# AdvProp (EfficientNet)

## AdvProp (EfficientNet)

**AdvProp** is an adversarial training scheme which treats adversarial examples as additional examples, to prevent overfitting. Key to the method is the usage of a separate auxiliary batch norm for adversarial examples, as they have different underlying distributions to normal examples.

The weights from this model were ported from [Tensorflow/TPU](https://github.com/tensorflow/tpu).

### How do I use this model on an image?

To load a pretrained model:

Copied

```
>>> import timm
>>> model = timm.create_model('tf_efficientnet_b0_ap', pretrained=True)
>>> model.eval()
```

To load and preprocess the image:

Copied

```
>>> import urllib
>>> from PIL import Image
>>> from timm.data import resolve_data_config
>>> from timm.data.transforms_factory import create_transform

>>> config = resolve_data_config({}, model=model)
>>> transform = create_transform(**config)

>>> url, filename = ("https://github.com/pytorch/hub/raw/master/images/dog.jpg", "dog.jpg")
>>> urllib.request.urlretrieve(url, filename)
>>> img = Image.open(filename).convert('RGB')
>>> tensor = transform(img).unsqueeze(0) # transform and add batch dimension
```

To get the model predictions:

Copied

```
>>> import torch
>>> with torch.no_grad():
...     out = model(tensor)
>>> probabilities = torch.nn.functional.softmax(out[0], dim=0)
>>> print(probabilities.shape)
>>> # prints: torch.Size([1000])
```

To get the top-5 predictions class names:

Copied

```
>>> # Get imagenet class mappings
>>> url, filename = ("https://raw.githubusercontent.com/pytorch/hub/master/imagenet_classes.txt", "imagenet_classes.txt")
>>> urllib.request.urlretrieve(url, filename) 
>>> with open("imagenet_classes.txt", "r") as f:
...     categories = [s.strip() for s in f.readlines()]

>>> # Print top categories per image
>>> top5_prob, top5_catid = torch.topk(probabilities, 5)
>>> for i in range(top5_prob.size(0)):
...     print(categories[top5_catid[i]], top5_prob[i].item())
>>> # prints class names and probabilities like:
>>> # [('Samoyed', 0.6425196528434753), ('Pomeranian', 0.04062102362513542), ('keeshond', 0.03186424449086189), ('white wolf', 0.01739676296710968), ('Eskimo dog', 0.011717947199940681)]
```

Replace the model name with the variant you want to use, e.g. `tf_efficientnet_b0_ap`. You can find the IDs in the model summaries at the top of this page.

To extract image features with this model, follow the [timm feature extraction examples](https://huggingface.co/docs/timm/feature_extraction), just change the name of the model you want to use.

### How do I finetune this model?

You can finetune any of the pre-trained models just by changing the classifier (the last layer).

Copied

```
>>> model = timm.create_model('tf_efficientnet_b0_ap', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
```

To finetune on your own dataset, you have to write a training loop or adapt [timm’s training script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

### How do I train this model?

You can follow the [timm recipe scripts](https://huggingface.co/docs/timm/scripts) for training a new model afresh.

### Citation

Copied

```
@misc{xie2020adversarial,
      title={Adversarial Examples Improve Image Recognition}, 
      author={Cihang Xie and Mingxing Tan and Boqing Gong and Jiang Wang and Alan Yuille and Quoc V. Le},
      year={2020},
      eprint={1911.09665},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}
```


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://boinc-ai.gitbook.io/timm/model-pages/advprop-efficientnet.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.