tf-keras-vis 0.4.0

Neural network visualization toolkit for tf.keras

tf-keras-vis

tf-keras-vis is a visualization toolkit for debugging tf.keras models in Tensorflow2.0+. Currently supported algorisms for visualization include:

• Activation Maximization
• Class Activation Maps
  • GradCAM
  • GradCAM++
• Saliency Maps
  • Vanilla Saliency
  • SmoothGrad

tf-keras-vis is designed to be ease of use, light-weight and flexible. All visualizations have the features as follows:

• Support N-dim image inputs, that's, not only support pictures but also such as 3D images.
• Support batch-wise processing, so, be able to efficiently process multiple inputs.
• Support the model that have either multiple inputs or multiple outputs, or both.
• Support Optimizers embeded in tf.keras to process Activation maximization.

Visualizations

Visualize Dense Layer

Visualize Convolutional Filer

GradCAM

The images above are generated by GradCAM++.

Saliency Map

The images above are generated by SmoothGrad.

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:0.4.0

If you have GPU processors,

$ docker run -itd --runtime=nvidia -p 8888:8888 keisen/tf-keras-vis:0.4.0-gpu

You can find other images at Docker Hub.

Usage

Please see below for details:

• examples/attentions.ipynb
• examples/visualize_dense_layer.ipynb
• examples/visualize_conv_filters.ipynb

[NOTE] If you have ever used keras-vis, perhaps you may feel that tf-keras-vis is similar with keras-vis. Yes, tf-keras-vis derived from keras-vis. And then it was designed to support features in the description of this README such as multiple inputs/outputs, batchwise processing and so on. Therefore, although both provided visualization algorisms are almost the same, those software architectures are different. Please notice that tf-keras-vis APIs doesn’t have compatibility with keras-vis.

ToDo

• API documentations
• We're going to add some algorisms such as below.
  • ScoreCAM: Score-Weighted Visual Explanations for Convolutional Neural Networks
  • Deep Dream
  • Style transfer

Known Issues

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