|
|
| --- |
| tags: |
| - image-classification |
| - ecology |
| - fungi |
| - FGVC |
| library_name: DanishFungi |
| license: cc-by-nc-4.0 |
| --- |
| # Model card for BVRA/vit_large_patch16_384.ft_df20m_384 |
| |
| ## Model Details |
| - **Model Type:** Danish Fungi Classification |
| - **Model Stats:** |
| - Params (M): 303.9M |
| - Image size: 384 x 384 |
| - **Papers:** |
| - **Original:** An image is worth 16x16 words: Transformers for image recognition at scale --> https://arxiv.org/pdf/2010.11929 |
| - **Train Dataset:** DF20 --> https://github.com/BohemianVRA/DanishFungiDataset/ |
| |
| ## Model Usage |
| ### Image Embeddings |
| ```python |
| import timm |
| import torch |
| import torchvision.transforms as T |
| from PIL import Image |
| from urllib.request import urlopen |
| model = timm.create_model("hf-hub:BVRA/vit_large_patch16_384.ft_df20m_384", pretrained=True) |
| model = model.eval() |
| train_transforms = T.Compose([T.Resize((384, 384)), |
| T.ToTensor(), |
| T.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])]) |
| img = Image.open(PATH_TO_YOUR_IMAGE) |
| output = model(train_transforms(img).unsqueeze(0)) |
| # output is a (1, num_features) shaped tensor |
| ``` |
| |
| ## Citation |
| ```bibtex |
| @InProceedings{Picek_2022_WACV, |
| author = {Picek, Lukas and Sulc, Milan and Matas, Jiri and Jeppesen, Thomas S. and Heilmann-Clausen, Jacob and L{e}ss{\o}e, Thomas and Fr{\o}slev, Tobias}, |
| title = {Danish Fungi 2020 - Not Just Another Image Recognition Dataset}, |
| booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, |
| month = {January}, |
| year = {2022}, |
| pages = {1525-1535} |
| } |
| |
| @article{picek2022automatic, |
| title={Automatic Fungi Recognition: Deep Learning Meets Mycology}, |
| author={Picek, Lukas and Sulc, Milan and Matas, Jiri and Heilmann-Clausen, Jacob and Jeppesen, Thomas S and Lind, Emil}, |
| journal={Sensors}, |
| volume={22}, |
| number={2}, |
| pages={633}, |
| year={2022}, |
| publisher={Multidisciplinary Digital Publishing Institute} |
| } |
| ``` |
|
|
