Add model

README.md

@@ -0,0 +1,92 @@
+---
+tags:
+- image-classification
+- timm
+library_name: timm
+license: apache-2.0
+datasets:
+- imagenet-1k
+---
+# Model card for convit_small.fb_in1k
+
+A ConViT image classification model. Trained on ImageNet-1k by paper authors.
+
+## Model Details
+- **Model Type:** Image classification / feature backbone
+- **Model Stats:**
+  - Params (M): 27.8
+  - GMACs: 5.8
+  - Activations (M): 17.9
+  - Image size: 224 x 224
+- **Papers:**
+  - ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases: https://arxiv.org/abs/2103.10697
+- **Dataset:** ImageNet-1k
+- **Original:** https://github.com/facebookresearch/convit
+
+## 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('convit_small.fb_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)
+```
+
+### 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(
+    'convit_small.fb_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, 197, 432) 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
+@article{d2021convit,
+  title={ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases},
+  author={d'Ascoli, St{'e}phane and Touvron, Hugo and Leavitt, Matthew and Morcos, Ari and Biroli, Giulio and Sagun, Levent},
+  journal={arXiv preprint arXiv:2103.10697},
+  year={2021}
+}
+```

config.json

@@ -0,0 +1,33 @@
+{
+  "architecture": "convit_small",
+  "num_classes": 1000,
+  "num_features": 432,
+  "global_pool": "token",
+  "pretrained_cfg": {
+    "tag": "fb_in1k",
+    "custom_load": false,
+    "input_size": [
+      3,
+      224,
+      224
+    ],
+    "fixed_input_size": true,
+    "interpolation": "bicubic",
+    "crop_pct": 0.875,
+    "crop_mode": "center",
+    "mean": [
+      0.485,
+      0.456,
+      0.406
+    ],
+    "std": [
+      0.229,
+      0.224,
+      0.225
+    ],
+    "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:b88f4b89ab391220c57b44c1c7fdaa7a4ba5909a056b903e240cb3a35a72c242
+size 111125778

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38efced406a2e9088bf4e727c47a13d4c23c33abafb7374154d0867d9e08260b
+size 111171549