tf-keras-vis 0.3.1

Neural network visualization toolkit for tf.keras

tf-keras-vis

tf-keras-vis is a visualization toolkit for debugging tf.keras models in Tensorflow2.

The features of tf-keras-vis are based on keras-vis, but tf-keras-vis's APIs doesn't have compatibility with keras-vis's, because we prioritized to get following features for our expriments.

• Support processing multipul images at a time as a batch
• Support tf.keras.Model that has multipul inputs (and, of course, multipul outpus too)
• Allow to use optimizers that embeded in tf.keras

Visualizations

Visualize Dense Layer

Visualize Convolutional Filer

Saliency Map and GradCAM

Requirements

• Python 3.5-3.8
• tensorflow>=2.0

Installation

• PyPI

$ pip install tf-keras-vis tensorflow

• Docker (container that run Jupyter Notebook)

$ docker run -itd -p 8888:8888 keisen/tf-keras-vis:0.2.4

If you have GPU processors,

$ docker run -itd --runtime=nvidia -p 8888:8888 keisen/tf-keras-vis:0.2.4-gpu

You can find other images at Docker Hub.

Usage

Please see examples/attentions.ipynb, examples/visualize_dense_layer.ipynb and examples/visualize_conv_filters.ipynb for details.

Known Issues

• With InceptionV3, ActivationMaximization doesn't work well, that's, it might generate meanninglessly bulr image.
• With cascading model, Gradcam doesn't work well, that's, it might occur some error.
• Unsupported channels-first models and datas.

ToDo

• API documentations
• We're going to add some algorisms such as below.
  • GradCAM++
  • SmoothGrad: removing noise by adding noise (DONE)
  • Deep Dream
  • Style transfer