https://github.com/jonasrauber/foolbox-tensorflow-keras-applications

The pretrained TensorFlow Keras models with a Foolbox Zoo compatible interface
https://github.com/jonasrauber/foolbox-tensorflow-keras-applications

adversarial-attacks foolbox imagenet keras pretrained-models tensorflow

Last synced: 25 days ago
JSON representation

The pretrained TensorFlow Keras models with a Foolbox Zoo compatible interface

• Host: GitHub
• URL: https://github.com/jonasrauber/foolbox-tensorflow-keras-applications
• Owner: jonasrauber
• Created: 2020-02-10T22:00:36.000Z (almost 5 years ago)
• Default Branch: master
• Last Pushed: 2020-02-10T23:16:42.000Z (almost 5 years ago)
• Last Synced: 2024-10-29T13:55:40.813Z (2 months ago)
• Topics: adversarial-attacks, foolbox, imagenet, keras, pretrained-models, tensorflow
• Language: Python
• Homepage: https://github.com/bethgelab/foolbox
• Size: 4.88 KB
• Stars: 4
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.rst

Awesome Lists containing this project

README

        
=================================================

TensorFlow pretrained ImageNet models for Foolbox

=================================================

This repository provides the `Keras Applications `_ (pretrained ImageNet models) in a `Foolbox Native `_ compatible format.

This code requires Foolbox 3.0 or newer.

Example

-------

.. code-block:: python

   import foolbox as fbn

   url = "https://github.com/jonasrauber/foolbox-tensorflow-keras-applications"

   fmodel = fbn.zoo.get_model(url, name="MobileNetV2")

   images, labels = fbn.samples(fmodel, dataset='imagenet', batchsize=16)

   print(fbn.accuracy(fmodel, images, labels))

   # -> 0.9375

   # you can now attack fmodel using Foolbox attacks

   # ...

Supported Models

----------------

- DenseNet121

- DenseNet169

- DenseNet201

- InceptionResNetV2

- InceptionV3

- MobileNet

- MobileNetV2

- NASNetLarge

- NASNetMobile

- ResNet50

- ResNet101

- ResNet152

- ResNet50V2

- ResNet101V2

- ResNet152V2

- VGG16

- VGG19

- Xception