Use manual for LUNIT_DINO
#1
by
Helly123
- opened
Can someone guide me on how to apply this to my dataset?
Hi @Helly123 !
The Model card provides a simple code example to compute the embeddings of an image:
from urllib.request import urlopen
from PIL import Image
import timm
# get example histology image
img = Image.open(
urlopen(
"https://github.com/owkin/HistoSSLscaling/raw/main/assets/example.tif"
)
)
# load model from the hub
model = timm.create_model(
model_name="hf-hub:1aurent/vit_small_patch8_224.lunit_dino",
pretrained=True,
).eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
To compute the embeddings of every image in your dataset, you can simply for loop the above code on each of your images.