Add model

README.md

@@ -0,0 +1,131 @@
+---
+tags:
+- image-classification
+- timm
+library_tag: timm
+license: apache-2.0
+datasets:
+- imagenet-1k
+---
+# Model card for davit_base.msft_in1k
+
+A DaViT image classification model. Trained on ImageNet-1k by paper authors.
+
+Thanks to [Fredo Guan](https://github.com/fffffgggg54) for bringing the classification backbone to `timm`.
+
+
+## Model Details
+- **Model Type:** Image classification / feature backbone
+- **Model Stats:**
+  - Params (M): 88.0
+  - GMACs: 15.5
+  - Activations (M): 40.7
+  - Image size: 224 x 224
+- **Papers:**
+  - DaViT: Dual Attention Vision Transformers: https://arxiv.org/abs/2204.03645
+- **Original:** https://github.com/dingmyu/davit
+- **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('davit_base.msft_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(
+    'davit_base.msft_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, 96, 56, 56])
+    #  torch.Size([1, 192, 28, 28])
+    #  torch.Size([1, 384, 14, 14])
+    #  torch.Size([1, 768, 7, 7]
+    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(
+    'davit_base.msft_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 (ie.e a (batch_size, num_features, H, W) tensor
+
+output = model.forward_head(output, pre_logits=True)
+# output is (batch_size, num_features) tensor
+```
+
+## Model Comparison
+### By Top-1
+
+|model                |top1  |top1_err|top5  |top5_err|param_count|img_size|crop_pct|interpolation|
+|---------------------|------|--------|------|--------|-----------|--------|--------|-------------|
+|davit_base.msft_in1k |84.634|15.366  |97.014|2.986   |87.95      |224     |0.95    |bicubic      |
+|davit_small.msft_in1k|84.25 |15.75   |96.94 |3.06    |49.75      |224     |0.95    |bicubic      |
+|davit_tiny.msft_in1k |82.676|17.324  |96.276|3.724   |28.36      |224     |0.95    |bicubic      |
+
+## Citation
+```bibtex
+@inproceedings{ding2022davit,
+    title={DaViT: Dual Attention Vision Transformer}, 
+    author={Ding, Mingyu and Xiao, Bin and Codella, Noel and Luo, Ping and Wang, Jingdong and Yuan, Lu},
+    booktitle={ECCV},
+    year={2022},
+}
+```

config.json

@@ -0,0 +1,35 @@
+{
+  "architecture": "davit_base",
+  "num_classes": 1000,
+  "num_features": 1024,
+  "pretrained_cfg": {
+    "tag": "msft_in1k",
+    "custom_load": false,
+    "input_size": [
+      3,
+      224,
+      224
+    ],
+    "fixed_input_size": false,
+    "interpolation": "bicubic",
+    "crop_pct": 0.9,
+    "crop_mode": "center",
+    "mean": [
+      0.485,
+      0.456,
+      0.406
+    ],
+    "std": [
+      0.229,
+      0.224,
+      0.225
+    ],
+    "num_classes": 1000,
+    "pool_size": [
+      7,
+      7
+    ],
+    "first_conv": "stem.conv",
+    "classifier": "head.fc"
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:064f0449df34109ec5f8ff31dddf9d9c31a3fe4b03129e0a5b229aea2b0659fe
+size 351971805