Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/keisen/tf-keras-vis
Neural network visualization toolkit for tf.keras
https://github.com/keisen/tf-keras-vis
activation-maximization deep-learning explainability explainable-ai explainable-ml grad-cam gradcam gradcam-plus-plus keras keras-vis keras-visualization python saliency saliency-maps score-cam tensorflow visualization xai xai-library
Last synced: 25 days ago
JSON representation
Neural network visualization toolkit for tf.keras
- Host: GitHub
- URL: https://github.com/keisen/tf-keras-vis
- Owner: keisen
- License: mit
- Created: 2019-10-31T06:47:41.000Z (about 5 years ago)
- Default Branch: master
- Last Pushed: 2024-03-25T11:49:03.000Z (8 months ago)
- Last Synced: 2024-09-27T13:41:02.282Z (about 1 month ago)
- Topics: activation-maximization, deep-learning, explainability, explainable-ai, explainable-ml, grad-cam, gradcam, gradcam-plus-plus, keras, keras-vis, keras-visualization, python, saliency, saliency-maps, score-cam, tensorflow, visualization, xai, xai-library
- Language: Python
- Homepage: https://keisen.github.io/tf-keras-vis-docs/
- Size: 86.8 MB
- Stars: 313
- Watchers: 8
- Forks: 45
- Open Issues: 34
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Citation: CITATION.cff
Awesome Lists containing this project
README
# [tf-keras-vis](https://keisen.github.io/tf-keras-vis-docs/)
[](https://pepy.tech/project/tf-keras-vis)
[](https://badge.fury.io/py/tf-keras-vis)
[](https://badge.fury.io/py/tf-keras-vis)
[](https://github.com/keisen/tf-keras-vis/actions/workflows/python-package.yml)
[](https://opensource.org/licenses/MIT)
[](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 `tf.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 tf.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 tensorflow.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=tf.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