAutoencoderViT
model = MaskedAutoencoderViT.from_pretrained("MVRL/satmaepp_ViT-L_pretrain_fmow_rgb")
print(model.forward_encoder(torch.randn(1, 3, 224, 224), mask_ratio=0.0)[0].shape)