Add model

README.md

@@ -0,0 +1,109 @@
+---
+tags:
+- image-classification
+- timm
+library_tag: timm
+license: apache-2.0
+datasets:
+- imagenet-1k
+---
+# Model card for efficientformer_l7.snap_dist_in1k
+
+A EfficientFormer image classification model. Pretrained with distillation on ImageNet-1k.
+
+## Model Details
+- **Model Type:** Image classification / feature backbone
+- **Model Stats:**
+  - Params (M): 82.2
+  - GMACs: 10.2
+  - Activations (M): 24.5
+  - Image size: 224 x 224
+- **Original:** https://github.com/snap-research/EfficientFormer
+- **Papers:**
+  - EfficientFormer: Vision Transformers at MobileNet Speed: https://arxiv.org/abs/2206.01191
+- **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('efficientformer_l7.snap_dist_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(
+    'efficientformer_l7.snap_dist_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
+|model                              |top1  |top5  |param_count|img_size|
+|-----------------------------------|------|------|-----------|--------|
+|efficientformerv2_l.snap_dist_in1k |83.628|96.54 |26.32      |224     |
+|efficientformer_l7.snap_dist_in1k  |83.368|96.534|82.23      |224     |
+|efficientformer_l3.snap_dist_in1k  |82.572|96.24 |31.41      |224     |
+|efficientformerv2_s2.snap_dist_in1k|82.128|95.902|12.71      |224     |
+|efficientformer_l1.snap_dist_in1k  |80.496|94.984|12.29      |224     |
+|efficientformerv2_s1.snap_dist_in1k|79.698|94.698|6.19       |224     |
+|efficientformerv2_s0.snap_dist_in1k|76.026|92.77 |3.6        |224     |
+
+## Citation
+```bibtex
+@article{li2022efficientformer,
+  title={EfficientFormer: Vision Transformers at MobileNet Speed},
+  author={Li, Yanyu and Yuan, Geng and Wen, Yang and Hu, Ju and Evangelidis, Georgios and Tulyakov, Sergey and Wang, Yanzhi and Ren, Jian},
+  journal={arXiv preprint arXiv:2206.01191},
+  year={2022}
+}
+```
+```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/rwightman/pytorch-image-models}}
+}
+```

config.json

@@ -0,0 +1,36 @@
+{
+  "architecture": "efficientformer_l7",
+  "num_classes": 1000,
+  "num_features": 768,
+  "global_pool": "avg",
+  "pretrained_cfg": {
+    "tag": "snap_dist_in1k",
+    "custom_load": false,
+    "input_size": [
+      3,
+      224,
+      224
+    ],
+    "fixed_input_size": true,
+    "interpolation": "bicubic",
+    "crop_pct": 0.95,
+    "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": "stem.conv1",
+    "classifier": [
+      "head",
+      "head_dist"
+    ]
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0276e58a42943c429414c039c7838aef2bf40237219dc69c7f4a11378e924dd0
+size 329659889