Add model

README.md

@@ -0,0 +1,155 @@
+---
+tags:
+- image-classification
+- timm
+library_tag: timm
+license: apache-2.0
+datasets:
+- imagenet-1k
+---
+# Model card for nfnet_l0.ra2_in1k
+
+A NFNet-Lite (Lightweight NFNet) image classification model. Trained in `timm` by Ross Wightman.
+
+Normalization Free Networks are (pre-activation) ResNet-like models without any normalization layers. Instead of Batch Normalization or alternatives, they use Scaled Weight Standardization and specifically placed scalar gains in residual path and at non-linearities based on signal propagation analysis.
+
+Lightweight NFNets are `timm` specific variants that reduce the SE and bottleneck ratio from 0.5 -> 0.25 (reducing widths) and use a smaller group size while maintaining the same depth. SiLU activations used instead of GELU.
+
+
+
+## Model Details
+- **Model Type:** Image classification / feature backbone
+- **Model Stats:**
+  - Params (M): 35.1
+  - GMACs: 4.4
+  - Activations (M): 10.5
+  - Image size: train = 224 x 224, test = 288 x 288
+- **Papers:**
+  - High-Performance Large-Scale Image Recognition Without Normalization: https://arxiv.org/abs/2102.06171
+  - Characterizing signal propagation to close the performance gap in unnormalized ResNets: https://arxiv.org/abs/2101.08692
+- **Original:** https://github.com/huggingface/pytorch-image-models
+- **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('nfnet_l0.ra2_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(
+    'nfnet_l0.ra2_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, 64, 112, 112])
+    #  torch.Size([1, 256, 56, 56])
+    #  torch.Size([1, 512, 28, 28])
+    #  torch.Size([1, 1536, 14, 14])
+    #  torch.Size([1, 2304, 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(
+    'nfnet_l0.ra2_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, 2304, 7, 7) 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{brock2021high,
+  author={Andrew Brock and Soham De and Samuel L. Smith and Karen Simonyan},
+  title={High-Performance Large-Scale Image Recognition Without Normalization},
+  journal={arXiv preprint arXiv:2102.06171},
+  year={2021}
+}
+```
+```bibtex
+@inproceedings{brock2021characterizing,
+  author={Andrew Brock and Soham De and Samuel L. Smith},
+  title={Characterizing signal propagation to close the performance gap in
+  unnormalized ResNets},
+  booktitle={9th International Conference on Learning Representations, {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 +1,41 @@
+{
+  "architecture": "nfnet_l0",
+  "num_classes": 1000,
+  "num_features": 2304,
+  "pretrained_cfg": {
+    "tag": "ra2_in1k",
+    "custom_load": false,
+    "input_size": [
+      3,
+      224,
+      224
+    ],
+    "test_input_size": [
+      3,
+      288,
+      288
+    ],
+    "fixed_input_size": false,
+    "interpolation": "bicubic",
+    "crop_pct": 0.9,
+    "test_crop_pct": 1.0,
+    "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.conv1",
+    "classifier": "head.fc"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fce06fcc634422a28b462ab884e831e8ecabb24673a6309af4724be74adfeec8
+size 140319350

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7de9a7a7df356fbd65293fa8f9a091056f255e6c6522ebdd8bd169afe37e5d01
+size 140376257