Neural network visualization toolkit for tf.keras
Project description
tf-keras-vis
tf-keras-vis is a visualization toolkit for debugging Keras models with Tensorflow 2.0, 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
- Allow more clear, sharp and stable visualizing in ActivationMaximization
And then we will add some algorisms such as below.
- SmoothGrad: removing noise by adding noise (DONE)
- Deep Dream
- Style transfer
Requirements
- Python 3.6+
- (tensorflow or tensorflow-gpu) >= 2.0
Installation
- PyPI
$ pip install tf-keras-vis
- Sources
$ cd tf-keras-vis
$ pip install -e .
Or
$ cd tf-keras-vis
$ python setup.py install
Usage
T.B.D.
For now, Please see examples/activation_maximization.ipynb
and examples/saliency.ipynb
.
When you want to run jupyter notebook, we recommend that install tf-keras-vis such as follow:
$ cd tf-keras-vis
$ pip install -e .[examples]
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.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
tf-keras-vis-0.1.0.tar.gz
(10.1 kB
view hashes)
Built Distribution
Close
Hashes for tf_keras_vis-0.1.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | c61695f315151efd9a15ec2f346a77a8e73ded760f30a3d4beaaef729ba21f4b |
|
MD5 | f6cc5f868917ed8edf22babb9d0e9c07 |
|
BLAKE2b-256 | 0cbcaf7a973afa53f1a27cbfba424009612b15658aa67e97339a008d99b421c6 |