Neural network visualization toolkit for tf.keras
Project description
tf-keras-vis
tf-keras-vis is a visualization toolkit for debugging tf.keras models in Tensorflow2.0+.
These features are based on ones of keras-vis, but tf-keras-vis APIs doesn't have compatibility with keras-vis, because we prioritized to get following features for our expriments.
- Support processing multiple images at a time as a batch
- Support tf.keras.Model that has multiple inputs (and, of course, multiple outpus too)
- Allow to utilize optimizers that embeded in tf.keras
- Get faster processing by optimal calculation
Visualizations
Visualize Dense Layer
Visualize Convolutional Filer
GradCAM
Saliency Map (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:0.2.4
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 and Gradcam++ don't work well, that's, it might occur some error.
- Unsupport
channels-firstmodels and datas.
ToDo
- API documentations
- We're going to add some algorisms such as below.
- SmoothGrad: removing noise by adding noise (DONE)
- GradCAM++
- ScoreCAM
- Deep Dream
- Style transfer
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-0.3.3.tar.gz
(12.8 kB
view hashes)
Built Distribution
Close
Hashes for tf_keras_vis-0.3.3-py3-none-any.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 66a5134ada8613d95c05e35ac6f4b410076c7c753d85d7703e86e03a58844346 |
|
| MD5 | 814e1a93ce61553aa386a22463cbd208 |
|
| BLAKE2b-256 | 64849006da00583436e5a27431da4cf354805976fd3707f470024ab86aa2605a |
