Add model

README.md

@@ -0,0 +1,150 @@
+---
+tags:
+- image-classification
+- timm
+library_name: timm
+license: apache-2.0
+datasets:
+- imagenet-1k
+---
+# Model card for tf_efficientnet_b5.aa_in1k
+
+A EfficientNet image classification model. Trained on ImageNet-1k with auto-augment in Tensorflow by paper authors, ported to PyTorch by Ross Wightman.
+
+
+## Model Details
+- **Model Type:** Image classification / feature backbone
+- **Model Stats:**
+  - Params (M): 30.4
+  - GMACs: 10.5
+  - Activations (M): 98.9
+  - Image size: 456 x 456
+- **Papers:**
+  - EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks: https://arxiv.org/abs/1905.11946
+  - AutoAugment: Learning Augmentation Policies from Data: https://arxiv.org/abs/1805.09501
+- **Dataset:** ImageNet-1k
+- **Original:** https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
+
+## 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('tf_efficientnet_b5.aa_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(
+    'tf_efficientnet_b5.aa_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, 24, 228, 228])
+    #  torch.Size([1, 40, 114, 114])
+    #  torch.Size([1, 64, 57, 57])
+    #  torch.Size([1, 176, 29, 29])
+    #  torch.Size([1, 512, 15, 15])
+
+    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(
+    'tf_efficientnet_b5.aa_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, 2048, 15, 15) 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{tan2019efficientnet,
+  title={Efficientnet: Rethinking model scaling for convolutional neural networks},
+  author={Tan, Mingxing and Le, Quoc},
+  booktitle={International conference on machine learning},
+  pages={6105--6114},
+  year={2019},
+  organization={PMLR}
+}
+```
+```bibtex
+@inproceedings{47890,
+    title       = {AutoAugment: Learning Augmentation Policies from Data},
+    author      = {Ekin Dogus Cubuk and Barret Zoph and Dandelion Mane and Vijay Vasudevan and Quoc V. Le},
+    year        = {2019},
+    URL = {https://arxiv.org/pdf/1805.09501.pdf}
+}
+```
+```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 +1,35 @@
+{
+  "architecture": "tf_efficientnet_b5",
+  "num_classes": 1000,
+  "num_features": 2048,
+  "pretrained_cfg": {
+    "tag": "aa_in1k",
+    "custom_load": false,
+    "input_size": [
+      3,
+      456,
+      456
+    ],
+    "fixed_input_size": false,
+    "interpolation": "bicubic",
+    "crop_pct": 0.934,
+    "crop_mode": "center",
+    "mean": [
+      0.485,
+      0.456,
+      0.406
+    ],
+    "std": [
+      0.229,
+      0.224,
+      0.225
+    ],
+    "num_classes": 1000,
+    "pool_size": [
+      15,
+      15
+    ],
+    "first_conv": "conv_stem",
+    "classifier": "classifier"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e81868f5acfdd37fc79a337761cba24b33611d652ca969cbe9a474fd800ad4de
+size 122330162

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0df0fd8045493680758e74f5ad9d32e7dd006fd6c3f13018276d2fea08d65b6
+size 122540453