Hugging Face

from huggingface_hub import login
import torch
import timm
from torchvision import transforms

login()  # token from https://huggingface.co/settings/tokens

model = timm.create_model(
    "hf-hub:bioptimus/H-optimus-1",
    pretrained=True, init_values=1e-5, dynamic_img_size=False,
)
model.to("cuda").eval()

transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize(
        mean=(0.707223, 0.578729, 0.703617),
        std=(0.211883, 0.230117, 0.177517),
    ),
])

tile = transforms.ToPILImage()(torch.rand(3, 224, 224))

with torch.autocast(device_type="cuda", dtype=torch.float16):
    with torch.inference_mode():
        features = model(transform(tile).unsqueeze(0).to("cuda"))

assert features.shape == (1, 1536)