tf-keras-vis

KO | EN

gitlite — search

#javascript #hacktoberfest #react #ai #typescript #go #android #kubernetes #awesome-list #pytorch #security #mcp #ios #open-source

(★ 337)

Neural network visualization toolkit for tf.keras

File Explorer

Download Latest Version (.zip)

- conda_build_config.yaml
- meta.yaml
- - python-package-cron.yml
  - python-package-TF2.17.yml
  - python-package-TF2.5.yml
  - python-package.yml
  - python-publish.yml
  - sphinx-publish.yml
- cpu.Dockerfile
- gpu.Dockerfile
- - tf_keras_vis.activation_maximization.callbacks.md
  - tf_keras_vis.activation_maximization.input_modifiers.md
  - tf_keras_vis.activation_maximization.md
  - tf_keras_vis.activation_maximization.regularizers.md
  - tf_keras_vis.gradcam.md
  - tf_keras_vis.gradcam_plus_plus.md
  - tf_keras_vis.layercam.md
  - tf_keras_vis.md
  - tf_keras_vis.saliency.md
  - tf_keras_vis.scorecam.md
  - tf_keras_vis.utils.md
  - tf_keras_vis.utils.model_modifiers.md
  - tf_keras_vis.utils.scores.md
- - attentions.ipynb
  - index.md
  - visualize_conv_filters.ipynb
  - visualize_dense_layer.ipynb
- conf.py
- images
- index.md
- license.md
- Makefile
- quick-start.md
- attentions.ipynb
- images
- README.md
- visualize_conv_filters.ipynb
- visualize_dense_layer.ipynb
- - __init__.py
  - attentions_test.py
  - conftest.py
  - gradcam_plus_plus_test.py
  - gradcam_test.py
  - saliency_test.py
  - scorecam_test.py
  - tf_keras_vis_test.py
- __init__.py
- - __init__.py
  - callbacks.py
  - input_modifiers.py
  - regularizers.py
- - __init__.py
  - callbacks.py
  - input_modifiers.py
  - losses.py
  - model_modifiers.py
  - regularizers.py
  - scores.py
  - test.py
- __init__.py
- gradcam.py
- gradcam_plus_plus.py
- layercam.py
- saliency.py
- scorecam.py
.gitignore
CITATION.cff
LICENSE
MANIFEST.in
README.md
setup.cfg
setup.py
VERSION

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# [tf-keras-vis](https://keisen.github.io/tf-keras-vis-docs/)

[![Downloads](https://pepy.tech/badge/tf-keras-vis)](https://pepy.tech/project/tf-keras-vis)
[![Python](https://img.shields.io/pypi/pyversions/tf-keras-vis.svg?style=plastic)](https://badge.fury.io/py/tf-keras-vis)
[![PyPI version](https://badge.fury.io/py/tf-keras-vis.svg)](https://badge.fury.io/py/tf-keras-vis)
[![Python package](https://github.com/keisen/tf-keras-vis/actions/workflows/python-package.yml/badge.svg)](https://github.com/keisen/tf-keras-vis/actions/workflows/python-package.yml)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
[![Documentation](https://img.shields.io/badge/api-reference-blue.svg)](https://keisen.github.io/tf-keras-vis-docs/)

## Web documents

https://keisen.github.io/tf-keras-vis-docs/

## Overview

tf-keras-vis is a visualization toolkit for debugging `keras.Model` in Tensorflow2.0+.
Currently supported methods for visualization include:

* Feature Visualization
   - ActivationMaximization ([web](https://distill.pub/2017/feature-visualization/), [github](https://github.com/raghakot/keras-vis))
* Class Activation Maps
   - GradCAM ([paper](https://arxiv.org/pdf/1610.02391v1.pdf))
   - GradCAM++ ([paper](https://arxiv.org/pdf/1710.11063.pdf))
   - ScoreCAM ([paper](https://arxiv.org/pdf/1910.01279.pdf), [github](https://github.com/haofanwang/Score-CAM))
   - Faster-ScoreCAM ([github](https://github.com/tabayashi0117/Score-CAM/blob/master/README.md#faster-score-cam))
   - LayerCAM ([paper](http://mftp.mmcheng.net/Papers/21TIP_LayerCAM.pdf), [github](https://github.com/PengtaoJiang/LayerCAM)) :new::zap:
* Saliency Maps
   - Vanilla Saliency ([paper](https://arxiv.org/pdf/1312.6034.pdf))
   - SmoothGrad ([paper](https://arxiv.org/pdf/1706.03825.pdf))

tf-keras-vis is designed to be light-weight, flexible and ease of use.
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 input images.
* Support the model that have either **multiple inputs** or **multiple outputs**, or both.
* Support the **mixed-precision** model.

And in ActivationMaximization,

* Support Optimizers that are built to keras.

### Visualizations

#### Dense Unit

#### Convolutional Filter

#### Class Activation Map

The images above are generated by `GradCAM++`.

#### Saliency Map

The images above are generated by `SmoothGrad`.

## Usage

### ActivationMaximization (Visualizing Convolutional Filter)

```python
import tensorflow as tf
from keras.applications import VGG16
from matplotlib import pyplot as plt
from tf_keras_vis.activation_maximization import ActivationMaximization
from tf_keras_vis.activation_maximization.callbacks import Progress
from tf_keras_vis.activation_maximization.input_modifiers import Jitter, Rotate2D
from tf_keras_vis.activation_maximization.regularizers import TotalVariation2D, Norm
from tf_keras_vis.utils.model_modifiers import ExtractIntermediateLayer, ReplaceToLinear
from tf_keras_vis.utils.scores import CategoricalScore

# Create the visualization instance.
# All visualization classes accept a model and model-modifier, which, for example,
#     replaces the activation of last layer to linear function so on, in constructor.
activation_maximization = \
   ActivationMaximization(VGG16(),
                          model_modifier=[ExtractIntermediateLayer('block5_conv3'),
                                          ReplaceToLinear()],
                          clone=False)

# You can use Score class to specify visualizing target you want.
# And add regularizers or input-modifiers as needed.
activations = \
   activation_maximization(CategoricalScore(FILTER_INDEX),
                           steps=200,
                           input_modifiers=[Jitter(jitter=16), Rotate2D(degree=1)],
                           regularizers=[TotalVariation2D(weight=1.0),
                                         Norm(weight=0.3, p=1)],
                           optimizer=keras.optimizers.RMSprop(1.0, 0.999),
                           callbacks=[Progress()])

## Since v0.6.0, calling `astype()` is NOT necessary.
# activations = activations[0].astype(np.uint8)

# Render
plt.imshow(activations[0])
```

### Gradcam++

```python
import numpy as np
from matplotlib import pyplot as plt
from matplotlib import cm
from tf_keras_vis.gradcam_plus_plus import GradcamPlusPlus
from tf_keras_vis.utils.model_modifiers import ReplaceToLinear
from tf_keras_vis.utils.scores import CategoricalScore

# Create GradCAM++ object
gradcam = GradcamPlusPlus(YOUR_MODEL_INSTANCE,
                          model_modifier=ReplaceToLinear(),
                          clone=True)

# Generate cam with GradCAM++
cam = gradcam(CategoricalScore(CATEGORICAL_INDEX),
              SEED_INPUT)

## Since v0.6.0, calling `normalize()` is NOT necessary.
# cam = normalize(cam)

plt.imshow(SEED_INPUT_IMAGE)
heatmap = np.uint8(cm.jet(cam[0])[..., :3] * 255)
plt.imshow(heatmap, cmap='jet', alpha=0.5) # overlay
```

Please see the guides below for more details:

### Getting Started Guides

* [Saliency and CAMs](https://keisen.github.io/tf-keras-vis-docs/examples/attentions.html)
* [Visualize Dense Layer](https://keisen.github.io/tf-keras-vis-docs/examples/visualize_dense_layer.html)
* [Visualize Convolutional Filer](https://keisen.github.io/tf-keras-vis-docs/examples/visualize_conv_filters.html)

**[NOTES]**
If you have ever used [keras-vis](https://github.com/raghakot/keras-vis), you may feel that tf-keras-vis is similar with keras-vis.
Actually tf-keras-vis derived from keras-vis, and both provided visualization methods are almost the same.
But please notice that tf-keras-vis APIs does NOT have compatibility with keras-vis.

## Requirements

* Python 3.7+
* Tensorflow 2.0+

## Installation

* PyPI

```bash
$ pip install tf-keras-vis tensorflow
```

* Source (for development)

```bash
$ git clone https://github.com/keisen/tf-keras-vis.git
$ cd tf-keras-vis
$ pip install -e .[develop] tensorflow
```

## Use Cases

* [chitra](https://github.com/aniketmaurya/chitra)
   * A Deep Learning Computer Vision library for easy data loading, model building and model interpretation with GradCAM/GradCAM++.

## Known Issues

* With InceptionV3, ActivationMaximization doesn't work well, that's, it might generate meaninglessly blur image.
* With cascading model, Gradcam and Gradcam++ don't work well, that's, it might occur some error. So we recommend to use FasterScoreCAM in this case.
* `channels-first` models and data is unsupported.

## ToDo

* Guides
   * Visualizing multiple attention or activation images at once utilizing batch-system of model
   * Define various score functions
   * Visualizing attentions with multiple inputs models
   * Visualizing attentions with multiple outputs models
   * Advanced score functions
   * Tuning Activation Maximization
   * Visualizing attentions for N-dim image inputs
*  We're going to add some methods such as below
   - Deep Dream
   - Style transfer

tf-keras-vis

File Explorer

Today's picks

Was this content helpful?

Recent Feedback

tf-keras-vis

File Explorer

Today's picks

Was this content helpful?

Recent Feedback

Download README