Add model

README.md

@@ -0,0 +1,148 @@
+---
+tags:
+- image-classification
+- timm
+library_name: timm
+license: apache-2.0
+datasets:
+- imagenet-1k
+- webli
+---
+# Model card for vit_so400m_patch14_siglip_378.webli_ft_in1k
+
+A Vision Transformer (ViT) encoder. Pretrained with SigLIP contrastive learning. Fine-tuned on ImageNet-1k in `timm`.
+
+## Model Details
+- **Model Type:** Image classification / feature backbone
+- **Model Stats:**
+  - Params (M): 429.4
+  - GMACs: 335.4
+  - Activations (M): 452.9
+  - Image size: 378 x 378
+- **Papers:**
+  - Sigmoid Loss for Language Image Pre-Training: https://arxiv.org/abs/2303.15343
+  - An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
+- **Pretrain Dataset:** WebLI
+- **Original:** https://github.com/google-research/big_vision
+- **Dataset:** ImageNet-1k
+
+## Model Usage
+### Image Classification
+```python
+from urllib.request import urlopen
+from PIL import Image
+import timm
+
+img = Image.open(urlopen(
+    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
+))
+
+model = timm.create_model('vit_so400m_patch14_siglip_378.webli_ft_in1k', pretrained=True)
+model = model.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))  # unsqueeze single image into batch of 1
+
+top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
+```
+
+### Feature Map Extraction
+```python
+from urllib.request import urlopen
+from PIL import Image
+import timm
+
+img = Image.open(urlopen(
+    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
+))
+
+model = timm.create_model(
+    'vit_so400m_patch14_siglip_378.webli_ft_in1k',
+    pretrained=True,
+    features_only=True,
+)
+model = model.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))  # unsqueeze single image into batch of 1
+
+for o in output:
+    # print shape of each feature map in output
+    # e.g.:
+    #  torch.Size([1, 1152, 27, 27])
+    #  torch.Size([1, 1152, 27, 27])
+    #  torch.Size([1, 1152, 27, 27])
+
+    print(o.shape)
+```
+
+### Image Embeddings
+```python
+from urllib.request import urlopen
+from PIL import Image
+import timm
+
+img = Image.open(urlopen(
+    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
+))
+
+model = timm.create_model(
+    'vit_so400m_patch14_siglip_378.webli_ft_in1k',
+    pretrained=True,
+    num_classes=0,  # remove classifier nn.Linear
+)
+model = model.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
+
+# or equivalently (without needing to set num_classes=0)
+
+output = model.forward_features(transforms(img).unsqueeze(0))
+# output is unpooled, a (1, 729, 1152) shaped tensor
+
+output = model.forward_head(output, pre_logits=True)
+# output is a (1, num_features) shaped tensor
+```
+
+## Model Comparison
+Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
+
+## Citation
+```bibtex
+@inproceedings{zhai2023sigmoid,
+  title={Sigmoid loss for language image pre-training},
+  author={Zhai, Xiaohua and Mustafa, Basil and Kolesnikov, Alexander and Beyer, Lucas},
+  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
+  pages={11975--11986},
+  year={2023}
+}
+```
+```bibtex
+@article{dosovitskiy2020vit,
+  title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
+  author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and  Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
+  journal={ICLR},
+  year={2021}
+}
+```
+```bibtex
+@misc{rw2019timm,
+  author = {Ross Wightman},
+  title = {PyTorch Image Models},
+  year = {2019},
+  publisher = {GitHub},
+  journal = {GitHub repository},
+  doi = {10.5281/zenodo.4414861},
+  howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
+}
+```

config.json

@@ -0,0 +1,33 @@
+{
+  "architecture": "vit_so400m_patch14_siglip_378",
+  "num_classes": 1000,
+  "num_features": 1152,
+  "global_pool": "map",
+  "pretrained_cfg": {
+    "tag": "webli_ft_in1k",
+    "custom_load": false,
+    "input_size": [
+      3,
+      378,
+      378
+    ],
+    "fixed_input_size": true,
+    "interpolation": "bicubic",
+    "crop_pct": 1.0,
+    "crop_mode": "squash",
+    "mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "num_classes": 1000,
+    "pool_size": null,
+    "first_conv": "patch_embed.proj",
+    "classifier": "head"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aa26b75cd67e6498a1b84a81a6956363b33d2e850f5442876f2d5915a85bf29
+size 1717547296

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d9d320a9ae6212dd39ec06f04bce62bbecf89a57e31a2c07722bc9340951fc1
+size 1717643562