tf-keras-vis 0.2.1

Neural network visualization toolkit for tf.keras

tf-keras-vis

tf-keras-vis is a visualization toolkit for debugging Keras models with Tensorflow2, but not original Keras.

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, instead of getting it, we prioritized to get following features.

• 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 use optimizers that embeded in tf.keras

And then we will add some algorisms such as below.

• SmoothGrad: removing noise by adding noise (DONE)
• Deep Dream
• Style transfer

Requirements

• Python 3.5, 3.6 or 3.7
• tensorflow>=2.0.0

Installation

• PyPI

$ pip install tf-keras-vis tensorflow

• Docker

$ docker pull keisen/tf-keras-vis:0.2.0

You can find other images (that's nvidia-docker images) at dockerhub.

Usage

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

• Run Jupyter notebooks on Docker

$ docker run -it -v /PATH/TO/tf-keras-vis:/tf-keras-vis -p 8888:8888 keisen/tf-keras-vis:0.2.0 jupyter lab

Or, if you have GPU processors,

$ docker run -it --runtime=nvidia -v /PATH/TO/tf-keras-vis:/tf-keras-vis -p 8888:8888 keisen/tf-keras-vis:0.2.0-gpu jupyter lab

API Documentation

T.B.D.

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.