metadata
license: apache-2.0
Model: ScaleMAE (https://arxiv.org/abs/2212.14532)
Variant: scalemae-vitlarge-800
Example Usage:
from huggingface_hub import hf_hub_download
import torch
hf_hub_download("MVRL/scalemae-vitlarge-800", "model.py", local_dir=".")
from model import ScaleMAE_baseline
model = ScaleMAE_baseline.from_pretrained("MVRL/scalemae-vitlarge-800")
print(model(torch.randn(1, 3, 224, 224),patch_size=16).shape)